Net Reservoir Discrimination through Multi-Attribute Analysis at Single Sample Scale

Net Reservoir Discrimination through Multi-Attribute Analysis at Single Sample Scale

By Jonathan Leal, Rafael Jerónimo, Fabian Rada, Reinaldo Viloria and Rocky Roden
Published with permission: First Break
Volume 37, September 2019

Abstract

A new approach has been applied to discriminate Net Reservoir using multi-attribute seismic analysis at single sample resolution, complemented by bivariate statistical analysis from petrophysical well logs. The combination of these techniques was used to calibrate the multi-attribute analysis to ground truth, thereby ensuring an accurate representation of the reservoir static properties and reducing the uncertainty related to reservoir distribution and storage capacity. Geographically, the study area is located in the south of Mexico. The reservoir rock consists of sandstones from the Upper Miocene age in a slope fan environment.

The first method in the process was the application of Principal Component Analysis (PCA), which was employed to identify the most prominent attributes for detecting lithological changes that might be associated with the Net Reservoir. The second method was the application of the Kohonen Self-Organizing Map (SOM) Neural Network Classification at voxel scale (i.e., sample rate and bin size dimensions from seismic data), instead of using waveform shape classification. The sample-level analysis revealed significant new information from different seismic attributes, providing greater insights into the characteristics of the reservoir distribution in a shaly sandstone. The third method was a data analysis technique based on contingency tables and Chi-Square test, which revealed relationships between two categorical variables (SOM volume neurons and Net Reservoir). Finally, a comparison between a SOM of simultaneous seismic inversion attributes and traditional attributes classification was made corroborating the delineated prospective areas. The authors found the SOM classification results are beneficial to the refinement of the sedimentary model in a way that more accurately identified the lateral and vertical distribution of the facies of economic interest, enabling decisions for new well locations and reducing the uncertainty associated with field exploitation. However, the Lithological Contrast SOM results from traditional attributes showed a better level of detail compared with seismic inversion SOM.

Introduction

Self-Organizing Maps (SOM) is an unsupervised neural network – a form of machine learning – that has been used in multi-attribute seismic analysis to extract more information from the seismic response than would be practical using only single attributes. The most common use is in automated facies mapping. It is expected that every neuron or group of neurons can be associated with a single depositional environment, the reservoir´s lateral and vertical extension, porosity changes or fluid content (Marroquín et al., 2009). Of course, the SOM results must be calibrated with available well logs. In this paper, the authors generated petrophysical labels to apply statistical validation techniques between well logs and SOM results. Based on the application of PCA to a larger set of attributes, a smaller, distilled set of attributes were classified using the SOM process to identify lithological changes in the reservoir (Roden et al., 2015).

A bivariate statistical approach was then conducted to reveal the relationship between two categorical variables: the individual neurons comprising the SOM classification volume and Net Reservoir determined from petrophysical properties (percentage of occurrence of each neuron versus Net Reservoir).

The Chi-Square test compares the behavior of the observed frequencies (Agresti, 2002) for each SOM neuron lithological contrast against the Net Reservoir variable (grouped in “Net Reservoir” and “no reservoir” categories). Additional data analysis was conducted to determine which neurons responded to the presence of hydrocarbons using box plots showing Water Saturation, Clay Volume, and Effective Porosity as Net Pay indicators. The combination of these methods demonstrated an effective means of identifying the approximate region of the reservoir.

About the Study Area

The reservoir rock consists of sandstones from the Upper Miocene age in a slope fan environment. These sandstones correspond to channel facies, and slope lobes constituted mainly of quartz and potassium feldspars cemented in calcareous material of medium maturity. The submarine slope fans were deposited at the beginning of the deceleration of the relative sea-level fall, and consist of complex deposits associated with gravitational mass movements.

Stratigraphy and Sedimentology

The stratigraphic chart comprises tertiary terrigenous rocks from Upper Miocene to Holocene. The litho-stratigraphic units are described in Table 1.

Table 1: Stratigraphic Epoch Chart of Study Area

 

Figure 1. Left: Regional depositional facies. Right: Electrofacies and theoretical model, Muti (1978).

Figure 1 (left) shows the facies distribution map of the sequence, corresponding to the first platform-basin system established in the region. The two dashed lines – one red and one dark brown – represent the platform edge at different times according to several regional integrated studies in the area. The predominant direction of contribution for studied Field W is south-north, which is consistent with the current regional sedimentary model. The field covers an area of approximately 46 km2 and is located in facies of distributary channels northeast of the main channel. The reservoir is also well-classified and consolidated in clay matrix, and it is thought that this texture corresponds to the middle portion of the turbidite system. The observed electrofacies logs of the reservoir are box-shaped in wells W-2, W-4, W-5, and W-6 derived from gamma ray logs and associated with facies of distributary channels that exhibit the highest average porosity. In contrast, wells W-3 and W-1 are different – associated with lobular facies – according to gamma ray logs. In Figure 1 (right), a sedimentary scheme of submarine fans proposed by Muti (1978).

Petrophysics

The Stieber model was used to classify Clay Volume (VCL). The Effective Porosity (PIGN) was obtained using the Neutron-Density model and non-clay water intergranular Water Saturation (SUWI) was determined to have a salinity of 45,000 ppm using the Simandoux model. Petrophysical cut-off values used to distinguish Net Reservoir and Net Pay estimations were 0.45, 0.10 and 0.65, respectively.

Reservoir Information

The reservoir rock corresponds to sands with Net Pay thickness ranging from 9-12 m, porosity between 18-25%, average permeability of 8-15 mD, and Water Saturation of approximately 25%. The initial pressure was 790 kg / cm2 with the current pressure is 516 kg/cm2. The main problems affecting productivity in this volumetric reservoir are pressure drop, being the mechanism of displacement the rock-fluid expansion, and gas in solution. Additionally, there are sanding problems and asphaltene precipitation.

Methodology

Multidisciplinary information was collected and validated to carry out seismic multi-attribute analysis. Static and dynamic characterization studies were conducted in the study area, revealing the most relevant reservoir characteristics and yielding a better sense of the proposed drilling locations. At present, six wells have been drilled.

The original available seismic volume and associated gathers employed in the generation of multiple attributes and for simultaneous inversion were determined to be of adequate quality. At target depth, the dominant frequency approaches 14 Hz, and the interval velocity is close to 3,300 m/s. Therefore, the vertical seismic resolution is 58 m. The production sand has an average thickness of 13 m, so it cannot be resolved with conventional seismic amplitude data.

Principal Component Analysis (PCA)

Principal Component Analysis (PCA) is one of the most common descriptive statistics procedures used to synthesize the information contained in a set of variables (volumes of seismic attributes) and to reduce the dimensionality of a problem. Applied to a collection of seismic attributes, PCA can be used to identify the seismic attributes that have the greatest “contribution,” based on the extent of their relative variance to a region of interest. Attributes identified through the use of PCA are responsive to specific geological features, e.g., lithological contrast, fracture zones, among others. The output of PCA is an Eigen spectrum that quantifies the relative contribution or energy of each seismic attribute to the studied characteristic.

PCA Applied for Lithological Contrast Detection

The PCA process was applied to the following attributes to identify the most significant attributes to the region to detect lithological contrasts at the depth of interest: Thin Bed Indicator, Envelope, Instantaneous Frequency, Imaginary Part, Relative Acoustic Impedance, Sweetness, Amplitude, and Real Part. Of the entire seismic volume, only the voxels in a time window (seismic samples) delimited by the horizon of interest were analyzed, specifically 56 milliseconds above and 32 milliseconds below the horizon. The results are shown for each principal component. In this case, the criterion used for the selected attributes were those whose maximum percentage contribution to the principle component was greater than or equal to 80%. Using this selection technique, the first five principal components were reviewed in the Eigen spectrum. In the end, six (6) attributes of the first two principal components were selected (Figure 2).

Figure 2. PCA results for lithological contrast detection.

Simultaneous Classification of Seismic Attributes Using a Self-Organizing Maps (SOM) Neural Network (Voxel Scale)

The SOM method is an unsupervised classification process in that the network is trained from the input data alone. A SOM consists of components (vectors) called neurons or classes and input vectors that have a position on the map. The values are compared employing neurons that are capable of detecting groupings through training (machine learning) and mapping. The SOM process non-linearly maps the neurons to a two dimensional, hexagonal or rectangular grid. SOM describes a mapping of a larger space to a smaller one. The procedure for locating a vector from the data space on the map is to find the neuron with the vector of weights (smaller metric distance) closer to the vector of the data space. (The subject of this analysis accounted for seismic samples located within the time window covering several samples above and below the target horizon throughout the study area). It is important to classify attributes that have the same common interpretive use, such as lithological indicators, fault delineation, among others. The SOM revealed patterns and identified natural organizational structures present in the data that are difficult to detect in any other way (Roden et al., 2015), since the SOM classification used in this study is applied on individual samples (using sample rate and bin size from seismic data, Figure 2, lower right box), detecting features below conventional seismic resolution, in contrast with traditional wavelet-based classification methods.

SOM Classification for Lithological Contrast Detection

The following six attributes were input to the SOM process with 25 classes (5 X 5) stipulated as the desired output: Envelope, Hilbert, Relative Acoustic Impedance, Sweetness, Amplitude, and Real Part.

As in the PCA analysis, the SOM was delimited to seismic samples (voxels) in a time window following the horizon of interest, specifically 56 milliseconds above to 32 milliseconds below. The resulting SOM classification volume was examined with several visualization and statistical analysis techniques to associate SOM classification patterns with reservoir rock.

3D and Plan Views

One way of identifying patterns or trends coherent with the sedimentary model of the area is visualizing all samples grouped by each neuron in 3D and plan views using stratal-slicing technique throughout the reservoir. The Kohonen SOM and the 2D Colormap in Figure 3 (lower right) ensures that the characteristics of neighboring neurons are similar. The upper part of Figure 3 shows groupings classified by all 5x5 (25) neurons comprising the neural network, while in the lower part there are groupings interpreted to be associated with the reservoir classified by a few neurons that are consistent with the regional sedimentary model, i.e., neurons N12, N13, N16, N17, N22, and N23.

Figure 3. Plan view with geological significance preliminary geobodies from Lithological Contrast SOM. Below: only neurons associated with reservoir are shown.

Vertical Seismic Section Showing Lithological Contrast SOM

The observed lithology in the reservoir sand is predominantly made up of clay sandstone. A discrete log for Net Reservoir was generated to calibrate the results of the Lithological Contrast SOM, using cut-off values according to Clay Volume and Effective Porosity. Figure 4 shows the SOM classification of Lithological Contrast with available well data and plan view. The samples grouped by neurons N17, N21, and N22 match with Net Reservoir discrete logs. It is notable that only the well W-3 (minor producer) intersected the samples grouped by the neuron N17 (light blue). The rest of the wells only intersected neurons N21 and N22. It is important to note that these features are not observed on the conventional seismic amplitude data (wiggle traces).

Figure 4. Vertical section composed by the SOM of Lithological Contrast, Amplitude attribute (wiggle), and Net Reservoir discrete property along wells.

Stratigraphic Well Section

A cross-section containing the wells (Figure 5) shows logs of Gamma Ray, Clay Volume, perforations, resistivity, Effective Porosity, Net Reservoir with lithological contrast SOM classification, and Net Pay.
The results of SOM were compared by observation with discrete well log data, relating specific neurons to the reservoir. At target zone depth, only the neurons N16, N17, N21, and N22 are present. It is noteworthy that only W-3 well (minor producer) intersect clusters formed by neuron N17 (light blue). The rest of the wells intersect neurons N16, N21, N22, and N23.

Statistical Analysis Vertical Proportion Curve (VPC)

Traditionally, Vertical Proportion Curves (VPC) are qualitative and quantitative tools used by some sedimentologists to define succession, division, and variability of sedimentary sequences from well data, since logs describe vertical and lateral evolution of facies (Viloria et al., 2002). A VPC can be modeled as an accumulative histogram where the bars represent the facies proportion present at a given level in a stratigraphic unit. As part of the quality control and revision of the SOM classification volume for Lithological Contrasts, this statistical technique was used to identify whether in the stratigraphic unit or in the window of interest, a certain degree of succession and vertical distribution of specific neurons observed could be related to the reservoir.

The main objective of this statistical method is to identify how specific neurons are vertically concentrated along one or more logs. As an illustration of the technique, a diagram of the stratigraphic grid is shown in Figure 6. The VPC was extracted from the whole 3D grid of SOM classification volume for Lithological Contrast, and detection was generated by counting the occurrence among the 25 neurons or classes in each stratigraphic layer in the VPC extracted from the grid. The VPC of SOM neurons exhibits remarkable slowly-varying characteristics indicative of geologic depositional patterns. The reservoir top corresponds to stratigraphic layer No. 16. In the VPC on the right, only neurons N16, N17, N21, and N22 are present. These neurons have a higher percentage occurrence relative to all 25 classes from the top of the target sand downwards. Corroborating the statistics, these same neural classes appear in the map view in Figure 3 and the vertical section shown in Figure 4. The stratigraphic well section in Figure 5 also supports the statistical results. It is important to note that these neurons also detected seismic samples above the top of the sand top, although in a lesser proportion. This effect is consistent with the existence of layers with similar lithological characteristics, which can be seen from the well logs.

Figure 6. Vertical proportion Curve to identify neurons related to reservoir rock.

Bivariate Statistical Analysis Cross Tabs

The first step in this methodology is a bivariate analysis through cross-tabs (contingency table) to determine if two categorical variables are related based on observing the extent to which the occurrence of one variable is repeated in the categories of the second. Given that one variable is analyzed in terms of another, a distinction must be made between dependent and independent variables. With cross tabs analysis, the possibilities are extended to (in addition to frequency analyzes for each variable, separately) the analyses of the joint frequencies or those in which the analysis unit nature is defined by the combination of two variables.

The result was obtained by extracting the SOM classification volume along wells paths and constructing a discrete well log with two categories: “Net Reservoir” and “not reservoir.” The distinction between “Net Reservoir” and “not reservoir” simply means that the dependent variable might have a hydrocarbon storage capacity or not. In this case, the dependent variable corresponds to neurons of SOM classification for Lithological Contrast volume. It is of ordinal type, since it has an established internal order, and the change from one category to another is not the same. The neurons go from N1 to N25, organized in rows. The independent variable is Net Reservoir, which is also an ordinal type variable. In this tab, the values organized in rows correspond to neurons from the SOM classification volume for Lithological Contrast, and in the columns are discrete states of the “Net Reservoir” and “not reservoir” count for each neuron. Table 2 shows that the highest Net Reservoir counts are associated with neurons N21 and N22 at 47.0% and 28.2% respectively. Conversely, lower counts of Net Reservoir are associated with neurons N17 (8.9%), N16 (7.8%) and N23 (8.0%).

Table 2. Cross Tab for Lithological Contrast SOM versus Net reservoir.

Neuron N21 was detected at reservoir depth in wells W-2 (producer), W-4 (abandoned for technical reasons during drilling), W-5 (producer) and W-6 (producer). N21 showed higher percentages of occurrence in Net Reservoir, so this neuron could be identified as indicating the highest storage capacity. N22 was present in wells W-1 and W-6 at target sand depth but also detected in wells W-2, W-4 and W-5 in clay-sandy bodies overlying the highest quality zone in the reservoir. N22 was also detected in the upper section of target sand horizontally navigated by the W-6 well, which has no petrophysical evaluation. N17 was only detected in well W-3, a minor producer of oil, which was sedimentologically cataloged as lobular facies and had the lowest reservoir rock quality. N16 was detected in a very small proportion in wells W-4 (abandoned for technical reasons during drilling) and W-5 (producer). Finally, N23 was only detected towards the top of the sand in well W-6, and in clayey layers overlying it in the other wells. This is consistent with the observed percentage of 8% Net Reservoir, as shown in Table 2.

Chi-Square Independence Hypothesis Testing

After applying the cross-tab evaluation, this classified information was the basis of a Chi-Square goodness-of-fit test to assess the independence or determine the association between two categorical variables: Net Reservoir and SOM neurons. That is, it aims to highlight the absence of a relationship between the variables. The Chi-Square test compared the behavior of the observed frequencies for each Lithological Contrast neuron with respect to the Net Reservoir variable (grouped in “Net Reservoir” and “no reservoir”), and with the theoretically expected frequency distribution when the hypothesis is null.

As a starting point, the null hypothesis formulation was that the Lithological Contrast SOM neuron occurrences are independent of the presence of Net Reservoir. If the calculated Chi-Square value is equal to or greater than a certain critical theoretical value, the null hypothesis must be rejected. Consequently, the alternative hypothesis must be accepted. Observe the results in Table 3 where the calculated Chi-Square is greater than the theoretical critical value (296 ≥ 9.4, with four degrees of freedom and 5% confidence level), so the null hypothesis of the independence of Net Pay with SOM neurons is rejected, leaving a relationship between Net Reservoir and Lithological Contrast SOM variables.

The test does not report a goodness of fit magnitude (substantial, moderate or poor), however. To measure the degree of correlation between both variables, Pearson’s Phi (φ) and Cramer’s V (ν) measures were computed. Pearson’s φ coefficient was estimated from Eq. 1.1.

Eq. 1.1

where X2: Chi-Square and n : No. of cases

Additionally, Cramer’s V was estimated using Eq. 1.2.

Eq. 1.2

In both cases, values near zero indicate a poor or weak relationship while values close to one indicate a strong relation. The authors obtained values for φ, and Cramer´s ν equals to 0.559 (Table 3). Based on this result, we can interpret a moderate relation between both variables.

Table 3. Calculated and theoretical Chi-Square values and its correlation measures.

Box-and-Whisker Plots

Box-and-whisker plots were constructed to compare and understand the behavior of petrophysical properties for the range that each neuron intersects the well paths in the SOM volume. Also, these quantify which neurons of interest respond to Net Reservoir and Net Pay properties (Figure 7). Five descriptive measures are shown for a box-and-whisker plot of each property:

• Median (thick black horizontal line)
• First quartile (lower limit of the box)
• Third quartile (upper limit of the box)
• Maximum value (upper end of the whisker)
• Minimum value (lower end of the whisker)

The graphs provide information about data dispersion, i.e., the longer the box and whiskers, the greater the dispersion and also data symmetry. If the median is relatively centered of the box, the distribution is symmetrical. If, on the contrary, it approaches the first or third quartile, the distribution could be skewed to these quartiles, respectively. Finally, these graphs identify outlier observations that depart from the rest of the data in an unusual way (these are represented by dots and asterisks as less or more distant from the data center). Horizontal dashed green line is the cut-off value for Effective Porosity (PIGN >0.10) while the dashed blue line represents the cut-off value for Clay Volume (VCL>0.45) and, dashed beige line is cut-off value for Water Saturation (SUWI<0.65).

Based on these data and the resulting analysis, it can be inferred that neurons N16, N17, N21, N22, and N23 respond positively to Net Reservoir. Of these neurons, the most valuable predictors are N21 and N22 since they present lower clay content in comparison with neurons N16 and N23 and associated higher Effective Porosity shown by neurons N16, N17, and N23 (Figure 7a). Neurons N21 and N22 are ascertained to represent the best reservoir rock quality. Finally, neuron N23 (Figure 7b), can be associated with rock lending itself with storage capacity, but clayey and with high Water Saturation, which allows discarding it as a significant neuron. It is important to note that this analysis was conducted by accounting for the simultaneous occurrence of the petrophysical values (VCL, PIGN, and SUWI) on the neurons initially intersected (Figure 7a), and then on the portion of the neurons that pass Net Reservoir cut-off values (Figure 7b), and finally on the portion of the neurons that pass net-pay cut-off values (Figure 7c). For all these petrophysical reasons, the neurons to be considered as a reference to estimate the lateral and vertical distribution of Net Reservoir associated with the target sand are in order of importance, N21, N22, N16, and N17.

Figure 7. Comparison between neurons according to petrophysical properties: VCL (Clay Volume), PIGN (Effective Porosity) and SUWI (Water Saturation). a) SOM neurons for lithological contrast detection, b) Those that pass Net Reservoir cut-off and c) Those that pass Net Pay cut-off.

Simultaneous Seismic Inversion

During this study, a simultaneous prestack inversion was performed using 3D seismic data and sonic logs, in order to estimate seismic petrophysical attributes as Acoustic Impedance (Zp), Shear Impedance (Zs), Density (Rho), as well as P&S-wave velocities, among others. They are commonly used as lithology indicators, possible fluids, and geomechanical properties. Figure 8a shows a scatter plot from well data of seismic attributes Lambda Rho and Mu Rho ratio versus Clay Volume (VCL) and as discriminator Vp/Vs ratio (Vp/Vs). The target sand corresponds to low Vp/Vs and Lambda/Mu values (circled in the figure). Another discriminator in the reservoir was S-wave impedance (Zs) (Figure 8b). From this, seismic inversion attributes were selected for classification by SOM neural network analysis. These attributes were Vp/Vs ratio, Lambda Rho/Mu Rho ratio, and Zs.

Figure 8. Scatter plots: a) Lambda Rho and Mu Rho ratio versus VCL and Vp/Vs y b) Zs versus VCL and Vp/Vs.

Self-Organizing Map (SOM) Comparison

Figure 9 is a plan view of neuron-extracted geobodies associated with the sand reservoir. In the upper part, a SOM classification for Lithological Contrast detection obtained from six traditional seismic attributes is shown; and in the lower part, a different SOM classification for Lithological Contrast detection was obtained from three attributes of simultaneous inversion. Both results are very similar. The selection of SOM classification neurons from inversion attributes was done through spatial pattern recognition, i.e., identifying geometry/shape of the clusters related to each of 25 neurons congruent with the sedimentary model, and by using a stratigraphic section for wells that includes both SOM classifications tracks.

Figure 9. Plan view of neurons with geological meaning. Up: SOM Classification from traditional attributes. Down: SOM Classification from simultaneous inversion attributes.

Figure 10 shows a well section that includes a track for Net Reservoir and Net Pay classification along with SOM classifications from traditional attributes and a second SOM from simultaneous inversion attributes defined from SOM volumes and well paths intersection. In fact, only the neurons numbers with geological meaning are shown.

Figure 10. Well section showing the target zone with tracks for discrete logs from Net Reservoir, Net Pay and both SOM classifications.

Discussion and Conclusions

Principal Component Analysis (PCA) identified the most significant seismic attributes to be classified by Self-Organizing Maps (SOM) neural network at single-sample basis to detect features associated with lithological contrast and recognize lateral and vertical extension in the reservoir. The interpretation of SOM classification volumes was supported by multidisciplinary sources (geological, petrophysical, and dynamic data). In this way, the clusters detected by certain neurons became the inputs for geobody interpretation. The statistical analysis and visualization techniques enabled the estimation of Net Reservoir for each neuron. Finally, the extension of reservoir rock geobodies derived from SOM classification of traditional attributes was corroborated by the SOM acting on simultaneous inversion attributes. Both multi-attribute machine learning analysis of traditional attributes and attributes of seismic inversion enable refinement of the sedimentary model to reveal more precisely the lateral and vertical distribution of facies. However, the Lithological Contrast SOM results from traditional attributes showed a better level of detail compared with seismic inversion SOM.

Collectively, the workflow may reduce uncertainty in proposing new drilling locations. Additionally, this methodology might be applied using specific attributes to identify faults and fracture zones, identify absorption phenomena, porosity changes, and direct hydrocarbon indicator features, and determine reservoir characteristics.

Acknowledgments

The authors thank Pemex and Oil and Gas Optimization for providing software and technical resources. Thanks also are extended to Geophysical Insights for the research and development of the Paradise® AI workbench and the machine learning applications used in this paper. Finally, thank Reinaldo Michelena, María Jerónimo, Tom Smith, and Hal Green for review of the manuscript.

References

Agresti, A., 2002, Categorical Data Analysis: John Wiley & Sons.

Marroquín I., J.J. Brault and B. Hart, 2009, A visual data mining methodology to conduct seismic facies analysis: Part 2 – Application to 3D seismic data: Geophysics, 1, 13-23.

Roden R., T. Smith and D. Sacrey, 2015, Geologic pattern recognition from seismic attributes: Principal component analysis and self-organizing maps: Interpretation, 4, 59-83.

Viloria R. and M. Taheri, 2002, Metodología para la Integración de la Interpretación Sedimentológica en el Modelaje Estocástico de Facies Sedimentarias, (INT-ID-9973, 2002). Technical Report INTEVEP-PDVSA.

Machine Learning Applied to 3D Seismic Data from the Denver-Julesburg Basin Improves Stratigraphic Resolution in the Niobrara

Machine Learning Applied to 3D Seismic Data from the Denver-Julesburg Basin Improves Stratigraphic Resolution in the Niobrara

By Carolan Laudon, Sarah Stanley, Patricia Santogrossi 
Published with permission: Unconventional Resources Technology Conference (URTeC 2019)
July 2019

Abstract

Seismic attributes can be both powerful and challenging to incorporate into interpretation and analysis. Recent developments with machine learning have added new capabilities to multi-attribute seismic analysis. In 2018, Geophysical Insights conducted a proof of concept on 100 square miles of multi-client 3D data jointly owned by Geophysical Pursuit, Inc. (GPI) and Fairfield Geotechnologies (FFG) in the Denver-Julesburg Basin (DJ). The purpose of the study was to evaluate the effectiveness of a machine learning workflow to improve resolution within the reservoir intervals of the Niobrara and Codell formations, the primary targets for development in this portion of the basin.

The seismic data are from Phase 5 of the GPI/Fairfield Niobrara program in northern Colorado. A preliminary workflow which included synthetics, horizon picking and correlation of 28 wells was completed. The seismic volume was re-sampled from 2 ms to 1 ms. Detailed well time-depth charts were created for the Top Niobrara, Niobrara A, B and C benches, Fort Hays and Codell intervals. The interpretations, along with the seismic volume, were loaded into the Paradise® machine learning application, and two suites of attributes were generated, instantaneous and geometric. The first step in the machine learning workflow is Principal Component Analysis (PCA). PCA is a method of identifying attributes that have the greatest contribution to the data and that quantifies the relative contribution of each. PCA aids in the selection of which attributes are appropriate to use in a Self-Organizing Map (SOM). In this case, 15 instantaneous attribute volumes, plus the parent amplitude volume, were used in the PCA and eight were selected to use in SOMs. The SOM is a neural network-based machine learning process that is applied to multiple attribute volumes simultaneously. The SOM produces a non-linear classification of the data in a designated time or depth window.

For this study, a 60-ms interval that encompasses the Niobrara and Codell formations was evaluated using several SOM topologies. One of the main drilling targets, the B chalk, is approximately 30 feet thick; making horizontal well planning and execution a challenge for operators. An 8 X 8 SOM applied to 1 ms seismic data improves the stratigraphic resolution of the B bench. The neuron classification also images small but significant structural variations within the chalk bench. These variations correlate visually with the geometric curvature attributes. This improved resolution allows for precise well planning for horizontals within the bench. The 25 foot thick C bench and the 17 to 25 foot thick Codell are also seismically resolved via SOM analysis. Petrophysical analyses from wireline logs run in seven wells within the survey by Digital Formation; together with additional results from SOMs show the capability to differentiate a high TOC upper unit within the A marl which presents an additional exploration target. Utilizing 2D color maps and geobodies extracted from the SOMs combined with petrophysical results allows calculation of reserves for the individual reservoir units as well as the recently identified high TOC target within the A marl.

The results show that a multi-attribute machine learning workflow improves the seismic resolution within the Niobrara reservoirs of the DJ Basin and results can be utilized in both exploration and development.

Introduction and preliminary work

The Denver-Julesburg Basin is an asymmetrical foreland basin that covers approximately 70,000 square miles over parts of Colorado, Wyoming, Kansas and Nebraska. The basin has over 47,000 oil and gas wells with a production history that dates back to 1881 (Higley, 2015). In 2009, operators in the Wattenberg field began to drill and complete horizontal wells in the chalk benches of the Niobrara formation and within the Codell sandstone. As of October 2018, approximately 9500 horizontal wells have been drilled and completed within Colorado and Wyoming in the Niobrara and Codell formations (shaleprofile.com/2019/01/29/niobrara-co-wy-update-through-october-2018).

The transition to horizontal drilling necessitated the acquisition of modern, 3D seismic data (long offset, wide azimuth) to properly image the complex faulting and fracturing within the basin. In 2011, Geophysical Pursuit, Inc., in partnership with the former Geokinetics Inc., embarked on a multi-year, multi-client seismic program that ultimately resulted in the acquisition of 1580 square miles of contiguous 3D seismic data. In 2018, Geophysical Pursuit, Inc. (GPI) and joint-venture partner Fairfield Geotechnologies (FFG) provided Geophysical Insights with seismic data in the Denver-Julesburg Basin to conduct a proof of concept evaluation of the effectiveness of a machine learning workflow to improve resolution within the reservoir intervals of the Niobrara and Codell formations, currently the primary targets for development in this portion of the basin. The GPI/FFG seismic data analyzed are 100 square miles from the Niobrara Phase 5 multi-client 3D program in northern Colorado (Figure 1). Prior to the machine learning workflow, a preliminary interpretation workflow was carried out, that included synthetics, horizon picking and well correlation on 28 public wells with digital data. The seismic volume was resampled from 2 ms to 1 ms. Time depth charts were made with detailed well ties for the Top Niobrara, Niobrara A, B, and C benches, Fort Hays and Codell. The interpretations, along with the re-sampled seismic amplitude volume, were loaded into the Paradise® machine learning application. The machine learning software has several options for computing seismic attributes, and two suites were selected for the study: standard instantaneous attributes and geometric attributes from the AASPI (Attribute Assisted Seismic Processing and Interpretation) consortium (http://mcee.ou.edu/aaspi/).

Figure 1: Map of GPI FFG multi-client program and study area outline

Geologic Setting of the Niobrara and Surrounding Formations

The Niobrara formation is late Cretaceous in age and was deposited in the Western Interior Seaway (Kaufmann, 1977). The Niobrara is subdivided into the basal Fort Hays limestone and the Smoky Hill member. The Smoky Hill member is further subdivided into three subunits informally termed Niobrara A, B, and C. These units consist of fractured chalk benches which are primary reservoirs with marls and shales between the benches which comprise source rocks and secondary reservoir targets. (Figure 2). The Niobrara unconformably overlies the Codell sandstone and is overlain by the Sharon Springs member of the Pierre shale.

The Codell is also late Cretaceous in age, and unconformably underlies the Fort Hays member of the Niobrara formation. In general, the Codell thins from north to south due to erosional truncation (Sterling, Bottjer and Smith, 2016). In the study area, the thickness of the Codell ranges from 18 to 25 feet. Lewis (2013) inferred an eastern provenance for the Codell with a limited area of deposition or subsequent erosion through much of the DJ Basin. Based upon geochemical analyses, Sterling and others (2016) state that hydrocarbons produced from the Codell are sourced from the Niobrara, primarily the C marl, and the thermal maturity provides evidence of migration into the Codell. The same study found that oil produced from the Niobrara C chalk was generated in-situ.

Figure 2 (Sonnenberg, 2015) shows a generalized stratigraphic column and a structure map for the Niobrara in the DJ Basin along with an outline of the DJ basin and the location of the Wattenberg Field within which the study area is contained.

Figure 2: Outline of the DJ Basin with Niobrara structure contours and generalized stratigraphic column that shows the source rock and reservoir intervals for late Cretaceous units in the basin (from Sonnenberg, 2015).

Figure 3 shows the structural setting of the Niobrara in the study area, as well as types of fractures which can be expected to provide storage capacity and permeability for reservoirs within the chalk benches (Friedman and others, 1992). The study area covers approximately 100 square miles and shows large antiforms on the western edge. The area is normally faulted with most faults trending northeast to southwest. The Top Niobrara time structure also shows extensive small-scale structural relief which is visualized in a curvature attribute volume as shown in Figure 4. This implies that a significant amount of fracturing is present within the Niobrara.

Figure 3: Gross structure of the Niobrara in the study area in seismic two-way travel time. Insets from Friedman and others, 1992, showing predicted fracture types from structural elements. Area shown is approximately 100 square miles.

Figure 4: Most positive curvature, K1 on top Niobrara. The faulting and fractures are complex with both NE-SW and NW-SE trends apparent. Area shown is approximately 100 square miles. Seismic data provided courtesy of GPI and FFG.

Meissner and others (1984) and Landon and others (2001) have stated that the Niobrara formation kerogen is Type-II and oil-prone. Landon and others, and Finn and Johnson (2005) have also stated that the DJ basin contains the richest Niobrara source rocks with TOC contents reaching eight weight percent. Niobrara petroleum production is dependent on fractures in the hard, brittle, carbonate-rich zones. These zones are overlain and/or interbedded with soft, ductile marine shales that inhibit migration and seal the hydrocarbons in the fractured zones.

Why Utilize Machine Learning?

In the study area, the Niobrara to Greenhorn section is represented in approximately 60 milliseconds of two-way travel time in the seismic data. Figure 5 shows an amplitude section through a well within the study area. Figure 6 is an index map of wells used in the study with the Anderson 11-2 well highlighted in red. It is apparent that the top Niobrara is a well resolved positive amplitude or peak which can be picked on either a normal amplitude section or an instantaneous phase display. The individual units within the Niobrara A bench, A marl, B bench, B marl, C bench, C marl, Fort Hays and Codell present a significant challenge for an interpreter to resolve using only one or two attributes. The use of simultaneous multiple seismic attributes holds promise to resolve thin beds and a machine learning approach is one methodology which has been documented to successfully resolve stratigraphy below tuning (Roden and others, 2015, Santogrossi, 2017).

Figure 5: Amplitude section shows the approximately 60 milliseconds between marked horizons which contain the Niobrara and Codell reservoirs. Trace spacing is 110 feet, vertical scale is two-way time in seconds. Seismic data are shown courtesy of GPI and FFG.

Figure 6: Index map of vertical wells used in study. The dashed lines connect well names to well locations. Wells were obtained from the Colorado Oil and Gas Conservation Commission public database.

Machine Learning Data Preparation

The Niobrara Phase 5 3D data used for this study consisted of a 32-bit seismic amplitude volume that covers approximately 100 square miles. The survey contained 5.118 seconds of data with a bin spacing of 110 feet. Machine learning classifications benefit from sharper natural clusters of information through one level of finer trace sampling. Machine learned seismic resolution also benefits from sample-by-sample classification when compared to conventional wavelet analysis. Therefore, the data were upsampled to 1 ms from its original 2 ms interval by Geophysical Insights. The 1 ms amplitude data were used for seismic attribute generation.

Focus should be placed on the time interval that encompasses the geologic units of interest. The time interval selected for this study was 0.5 seconds to 2.2 seconds.

A total of 44 digital wells were obtained, 40 of which were within the seismic survey.

Classification by Principal Component Analysis (PCA)

Multi-dimensional analysis and multi-attribute analysis go hand in hand. Because individuals are grounded in three-dimensional space, it is difficult to visualize what data in a higher number dimensional space looks like. Fortunately, mathematics doesn’t have this limitation and the results can be easily understood with conventional 2D and 3D viewers.

Working with multiple instantaneous or geometric seismic attributes generates tremendous volumes of data. These volumes contain huge numbers of data points which may be highly continuous, greatly redundant, and/or noisy. (Coleou et al., 2003). Principal Component Analysis (PCA) is a linear technique for data reduction which maintains the variation associated with the larger data sets (Guo and others, 2009; Haykin, 2009; Roden and others, 2015). PCA has the ability to separate attribute types by frequency, distribution, and even character. PCA technology is used to determine which attributes to use and which may be ignored due to their very low impact on neural network solutions.

Figure 7 illustrates the analysis of a data cluster in two directions offset by 90 degrees. The first principal component (eigenvector 1) analyses the data cluster along the longest axis. The second principal component (eigenvector 2) analyses the data cluster variations perpendicular to the first principal component. As stated in the diagram, each eigenvector is associated with an eigenvalue which shows how much variance is in the data.

Figure 7: 2 attribute data set demonstrating the concept of PCA

Eigenvectors and eigenvalues from inline 1683 were consistently used for Principal Component Analysis because line 1683 bisected the deepest well in the study area. The entire pre-Niobrara, Niobrara, Codell, and post-Niobrara depositional events were present in the borehole.

PCA results for the first two eigenvectors for the interval Top Niobrara to Top Greenhorn are shown in Figure 8. Results show the most significant attributes in the first eigenvector are Sweetness, Envelope, and Relative Acoustic Impedance; each contributes approximately 60% of the maximum value for the eigenvector. PCA results for the second eigenvector show Thin Bed and Instantaneous Frequency are the most significant attributes. Figure 9 shows instantaneous attributes from the first eigenvector (sweetness) and second eigenvector (thin bed indicator) extracted near the B chalk of the Niobrara. The table shown in Figure 9 lists the instantaneous attributes that PCA indicated contain the most significance in the survey and the eigenvector associated with the attribute. This selection of attributes comprises a ‘recipe’ for input to the Self-Organizing Maps for the interval Niobrara to Greenhorn.

Figure 8: Eigenvalue charts for Eigenvectors 1 and 2 from PCA for Top Niobrara to Top Greenhorn. Attributes that contribute more than 50% of the maximum were selected for input to SOM

Figure 9: Instantaneous attributes near the Niobrara B chalk. These are prominent attributes in Eigenvectors 1 and 2. On the right of the figure is a list of eight selected attributes for SOM analysis. Seismic data is shown courtesy of GPI and FFG.

Self-Organzing Maps

Teuvo Kohonen, a Finnish mathematician, invented the concepts of Self-organizing Maps (SOM) in 1982 (Kohonen, T., 2001). Self-Organizing Maps employ the use of unsupervised neural networks to reduce very high dimensions of data to a scale that can be easily visualized (Roden and others, 2015). Another important aspect of SOMs is that every seismic sample is used as input to classification as opposed to wavelet-based classification.

Figures 10 and 11 illustrate classification by SOM. Within the 3D seismic survey, samples are first organized into attribute points with similar properties called natural clusters in attribute space. Within each cluster new, empty, multi-attribute samples, named neurons, are introduced. The SOM neurons will seek out natural clusters of like characteristics in the seismic data and produce a 2D mesh that can be illustrated with a two- dimensional color map.

Figure 10: Example SOM classification of two attributes into 4 clusters (neurons)

In other words, the neurons “learn” the characteristics of a data cluster through an iterative process (epochs) of cooperative then competitive training. When the learning is completed each unique cluster is assigned to a neuron number and each seismic sample is now classified (Smith, 2016).

Figure 11: Illustration of how SOM works with 3D seismic volumes

Note that the two-dimensional color map in Figure 11 shows an 8X8 topology. Topology is important. The finer the topology of the two-dimensional color map the finer the data clusters associated with each neuron become. For example: an 8X8 topology distributes 64 neurons throughout an attribute set, while a 12X12 topology distributes 144 neurons. Finer topologies help to refine variations in lithologies, porosity, and other reservoir characteristics. Although there is no theoretical limit to a two-dimensional map topology, experience has shown that there is a practical limit to the number of neuron topologies for geological resolution. Conversely, a coarser neuron topology is associated with much larger data clusters and helps to define structural features. For the Niobrara project an 8X8 topology appeared to give the best stratigraphic resolution for instantaneous attributes and a 5X5 topology resolved the geometric attributes most effectively.

SOM Results for the Survey and their Interpretation

The SOM topology selected to best resolve the sub-Niobrara stratigraphy from the eight instantaneous attributes is an 8X8 hexagonal which yields 64 individual neurons. The SOM interval selected was Top Niobrara to Top Greenhorn. The next sequence of figures highlights the improved resolution provided by the SOM when compared to the original amplitude data. Figure 12 shows a north-south inline through the survey and through the Rotharmel 11-33 well which was one of the wells selected for petrophysical analysis. The original amplitude data is shown along with the SOM result for the interval.

Figure 12: North-South inline showing the original amplitude data (upper) and the 8X8 SOM result (lower) from Top Niobrara through Greenhorn horizons. Seismic data is shown courtesy of GPI and FFG.

The next image, Figure 13, zooms into the SOM and highlights the correlation with lithology from petrophysical analysis. The B chalk is noted by a stacked pattern of yellow-red-yellow neurons, with the red representing the maximum carbonate content within the middle of the chalk bench.

Figure 13: 8X8 Instantaneous SOM through Rotharmel 11-33 with well log composite. The B bench, highlighted in green on the wellbore, ties the yellow-red-yellow sequence of neurons. Seismic data is shown courtesy of GPI and FFG.

One can see on the SOM the sweet spot within the B chalk and that there is a fair amount of small-scale structural relief present. These results aid in the resolution of structural offset within the reservoir away from well control which is critical for staying in a 20 to 30 foot zone when drilling horizontally. Each classified sample is 1 ms in thickness which converted to depth equates to roughly 7 feet.

Figure 14 shows the K2 curvature attribute co-rendered with the SOM results in vertical sections. The Rotharmel 11-33 is at the intersection of the vertical sections. The curvature is extracted at the middle of the B chalk and shows good agreement with the SOM. The entire B bench is represented by only 5-6 ms of seismic data.

Figure 14: Most negative curvature, K2 rendered at the middle of the B chalk. Vertical sections are an 8X8 instantaneous SOM Top Niobrara to Top Greenhorn. Seismic data is shown courtesy of GPI and FFG.

A Marl Results

Seven wells within the survey were sent to a third party for petrophysical analysis (Figure 15). The analysis identified zones of interest within the Niobrara marls which are typically considered source rocks. The calculations show a high TOC zone in the upper A marl which the analysis identifies as shale pay (Figure 16). A seismic cross-section of the 8X8 instantaneous SOM (Figure 16) through the three wells depicted shows that this zone is well imaged. The neurons can be isolated and volumetric calculations derived from the representative neurons.

Figure 15: Index map for wells used in petrophysical analysis (in red)

Figure 16: Petrophysical results and SOM for three wells in the study area. The TOC curve (Track 12) and Shale pay curve (Track 10), highlighted in yellow, indicate the Upper A marl is both a rich source rock and a potential shale reservoir. Seismic data is shown courtesy of GPI and FFG.

Codell Results

The Codell sandstone in general and within the study area shows more heterogeneity in reservoir properties than the Niobrara chalk benches. The petrophysical analysis on 7 wells shows net pay ranging from zero feet to three feet. The gross thickness ranges from 17 feet to 25 feet. The SOM results reflect this heterogeneity, resolve the Codell gross interval throughout most of the study area, and thus, can be useful for horizontal well planning.

Figures 17 and 18 shows inline 60 through a well with the Top Niobrara to Greenhorn 8X8 SOM results. The 2D color map has been manipulated to emphasize the lower interval from approximately base Niobrara through the Codell. Figure 18 zooms into the well and shows the specific neurons associated with the Codell interval. Figures 19 shows a N-S traverse through four wells again with the Codell interval highlighted through use of a 2D color map. The western and southwest areas of the survey show a much more continuous character to the classification with only two neurons representing the Codell interval (6 and 48). Figure 20 shows both the N-S traverse and a crossline through the anomaly.

Figure 17: Instantaneous 8X8 SOM, Top Niobrara to Greenhorn. Seismic data is shown courtesy of GPI and FFG.

Figure 18: Detailed look at the Codell portion of the SOM at the Haythorn 4-12 with GR in background. The 2D color map shows how neurons can be isolated to show a specific stratigraphic interval. Seismic data is shown courtesy of GPI and FFG.

Figure 19: Traverse through 4 wells in the western part of the study area showing the isolation of the Codell sandstone within the SOM. The south west part of the line shows the Codell being represented by only 2 neurons (6 and 48). The colormap can be interrogated to determine which attributes contribute to any given neuron. Seismic data is shown courtesy of GPI and FFG.

Figure 20: View of the SW Codell anomaly where the neuron stacking pattern changes to two neurons only (6 and 47). Seismic data is shown courtesy of GPI and FFG.

Figure 21: 3D view of neurons isolated from the SOM in the Codell interval. The areas where red is prominent and continuous show the extent of Codell represented by neurons 6 and 47 only. Also, an area in the eastern part of the study is outlined. The Codell is not represented in this area by the six neurons highlighted in the 2D color map. Seismic data is shown courtesy of GPI and FFG.

Unfortunately, vertical well control was not available through this southwestern anomaly. To examine the extent of individual neurons within the SOM at Codell level, the next image, Figure 21, shows a 3D view of the isolated Codell neurons. The southwest anomaly is apparent as well as similar anomalies in the northern portion of the survey. What is also immediately apparent is that in the east-central portion of the survey, the Codell is not represented by the six neurons (6,7,47, 48, 55, 56) previously used to isolate it within the volume. Figure 22 takes a closer look at the SOM results through this area and also utilizes the original amplitude data. Both the SOM and the amplitude data show a change in character throughout the entire section, but the SOM results only change significantly in the lower Niobrara to Greenhorn portion of the interval.

The machine learning application has a feature in which individual neurons can be queried for statistics on how individual seismic attributes contribute to the cluster which makes up the neuron. Queries were done on all of the neurons within the Codell and shown are the results for neuron 6 which is one of 2 neurons characteristic of the southwestern Codell anomaly and on neuron 61in the area where the SOM changes significantly in Figure 23. Neuron 6 has equal contributions from Instantaneous Frequency, Hilbert, Thin Bed, and Relative Acoustic Impedance. Neuron 61 shows Instantaneous Q as the top attribute which is consistent with the interpretation of the section being structurally disturbed or highly fractured.

Figure 22: West-East crossline through two wells showing the SOM and amplitude data through the blank area from Figure 23. The seismic character and classification results differ significantly in this portion of the survey for the lower Niobrara, Fort Hays and Codell. This area is interpreted to be highly fractured. Seismic data is shown courtesy of GPI and FFG.

Figure 23: Example of attribute details for individual neurons (6 and 61). This shows the contribution of individual attributes to the neuron.

Structural Attributes

The machine learning workflow can be applied to geometric attributes. PCA and SOM need to be run separately from the instantaneous attributes since PCA assumes a Gaussian distribution of the attributes. This assumption doesn’t hold for geometric attributes but the SOM process does not assume any distribution and thus still finds patterns in the data. To produce a structural SOM, four attributes were selected from PCA: Curvature_K1, Similarity, Energy Ratio, Texture Entropy, and Texture Homogeneity. These were combined with the original amplitude data to generate SOMs from the Top Niobrara to Top Greenhorn interval. Several SOM topologies were generated with geometric attributes and a 5X5 yielded good results. Figure 24 shows the geometrical SOM results at the Top Niobrara, B bench, and Codell. The Top Niobrara level shows major faults, but not nearly as much structural disturbance as the mid-Niobrara B bench or the Codell level. The eastern part of the survey where the instantaneous classification changed also shows significant differences between the B bench and Codell and agrees with the interpretation that this is a highly fractured area for the lower Niobrara and Codell. The B bench appears more structurally disrupted than the Top Niobrara but shows fewer areal changes compared to Codell. Pressure and production data could help confirm how these features relate to reservoir quality.

Figure 24: 5X5 Structural SOM at 3 levels. There are significant changes both vertically and areally

Conclusions

Seismic multi-attribute analysis has always held the promise of improving interpretations via the integration of attributes which respond to subsurface conditions such as stratigraphy, lithology, faulting, fracturing, fluids, pressure, etc. Machine learning augments traditional interpretation and attribute analysis by utilizing attribute space to simultaneously classify suites of attributes into sample based, high dimension clusters that are subsequently visualized and further interpreted in the 3D seismic survey. 2D colormaps aid in their interpretation and visualization.

In the DJ Basin, we have resolved the primary reservoir targets, the Niobrara chalk benches and the Codell formation, represented within approximately 60 ms of data in two-way time, to the level of one to five neurons which is approximately 7 to 35 feet in thickness. Structural SOM classifications with a suite of geometric attributes better image the complex faulting and fracturing and its variations throughout the reservoir interval. The classification volumes are designed to aid in drilling target identification, reserves calculations and horizontal well planning.

Acknowledgements

The authors would like to thank their colleagues at Geophysical Insights for their valuable insight and suggestions and Digital Formation for the petrophysical analysis. We also thank Geophysical Pursuit, Inc. and Fairfield Geotechnologies for use of their data and permission to publish this paper.

References

Coleou, T., M. Poupon, and A. Kostia, 2003, Unsupervised seismic facies classification: A review and comparison
of techniques and implementation: The Leading Edge, 22, 942–953, doi: 10.1190/1.1623635.

Finn, T. M. and Johnson, R. C., 2005, Niobrara Total Petroleum System in the Southwestern Wyoming Province, Chapter 6 of Petroleum Systems and Geologic Assessment of Oil and Gas in the Southwestern Wyoming Province, Wyoming, Colorado, and Utah, USGS Southwestern Wyoming Province Assessment Team, U.S. Geological Survey Digital Data Series DDS–69–D.

Guo, H., K. J. Marfurt, and J. Liu, 2009, Principal component spectral analysis: Geophysics, 74, no. 4, p. 35–43.

Haykin, S., 2009, Neural networks and learning machines, 3rd ed.: Pearson.

Kauffman, E.G., 1977, Geological and biological overview— Western Interior Cretaceous Basin, in Kauffman, E.G., ed., Cretaceous facies, faunas, and paleoenvironments across the Western Interior Basin: The Mountain Geologist, v. 14, nos. 3 and 4, p. 75–99.

Kohonen, T., 2001, Self-organizing maps: Third extended addition, Springer, Series in Information Services, Vol. 30.

Landon, S.M., Longman, M.W., and Luneau, B.A., 2001, Hydrocarbon source rock potential of the Upper Cretaceous Niobrara Formation, Western Interior Seaway of the Rocky Mountain region: The Mountain Geologist, v. 38, no. 1, p. 1–18.

Lewis, R.K., 2013, Stratigraphy and Depositional Environments of the Late Cretaceous (Late Turonian) Codell Sandstone and Juana Lopez Member of the Carlile Shale, Southeast Colorado: Colorado School of Mines MS Thesis, 190 p.

Longman, M.W., Luneau, B.A., and Landon, S.M., 1998, Nature and distribution of Niobrara lithologies in the Cretaceous Western Interior Seaway of the Rocky Mountain Region: The Mountain Geologist, v. 35, no. 4, p. 137–170.

Luneau, B., Longman, M., Kaufman, P., and Landon, S., 2011, Stratigraphy and Petrophysical Characteristics of the Niobrara Formation in the Denver Basin, Colorado and Wyoming, AAPG Search and Discovery Article #50469.

Meissner, F.F., Woodward, J., and Clayton, J.L., 1984, Stratigraphic relationships and distribution of source rocks in the greater Rocky Mountain region, in Woodward, J., Meissner, F.F., and Clayton, J.L., eds., Hydrocarbon source rocks of the greater Rocky Mountain region: Rocky Mountain Association of Geologists Guidebook, p. 1–34.

Molenaar, C.M., and Rice, D.D., 1988, Cretaceous rocks of the Western Interior Basin, in Sloss, L.L., ed., Sedimentary cover-North American craton, U.S.: Geological Society of America, The Geology of North America, v. D–2, p. 77–82.

Roden, R., Smith, T., and Sacrey, D., 2015, Geologic pattern recognition from seismic attributes: Principal component analysis and self-organizing maps, Interpretation, Vol. 3, No. 4, p. SAE59-SAE83.

Santogrossi, P., 2017, Classification/Corroboration of Facies Architecture in the Eagle Ford Group: A Case Study in Thin Bed Resolution, URTeC 2696775, doi 10.15530-urtec-2017-<2696775>.

Smith, T., 2016, Why SOM is an Appealing Learning Machine, Internal Geophysical Insights Paper.

Sonnenberg, S.A., 2015. Geologic Factors Controlling Production in the Codell Sandstone, Wattenberg Field, Colorado. URTeC Paper 2145312 presented at the Unconventional Resources Technology Conference, San Antonio, TX, July 20-22.

Sonnenberg, S.A., 2015. New reserves in an old field, the Niobrara/Codell resource plays in the Wattenberg Field, Denver Basin, Colorado. EAGE First Break, v. 33, p. 55-62.

Sterling, R., Bottjer, R. and Smith, K., 2016, Codell SS, A review of the Northern DJ oil resource play Laramie County, WY and Weld, County, CO, AAPG Search and Discovery Article #10754.

Machine Learning with Deborah Sacrey – AAPG Energy Insights Podcast

Machine Learning with Deborah Sacrey – AAPG Energy Insights Podcast

One of our very own esteemed geoscientists, Deborah Sacrey, sat down with Vern Stefanic to talk about Machine Learning in the energy industry.

To watch the video, please click here.

Transcript of podcast

Full Transcript

VERN STEFANIC: Hi, I’m Vern Stefanic. And welcome to another edition of AAPG’s Podcast, Energy Insights, where we talk to the leaders and the people of the energy industry who are making things happen and bringing the world more energy, the energy that it needs to keep going.

Today, we’re very happy to have as our guest Deborah Sacrey, who is Auburn Energy, consultant working outside of Houston, Texas. But somebody who’s got experience working in the energy industry for a long time, who’s been through many changes in the industry, and who keeps evolving to find new ways to make herself valuable to the profession and to the industry that’s going forward. Deborah, welcome, and thank you for being here with us today.

DEBORAH SACREY: I’m delighted. Thank you so much for inviting me.

VERN STEFANIC: Well one reason– we’re doing this from the AAPG Annual Convention in San Antonio, where you have been one of the featured speakers. And you were talking about what the future of petroleum geologist is going to be. Which was perfect, because you found yourself somebody who’s had to sort of evolve and change your focus, the focus of your career several times. Could you tell us a little bit about your journey?

DEBORAH SACREY: Well, what I found is that every time there’s a major technology change, a paradigm shift in the way we look at data, there are consequences to that. There are benefits and consequences. If you’re not prepared to accept that technology change, you get left behind. And it makes it hard for you to find a job.

But if you accept that technology change, and embrace it, and learn about it, then you can morph yourself into a very successful career, until the next time the technology changes again. So you’re constantly– you have ups and downs, and you’re constantly morphing yourself and evolving yourself to embrace new technology changes as they come along.

VERN STEFANIC: Which is important, because we live in– in the industry right now, there have been rapid change, which we’re going to talk about some of the places where we’re going on that. But because of that we always hear stories of a lot of petroleum geologists or professional geoscientists, who find themselves awkwardly lost in the shuffle somewhere and not knowing what to do. What I love about your message is that it’s the understanding of how technology is driving all of this and being aware of that. You’ve experienced this several times in your career, is that right?

DEBORAH SACREY: Oh, absolutely. I’ve been– I got out of school in 1976. So this makes my 43rd year in the career. What I’ve gone through is, we had a digital transformation. When I got out of school, we were always looking at paper seismic records. And I went to work for Gulf, and they’d be rolled up every night, and they’d be put in a tube, and they’d be locked behind the door. And during the day, you’d go check them out and take them to your office and work on paper.

So the digital transformation is when we moved from paper records into workstations, where we could actually scale the seismic, and can see the seismic, and blow it up, and do different things with it. That was a huge transformation. When we went from paper logs, which a lot of people still use today, to something that you can see on the screen, and blow it up and see all the nuances, of the information in the well.

Then the next major transformation came in the middle ’90s, when software was available for the smaller clients and independents to start looking at 3D. So we transition from the 2D world into the 3D world. And that was huge. I mean, it’s amazing to me that there’s any space left on the Gulf Coast that doesn’t have a 3D covering yet at this point. And now, we’re getting ready to go into another major transformation. And it’s all about data.

VERN STEFANIC: People have been told that, I think, maybe a couple of times, that oh, yeah, I understand that I have to change, and I have to be aware of it. But they really not have the skills or the insight on how to make some of those changes happen. I’m just curious, in your career do you recall some of the ways that you had to– just some of the realizations that you had. First, not just that you had to change, but some of the steps that you did to make it happen.

DEBORAH SACREY: Well, I think a lot of it, and what was important to me, is when I could see the changes coming. I had to educate myself. I didn’t have a resource to go to. I wasn’t working for a big company that had– that would send you off to classes. So it’s a matter of doing the research and understanding the technology that you’re facing.

And what I told people yesterday in my talk is that the AAPG Convention or any convention is an excellent resource for free education. Go out and look what the vendors are trying to do. And that’s your insight into how the technology is changing. And people can walk around the convention center. And they can listen to presentations for free and try to get an inkling of what’s getting ready to happen.

VERN STEFANIC: That’s great advice. That’s great insight. By the way, I’ve noticed that too in myself, in walking around the convention floor. That’s where I heard many things for the first time. Thought, oh, when I was at the Explorer, thought, oh, I ought to do a story about this.

DEBORAH SACREY: Right, exactly. And I think it’s especially important for the young people, the early career people, or the kids coming out of school, to understand that their lives will not always be with one company. When I went to work for Gulf in 1976, the gentleman who interviewed me on campus, looked me in the eye and said, Gulf will be your place of employment for life.

And I referenced yesterday a really good book. It’s called Who Moved my Cheese. So our cheese in our careers is constantly getting moved. And we have to be able to accept that and adapt to it. And you can only do it through education.

VERN STEFANIC: When did you realize, or was there a moment, when you saw that, oh, big data is important? Because it seems very obvious that we would see that. But I’m not sure everybody clicks on to– not just big data is going to be the name of the game, but this is what I’m going to do about it. What was your experience with that?

DEBORAH SACREY: Well, in 2011, a gentleman whom I’d been working with for a long time, Tom Smith, and he was the– Dr. Smith was the guy who started S&P, or Kingdom. When he sold Kingdom, he started doing research into ways that we could extend our understanding of seismic data and do applications using seismic attributes.

So he brought me in to help work with the developers to make this software geoscience friendly. Because our brains are wired a little bit differently from other people, other industries. And the technology he was using is machine learning, but it’s cluster analysis and it’s pattern recognition. Now what’s happened in the big data world is, all these companies, all the majors, all the large independents, have been drilling wells for years. And a lot of times, they’ve just been shoving the logs, and the drilling reports, and everything in a file.

So that’s all this paper that’s out there, that they’re just now starting to digitize, but you have to get it in a way that’s easily retrievable. So the big data– every time you drill a well now, you’re generating 10 gigabytes of information. And think about the wells that are being drilled, and how that information is being organized, and how it’s being put in– so if you use a keyword, like 24% porosity, you can go in and retrieve information on wells where they’ve determined that there’s 24% porosity in reservoirs. And that’s some of the data transformation we’re getting ready to go through, to make it accessible, because there’s so much out there.

VERN STEFANIC: OK, so understanding that having data is the key to having more knowledge, is the key to actually being a success, not just with your company, but also with actually bringing energy to the world.

DEBORAH SACREY: Right, I mean it’s not getting any easier to find. So we’re having to use advanced methods of technology and understanding the data information to be able to find the more subtle traps.

VERN STEFANIC: So– and I don’t know if this is too much of a jump– in fact, we can fill in the blanks if it is– but today we’re talking about machine learning and its applications and implications for the energy industry. And I know you are somebody who has been a little bit ahead of the curve on this one, in recognizing the need to understand what this is all about. So for some of us who don’t understand like you do, could you talk a little bit about that?

DEBORAH SACREY: Well, I can be specific about the technology that I’ve been using for the last five years.

VERN STEFANIC: OK, yeah.

DEBORAH SACREY: And like I said earlier, Tom brought me in to help guide the developers. But the basics behind the software I’ve been using is that instead of looking at the wavelet in the seismic data, I’m parsing the data down to a sample level. I’m looking at sample statistics.

So if your wavelet, if you’re in low frequency data, and your wavelet’s 30 milliseconds between the trough and the peak, I may be looking at 2 millisecond sample intervals. So I’m parsing the data 15 times as densely as you would if you were looking at the wavelet. What this allows me to do is, it allows me to see very thin beds at depth. Because I’m not looking at conventional seismic tuning anymore. I’m looking at statistics and cluster analysis that comes back to the workstation. Because every sample has an X, Y, and Z. So it has its place in the earth. And then I’m looking at true lithology patterns, like we’ve never been able to see before.

VERN STEFANIC: OK, well, never been able to see before is a remarkable statement. Are we talking about a game change for the profession at this point?

DEBORAH SACREY: Most definitely. I give a lot of talks on case histories. I’ve probably worked on a hundred 3Ds in the last five years, all around the world. And I have one example in the Eagle Ford set. The Eagle Ford is only a 30 millisecond thick formation in most of Texas. And so you’re looking at a peak and a trough, and you’re looking at two zero crossings. That’s four sample points.

But when you’re looking at that kind of discrete information that I can get out of it, I can see all six facies strats from the clay base, up through the brittle zone and the ash top, right underneath the Austin Chalk. Well, it’s the brittle zone, in the middle, where the higher TOC is, and what people are trying to stay in when they’re drilling the Eagle.

If you can define that and you can isolate it, then you can geosteer better. You can get better results from your well. But you’re talking about something that’s only 150 feet deep. And you’re trying to discern a very special part of that, where the hydrocarbons are really located. And so that’s going to be a game-changer.

VERN STEFANIC: So what would you say to people– but this is still you– you’re bringing your skills, your talents, everything that has brought you to this point in your career, and applying them with this new technology. What about the criticism, which may be completely invalid, but what about the criticism that people say that because of machine learning, we’re headed to a place where the very nature of the jobs of the professional geologists are going to be threatened? Is that a possibility? Is that something that we should even think about?

DEBORAH SACREY: Well, I think it’s a possibility. And why I say that is because a lot of the machine learning applications that are being developed out there are really improving efficiency, especially when it comes to the field and monitoring pressure gauges and things like that. They’re doing it remotely. And they’re getting into the artificial intelligence aspect of it. But the efficiency that you can bring to the field and operations will get rid of some of the people who go down and check the wells every day. Because they’ll be able to monitor it– they’ll know when rest is getting to one day or whether bad weather comes through and they’ve had problems. They’ll be able to know immediately without having to send someone out to the field.

Now, when you relate it to the geosciences, especially on the seismic side, you’re going to still need the experience. Because it’s a matter of maybe having a different way to view the data, but someone’s still going to have to interpret it. Someone’s still going to have to have knowledge about the attributes to use in the first place. That takes a person with some experience. And it’s not something that’s usually learned overnight. So I think some aspects of it will improving efficiency in the industry and do get rid of some jobs, and then some other aspects will not get rid of jobs.

VERN STEFANIC: Well, let me go down a difficult path then in our conversation, we all are aware of demographics within the industry, within the profession. And so, let’s start first with the baby boomers. Right, so there is an example. We have a case history of how we can approach that. From your perspective, though, it’s actually just being aware that change is necessary.

DEBORAH SACREY: Yeah, and you know, there are a lot of people out there who are in denial. And they think they can keep on working that same square of earth all the rest of their career. And those will be the guys who get left behind. One of the things I tried to emphasize yesterday is that old dogs can learn new tricks. And this is not that hard.

This kind of technology has been on Wall Street, it’s been in the medical industry for years. We’re just now getting to the point where we’re applying it to the oil and industry, to the energy industry.

VERN STEFANIC: Is there any advice that you could give to maybe younger, mid-career, the Gen X, or even kind of YPs, who are just now getting into the industry, special things they should be looking for or trying to do to enhance their careers?

DEBORAH SACREY: Well, certainly, if they’re working for a large company, American companies have already started making the shift to machine learning or artificial intelligence data mining. I’ve done a lot of work with Anadarko. They put a whole business unit together some years ago specifically to look into methodologies to improve the efficiencies on how they can get more out of this data. All the big companies have research departments. They’re getting into it.

I have a friend who just got a PhD several years ago in data mining. And she said her company is looking and screening all the new resumes coming in for any kind of statistics, any kind of data mining technology, or any kind of advanced machine learning. And they need a reference that they’ve had exposure to it, but that’s becoming a discriminator for finding a job in some instance, because they’re all making the digital transformation to efficiency and machine learning.

VERN STEFANIC: I don’t want to– I don’t want to overlook what might be obvious to some people, but I’d like to put it on the record. Auburn Energy, you, in recognizing and embracing the need to evolve along with the industry, as technology changes, you’ve had a little bit of success at this.

DEBORAH SACREY: I’ve been very lucky. I’ve been blessed in life with the successes I’ve had. I was getting bored with mapping and 3D. And so several years ago, at the time I was involved in this, I started looking in to different attributes, and what kind of reactions to the rock properties and sizing to get these different attributes, which is why this machine learning technology came along at the right time for me. Because it’s just a gradual going on. I’m not looking at one attribute at a time, I’m looking at 10 at the same time.

And in doing so, and in looking at the earth in a different way, I’ve been able to pick up some nuances that people have missed and had discoveries. I had a two million barrel field I found a couple years ago. I had an 80 bcf field that I found a couple years ago. I just had a discovery in Mississippi and in Oklahoma, in southern Oklahoma. And we’re expanding our lease activities to pick up on what I’m seeing in my technology there. So not only has it revitalized my love of digging in and looking at seismics, but it proves to be profitable as well.

VERN STEFANIC: So let me go ahead and maybe put you on the spot. Don’t mean to be– but because you are a person who’s gone through many stages of the industry, what can you see happening next? Do you have any kind of crystal ball look out to– or even just to say this is what needs to happen next to help you do your job better.

DEBORAH SACREY: Well, certainly the message I’m trying to get out to people of all ages is that this paradigm shift that we’re getting ready to go through, and you hear it over and over at all the conventions, is going to substantially change their lives. And we need to get on the train before it leaves the station or they will be left behind. And each time we’ve had a major paradigm shift, there have been some people who’ve been reluctant or didn’t want to get outside their box. And they wake up five or six years later and don’t recognize the world. Their world has completely changed and people have moved on.

And each time that happens, you can lose a certain part of the brain power and people who have knowledge of one county and one piece of Texas, because they just didn’t want to make– they didn’t want to bother themselves. And so I’m trying to get the word out to people that this change is coming. And it’s something that can be easily embraced and you should not be afraid of it, and just get on the bandwagon. I mean, it’s not that hard.

The technology and the software that I’m seeing being developed out there, it’s a piece of cake to use. You just have to have some knowledge of the seismic or logs. There’s a technology called convolutional neural network and it’s being used to map faults through 3D. So you may go in and map the faults in 10 lines out of 80 blocks of actual data. And the machine goes in and learns what certain kinds of faults look like from the 10 lines that you’ve mapped. And it will finish mapping all the faults in the whole bunch of blocks in the offshore data.

VERN STEFANIC: Wow.

DEBORAH SACREY: It’s scary. But fault picking is like one of the most boring things we can do in seismic data. So if you can find– if you can find an animal out there that will crawl through that data, and pick out the faults for you, that’s wonderful. That saves tons of human hours. And it’s good for stratigraphy. You give it some learning lines where you’ve mapped out blocks of clastics or carbonates, or turbidites, something like that, and it learns from that. And then it goes and maps that stratigraphy anywhere it can find it in the 3D. It’s very unique. You need to start educating yourself about what’s out there.

VERN STEFANIC: Well, you’re absolutely right. I try to in the world that I work with, but I’m always impressed that in the world that you’re part of, that there’s so much change that keeps coming. And it’s just fast. And it’s again, and again, and again. And the ability that people, such as yourself, has had to embrace that and to use technology in the new way– in fact, I’m going to guess– I’m going to guess that– have you offered suggestions to anyone, who are developing technology, have you got to the point where you say, you know what we need, we need now for it to do this?

DEBORAH SACREY: I’m still on a development team for the software I’m using.

VERN STEFANIC: You’re on the development– OK.

DEBORAH SACREY: Yeah, so we’re forward thinking two years down the road what kind of– what can we anticipate the technology needs to be doing two to three years down the road.

VERN STEFANIC: Can you talk about any of that?

DEBORAH SACREY: Well, I mean, I can. And certainly, this CNN technology is part of it. We’ve been approached by several larger companies to put this into our software. And they’re willing to help pay for the effort to do that, because it would take their departments too long. We’re too far advanced where we are. And it would take them too long to recreate the wheel.

So they’d rather support us to get the technology that they need, that they need for their data. And the beauty of all this is that you don’t have to shoot anything new. You don’t even necessarily have to reprocess it. You’re just getting more out of it than you’ve ever been able to get before.

VERN STEFANIC: That is beauty.

DEBORAH SACREY: It is cool. Because a lot of people don’t have the money to go shoot more data or reprocess it. They just want to take advantage of the stuff they already have in their archives.

VERN STEFANIC: When people talk about the industry being a sunset industry, I think they’re not giving it proper credit for what’s going on.

DEBORAH SACREY: Oh, I see this totally revitalizing– one of the examples I showed yesterday was the two million barrel oil field that I found in Brazoria County, Texas. And it’s from a six-foot thick off-shore bar at 10,800 feet. Well, that reflector is so weak– I mean, it’s not a bright spot. It doesn’t show up. People would have ignored it a long time, and have ignored it a long time, for drilling.

But I can prove that there’s two million barrels of oil in that six-foot thick sand that covers about 1,900 acres. So how many of those little things that we’ve ignored for years and years are still out there to be found. That’s what I’m saying. This technology is going to give us another little push. It’ll make us more efficient in the unconventional world. It will definitely help us find the subtle traps in the conventional world.

VERN STEFANIC: So there you have it. If you’re part of this profession now, you’re part of this industry now, don’t be discouraged. There’s actually great work to be done.

DEBORAH SACREY: Oh, there’s a lot of stuff left to find. We haven’t begun to quit finding yet. I mean, it’s just like Oklahoma– I grew up in Oklahoma. And for years and years, all the structural trap had been drilled, and all the clays had gone through. And everyone said, well, Oklahoma’s had it. And we turn around and there’s a new play. And you turn around, there’s the unconventional. There’s the SCOOP and STACK. There’s all the Woodford. There’s all these things that reenergized Oklahoma. And it’s been poked and punched for over 100 years. And people are still finding stuff. So we just– we just have to put better glasses on.

VERN STEFANIC: Yeah.

DEBORAH SACREY: We have to sharpen our goggles. And get in there and see what’s left.

VERN STEFANIC: Great words. Deb, thanks for this conversation today.

DEBORAH SACREY: You’re welcome.

VERN STEFANIC: Thank you. I hope it’s a conversation that we’ll continue. We’ll continue having this talk, because it sounds like there’s going to be new chapters added to the story.

DEBORAH SACREY: Oh, yeah, and I’m really– you know, I’m 66 years old, but I’m not ready to give it up yet. I’m having way too much fun.

VERN STEFANIC: That’s great. Thank you.

DEBORAH SACREY: You’re welcome.

VERN STEFANIC: And thank you for being part of this edition of Energy Insights, the AAPG Podcast, coming to you on the AAPG website, but now coming to you on platforms wherever you want to look. Look up a AAPG Energy Insights, we’ll be there. And we’re glad you’re part of it. But for now, thanks for listening.

The Oil Industry’s Cyber–Transformation Is Closer Than You Think

The Oil Industry’s Cyber–Transformation Is Closer Than You Think

By David Brown, Explorer Correspondent
Published with permission: AAPG Explorer
June 2019

The concept of digital transformation in the oil and gas industry gets talked about a lot these days, even though the phrase seems to have little specific meaning.

So, will there really be some kind of extensive cyber-transformation of the industry over the next decade?

“No,” said Tom Smith, president and CEO of Geophysical Insights in Houston.

Instead, it will happen “over the next three years,” he predicted.

Machine Learning

Much of the industry’s transformation will come from advances in machine learning, as well as continuing developments in computing and data analysis going on outside of oil and gas, Smith said.

Through machine learning, computers can develop, modify and apply algorithms and statistical models to perform tasks without explicit instructions.

“There’s basically been two types of machine learning. There’s ‘machine learning’ where you are training the machine to learn and adapt. After that’s done, you can take that little nugget (of adapted programming) and use it on other data. That’s supervised machine learning,” Smith explained.

“What makes machine learning so profoundly different is this concept that the program itself will be modified by the data. That’s profound,” he said.

Smith earned his master’s degree in geology from Iowa State University, then joined Chevron Geophysical as a processing geophysicist. He later left to complete his doctoral studies in 3-D modeling and migration at the University of Houston.

In 1984, he founded the company Seismic Micro-Technology, which led to development of the KINGDOM software suite for integrated geoscience interpretation. Smith launched Geophysical Insights in 2009 and introduced the Paradise analysis software, which uses machine learning and pattern recognition to extract information from seismic data.

He’s been named a distinguished alumnus of both Iowa State and the University of Houston College of Natural Sciences and Mathematics, and received the Society of Exploration Geophysicists Enterprise Award in 2000.

Smith sees two primary objectives for machine learning: replacing repetitive tasks with machines – essentially, doing things faster – and discovery, or identifying something new.

“Doing things faster, that’s the low-hanging fruit. We see that happening now,” Smith said.

Machine learning is “very susceptible to nuances of the data that may not be apparent to you and I. That’s part of the ‘discovery’ aspect of it,” he noted. “It isn’t replacing anybody, but it’s the whole process of the data changing the program.”

Most machine learning now uses supervised learning, which employs an algorithm and a training dataset to “teach” improvement. Through repeated processing, prediction and correction, the machine learns to achieve correct outcomes.

“Another aspect is that the first, fundamental application of supervised machine learning is in classification,” Smith said,

But, “in the geosciences, we’re not looking for more of the same thing. We’re looking for anomalies,” he observed.

Multidimensional Analysis

The next step in machine learning is unsupervised learning. Its primary goal Is to learn more about datasets by modeling the structure or distribution of the data – “to self-discover the characteristics of the data,” Smith said.

“If there are concentrations of information in the data, the unsupervised machine learning will gravitate toward those concentrations,” he explained.

As a result of changes in geology and stratigraphy, patterns are created in the amplitude and attributes generated from the seismic response. Those patterns correspond to subsurface conditions and can be understood using machine-learning and deep-learning techniques, Smith said.

Human seismic interpreters can see only in three dimensions, he noted, but the patterns resulting from multiple seismic attributes are multidimensional. He used the term “attribute space” to distinguish from three-dimensional seismic volumes.

In geophysics, unsupervised machine learning was first used to analyze multiple seismic attributes to classify these patterns, a result of concentrations of neurons.

“We see the effectiveness of (using multiple) attributes to resolve thin beds in unconventional plays and to expose direct hydrocarbon Indicators in conventional settings. Existing computing hardware and software now routinely handle multiple-attribute analysis, with 5 to 10 being typical numbers,” he said.

Machine-learning and deep-learning technology, such as the use of convolutional neural networks (CNN), has important practical applications in oil and gas, Smith noted. For instance, the “subtleties of shale-sand fan sequences are highly suited” to analysis by machine learning-enhanced neural networks, he said.

“Seismic facies classification and fault detection are just two of the important applications of CNN technology that we are putting into our Paradise machine-learning workbench this year,” he said.

A New Commodity

Just as a seismic shoot or a seismic imaging program have monetary value, algorithms enhanced by machine-learning systems also are valuable for the industry, explained Smith.

In the future, “people will be able to buy, sell and exchange machine-learning changes in algorithms. There will be industry standards for exchanging these ‘machine-learning engines,’ if you will,” he said.

As information technology continues to advance, those developments will affect computing and data analysis in oil and gas. Smith said he’s been pleased to see the industry “embracing the cloud” as a shared computing-and-data-storage space.

“An important aspect of this is, the way our industry does business and the way the world does business are very different,” Smith noted.

“When you look at any analysis of Web data, you are looking at many, many terabytes of information that’s constantly changing,” he said.

In a way, the oil and gas industry went to school on very large sets of seismic data when huge datasets were not all that common. Now the industry has some catching up to do with today’s dynamic data-and-processing approach.

For an industry accustomed to thinking in terms of static, captured datasets and proprietary algorithms, that kind of mind-shift could be a challenge.

“There are two things we’re going to have to give up. The first thing is giving up the concept of being able to ‘freeze’ all the input data,” Smith noted.

“The second thing we have to give up is, there’s been quite a shift to using public algorithms. They’re cheap, but they are constantly changing,” he said.

Moving the Industry Forward

Smith will serve as moderator of the opening plenary session, “Business Breakthroughs with Digital Transformation Crossing Disciplines,” at the upcoming Energy in Data conference in Austin, Texas.

Presentations at the Energy in Data conference will provide information and insights for geologists, geophysicists and petroleum engineers, but its real importance will be in moving the industry forward toward an integrated digital transformation, Smith said.

“We have to focus on the aspects of machine-learning impact not just on these three, major disciplines, but on the broader perspective,” Smith explained. “The real value of this event, in my mind, has to be the integration, the symbiosis of these disciplines.”

While the conference should appeal to everyone from a company’s chief information officer on down, recent graduates will probably find the concepts most accessible, Smith said.

“Early-career professionals will get it. Mid-managers will find it valuable if they dig a little deeper into things,” he said.

And whether it’s a transformation or simply part of a larger transition, the coming change in computing and data in oil and gas will be one of many steps forward, Smith said.

“Three years from now we’re going to say, ‘Gosh, we were in the Dark Ages three years ago,’” he said. “And it’s not going to be over.”

Applications of Machine Learning for Geoscientists – Permian Basin

Applications of Machine Learning for Geoscientists – Permian Basin

By Carrie Laudon
Published with permission: Permian Basin Geophysical Society 60th Annual Exploration Meeting
May 2019

Abstract

Over the last few years, because of the increase in low-cost computer power, individuals and companies have stepped up investigations into the use of machine learning in many areas of E&P. For the geosciences, the emphasis has been in reservoir characterization, seismic data processing, and to a lesser extent interpretation. The benefits of using machine learning (whether supervised or unsupervised) have been demonstrated throughout the literature, and yet the technology is still not a standard workflow for most seismic interpreters. This lack of uptake can be attributed to several factors, including a lack of software tools, clear and well-defined case histories and training. Fortunately, all these factors are being mitigated as the technology matures. Rather than looking at machine learning as an adjunct to the traditional interpretation methodology, machine learning techniques should be considered the first step in the interpretation workflow.

By using statistical tools such as Principal Component Analysis (PCA) and Self Organizing Maps (SOM) a multi-attribute 3D seismic volume can be “classified”. The PCA reduces a large set of seismic attributes both instantaneous and geometric, to those that are the most meaningful. The output of the PCA serves as the input to the SOM, a form of unsupervised neural network, which, when combined with a 2D color map facilitates the identification of clustering within the data volume. When the correct “recipe” is selected, the clustered or classified volume allows the interpreter to view and separate geological and geophysical features that are not observable in traditional seismic amplitude volumes. Seismic facies, detailed stratigraphy, direct hydrocarbon indicators, faulting trends, and thin beds are all features that can be enhanced by using a classified volume.

The tuning-bed thickness or vertical resolution of seismic data traditionally is based on the frequency content of the data and the associated wavelet. Seismic interpretation of thin beds routinely involves estimation of tuning thickness and the subsequent scaling of amplitude or inversion information below tuning. These traditional below-tuning-thickness estimation approaches have limitations and require assumptions that limit accuracy. The below tuning effects are a result of the interference of wavelets, which are a function of the geology as it changes vertically and laterally. However, numerous instantaneous attributes exhibit effects at and below tuning, but these are seldom incorporated in thin-bed analyses. A seismic multi-attribute approach employs self-organizing maps to identify natural clusters from combinations of attributes that exhibit below-tuning effects. These results may exhibit changes as thin as a single sample interval in thickness. Self-organizing maps employed in this fashion analyze associated seismic attributes on a sample-by-sample basis and identify the natural patterns or clusters produced by thin beds. Examples of this approach to improve stratigraphic resolution in both the Eagle Ford play, and the Niobrara reservoir of the Denver-Julesburg Basin will be used to illustrate the workflow.

Introduction

Seismic multi-attribute analysis has always held the promise of improving interpretations via the integration of attributes which respond to subsurface conditions such as stratigraphy, lithology, faulting, fracturing, fluids, pressure, etc. The benefits of using machine learning (whether supervised or unsupervised) has been demonstrated throughout the literature and yet the technology is still not a standard workflow for most seismic interpreters. This lack of uptake can be attributed to several factors, including a lack of software tools, clear and well-defined case histories, and training. This paper focuses on an unsupervised machine learning workflow utilizing Self-Organizing Maps (Kohonen, 2001) in combination with Principal Component Analysis to produce classified seismic volumes from multiple instantaneous attribute volumes. The workflow addresses several significant issues in seismic interpretation: it analyzes large amounts of data simultaneously; it determines relationships between different types of data; it is sample based and produces high-resolution results and, reveals geologic features that are difficult to see in conventional approaches.

Principal Component Analysis (PCA)

Multi-dimensional analysis and multi-attribute analysis go hand in hand. Because individuals are grounded in three-dimensional space, it is difficult to visualize what data in a higher number dimensional space looks like. Fortunately, mathematics doesn’t have this limitation and the results can be easily understood with conventional 2D and 3D viewers.

Working with multiple instantaneous or geometric seismic attributes generates tremendous volumes of data. These volumes contain huge numbers of data points which may be highly continuous, greatly redundant, and/or noisy. (Coleou et al., 2003). Principal Component Analysis (PCA) is a linear technique for data reduction which maintains the variation associated with the larger data sets (Guo and others, 2009; Haykin, 2009; Roden and others, 2015). PCA can separate attribute types by frequency, distribution, and even character. PCA technology is used to determine which attributes may be ignored due to their very low impact on neural network solutions and which attributes are most prominent in the data. Figure 1 illustrates the analysis of a data cluster in two directions, offset by 90 degrees. The first principal component (eigenvector 1) analyses the data cluster along the longest axis. The second principal component (eigenvector 2) analyses the data cluster variations perpendicular to the first principal component. As stated in the diagram, each eigenvector is associated with an eigenvalue which shows how much variance there is in the data.

two attribute data set

Figure 1. Two attribute data set illustrating the concept of PCA

The next step in PCA analysis is to review the eigen spectrum to select the most prominent attributes in a data set. The following example is taken from a suite of instantaneous attributes over the Niobrara formation within the Denver­ Julesburg Basin. Results for eigenvectors 1 are shown with three attributes: sweetness, envelope and relative acoustic impedance being the most prominent.

two attribute data set

Figure 2. Results from PCA for first eigenvector in a seismic attribute data set

Utilizing a cutoff of 60% in this example, attributes were selected from PCA for input to the neural network classification. For the Niobrara, eight instantaneous attributes from the four of the first six eigenvectors were chosen and are shown in Table 1. The PCA allowed identification of the most significant attributes from an initial group of 19 attributes.

Results from PCA for Niobrara Interval

Table 1: Results from PCA for Niobrara Interval shows which instantaneous attributes will be used in a Self-Organizing Map (SOM).

Self-Organizing Maps

Teuvo Kohonen, a Finnish mathematician, invented the concepts of Self-Organizing Maps (SOM) in 1982 (Kohonen, T., 2001). Self-Organizing Maps employ the use of unsupervised neural networks to reduce very high dimensions of data to a classification volume that can be easily visualized (Roden and others, 2015). Another important aspect of SOMs is that every seismic sample is used as input to classification as opposed to wavelet-based classification.

Figure 3 diagrams the SOM concept for 10 attributes derived from a 3D seismic amplitude volume. Within the 3D seismic survey, samples are first organized into attribute points with similar properties called natural clusters in attribute space. Within each cluster new, empty, multi-attribute samples, named neurons, are introduced. The SOM neurons will seek out natural clusters of like characteristics in the seismic data and produce a 2D mesh that can be illustrated with a two- dimensional color map. In other words, the neurons “learn” the characteristics of a data cluster through an iterative process (epochs) of cooperative than competitive training. When the learning is completed each unique cluster is assigned to a neuron number and each seismic sample is now classified (Smith, 2016).

two attribute data set

Figure 3. Illustration of the concept of a Self-Organizing Map

Figures 4 and 5 show a simple example using 2 attributes, amplitude, and Hilbert transform on a synthetic example. Synthetic reflection coefficients are convolved with a simple wavelet, 100 traces created, and noise added. When the attributes are cross plotted, clusters of points can be seen in the cross plot. The colored cross plot shows the attributes after SOM classification into 64 neurons with random colors assigned. In Figure 5, the individual clusters are identified and mapped back to the events on the synthetic. The SOM has correctly distinguished each event in the synthetic.

Two attribute synthetic example of a Self-Organizing Map

Figure 4. Two attribute synthetic example of a Self-Organizing Map. The amplitude and Hilbert transform are cross plotted. The colored cross plot shows the attributes after classification into 64 neurons by SOM.

Synthetic SOM example

Figure 5. Synthetic SOM example with neurons identified by number and mapped back to the original synthetic data

Results for Niobrara and Eagle Ford

In 2018, Geophysical Insights conducted a proof of concept on 100 square miles of multi-client 3D data jointly owned by Geophysical Pursuit, Inc. (GPI) and Fairfield Geotechnologies (FFG) in the Denver¬ Julesburg Basin (DJ). The purpose of the study is to evaluate the effectiveness of a machine learning workflow to improve resolution within the reservoir intervals of the Niobrara and Codell formations, the primary targets for development in this portion of the basin. An amplitude volume was resampled from 2 ms to 1 ms and along with horizons, loaded into the Paradise® machine learning application and attributes generated. PCA was used to identify which attributes were most significant in the data, and these were used in a SOM to evaluate the interval Top Niobrara to Greenhorn (Laudon and others, 2019).

Figure 6 shows results of an 8X8 SOM classification of 8 instantaneous attributes over the Niobrara interval along with the original amplitude data. Figure 7 is the same results with a well composite focused on the B chalk, the best section of the reservoir, which is difficult to resolve with individual seismic attributes. The SOM classification has resolved the chalk bench as well as other stratigraphic features within the interval.

North-South Inline showing the original amplitude data (upper) and the 8X8 SOM result (lower) from Top Niobrara

Figure 6. North-South Inline showing the original amplitude data (upper) and the 8X8 SOM result (lower) from Top Niobrara through Greenhorn horizons. Seismic data is shown courtesy of GPI and FFG.

8X8 Instantaneous SOM through Rotharmel 11-33 with well log composite

Figure 7. 8X8 Instantaneous SOM through Rotharmel 11-33 with well log composite. The B bench, highlighted in green on the wellbore, ties the yellow-red-yellow sequence of neurons. Seismic data is shown courtesy of GPI and FFG

 

8X8 SOM results through the Eagle Ford

Figure 8. 8X8 SOM results through the Eagle Ford. The primary target, the Lower Eagle Ford shale had 16 neuron classes over 14-29 milliseconds of data. Seismic data shown courtesy of Seitel.

The results shown in Figure 9 reveal non-layer cake facies bands that include details in the Eagle )RUG,v basal clay-rich shale, high resistivity and low resistivity Eagle Ford shale objectives, the Eagle Ford ash, and the upper Eagle Ford marl, which are overlain disconformably by the Austin Chalk.

Eagle Ford SOM classification shown with well results

Figure 9. Eagle Ford SOM classification shown with well results. The SOM resolves a high resistivity interval, overlain by a thin ash layer and finally a low resistivity layer. The SOM also resolves complex 3-dimensional relationships between these facies

Convolutional Neural Networks (CNN)

A promising development in machine learning is supervised classification via the applications of convolutional neural networks (CNNs). Supervised methods have, in the past, not been efficient due to the laborious task of training the neural network. CNN is a deep learning seismic classification. We apply CNN to fault detection on seismic data. The examples that follow show CNN fault detection results which did not require any interpreter picked faults for training, rather the network was trained using synthetic data. Two results are shown, one from the North Sea, Figure 10, and one from the Great South Basin, New Zealand, Figure 11.

Side by side comparison of coherence attribute to CNN fault probability attribute, North Sea

Figure 10. Side by side comparison of coherence attribute to CNN fault probability attribute, North Sea

Side by side comparison of coherence attribute to CNN fault probability attribute, North Sea

Figure 11. Comparison of Coherence to CNN fault probability attribute, New Zealand

Conclusions

Advances in compute power and algorithms are making the use of machine learning available on the desktop to seismic interpreters to augment their interpretation workflow. Taking advantage of today’s computing technology, visualization techniques, and an understanding of machine learning as applied to seismic data, PCA combined with SOMs efficiently distill multiple seismic attributes into classification volumes. When applied on a multi-attribute seismic sample basis, SOM is a powerful nonlinear cluster analysis and pattern recognition machine learning approach that helps interpreters identify geologic patterns in the data and has been able to reveal stratigraphy well below conventional tuning thickness.

In the fault interpretation domain, recent development of a Convolutional Neural Network that works directly on amplitude data shows promise to efficiently create fault probability volumes without the requirement of a labor-intensive training effort.

References

Coleou, T., M. Poupon, and A. Kostia, 2003, Unsupervised seismic facies classification: A review and comparison of techniques and implementation: The Leading Edge, 22, 942–953, doi: 10.1190/1.1623635.

Guo, H., K. J. Marfurt, and J. Liu, 2009, Principal component spectral analysis: Geophysics, 74, no. 4, 35–43.

Haykin, S., 2009. Neural networks and learning machines, 3rd ed.: Pearson

Kohonen, T., 2001,Self organizing maps: Third extended addition, Springer, Series in Information Services, Vol. 30.

Laudon, C., Stanley, S., and Santogrossi, P., 2019, Machine Leaming Applied to 3D Seismic Data from the Denver-Julesburg Basin Improves Stratigraphic Resolution in the Niobrara, URTeC 337, in press

Roden, R., and Santogrossi, P., 2017, Significant Advancements in Seismic Reservoir Characterization with Machine Learning, The First, v. 3, p. 14-19

Roden, R., Smith, T., and Sacrey, D., 2015, Geologic pattern recognition from seismic attributes: Principal component analysis and self-organizing maps, Interpretation, Vol. 3, No. 4, p. SAE59-SAE83.

Santogrossi, P., 2017, Classification/Corroboration of Facies Architecture in the Eagle Ford Group: A Case Study in Thin Bed Resolution, URTeC 2696775, doi 10.15530-urtec-2017-<2696775>.