A multi-disciplinary approach to establish a workflow for the application of machine learning for detailed reservoir description – Wisting case study

By Sharareh Manouchehri, Nam Pham, Terje A. Hellem and Rocky Roden | Published with permission: First Break | Volume 38, July 2020

Introduction

This paper presents a multidisciplinary approach, maximizing information extraction from seismic data to predict lithofacies and reservoir properties, based on the following steps:

  • Multi-attribute seismic analysis based on an unsupervised machine learning process called Self-Organizing Maps (SOMs). The selection of input attributes was thoroughly tested and optimized, based on close cooperation between geophysicists and geologists to extract more extensive and detailed geological features from seismic data.
  • Using the information from nearby wells and knowledge of rock physics, the individual neural classes were quantified and validated and then reorganized and translated to formation properties such as lithofacies, porosity, and clay content.

The study focused on the benefits and additional information that can be gained with this new approach compared to traditional quantitative interpretation, i.e., a prediction from acoustic impedance. Multi-attribute classification using machine learning (SOM) gave a better representation of the seismic characters, detecting the geologic trends in the field. A detailed quantitative interpretation of SOM neural classes was established to validate and translate formation-related classes optimally for reservoir prediction, and to eliminate classes irrelevant to the formations (i.e., seismic noise).

The result from this (‘Wisting’) case study shows that the new method gives the best match to the well data and extracts more reservoir-related information from seismic data compared to the conventional quantitative interpretation (QI) approach. In the upper part of the Triassic, with fluvial sediments assigned to the RG2 unit (Fruholmen Fm.), the reservoir quality and extent of mud clast-rich channel intervals are debated. In two of the wells, E and B, (see disclaimer at the end of the paper), a thicker mud unit was observed, and it was debated if this could act as a barrier to the overlying good reservoir. The result shows that the mud intervals are deposited locally and do not represent a regional mud layer. The additional information from seismic data seems to be valuable when used as input and refinement to the digital geological model.

Geological setting and challenges

This study is part of a multidisciplinary activity performed by Idemitsu Petroleum Norge AS (IPN) aiming at establishing a full-field geological model of the Wisting discovery as input to the production planning and development.

The Wisting and Hanssen discoveries are located in blocks 7324/7 and 7324/8 in the Norwegian sector of the Barents Sea (Figure 1a). The production licence PL537 was awarded in 2009 with OMV (25%) as the operator. Other partners include Equinor (35%), IPN (20%) and Petoro (20%). Equinor has recently taken over as operator for the development phase of the Wisting & Hanssen discoveries, with OMV due to regain operatorship at the start-up of production.

The first well was drilled in 2013 and made an oil discovery in the Wisting Central fault segment. The reservoir comprises the Late Triassic to Middle Jurassic Realgrunnen Subgroup (Figure 1b).

The lithostratigraphic nomenclature for the Triassic and Juras- sic generally applied in the Norwegian sector of the Barents Sea was initially defined based on type wells in the Hammerfest Basin (Dalland et al., 1988). Many companies use biostratigraphy as the basis for applying this nomenclature at a formation level in other basins and even structures hundreds of kilometres away from the type area. However, the IPN team applied a neutral subdivision of the reservoir according to four flow units designated RG1 to RG4, as denoted in Figure 1b. The uppermost unit of the Realgrunnen Subgroup (RG1) is the Stø Formation, which is the most prolific reservoir of the Norwegian sector of the Barents Sea.

To date, six wells have been drilled in the licence area. Except for a deviated well, which aimed to test deeper stratigraphic levels in the Hanssen structure, and a horizontal well that passes through three fault blocks, the four vertical wells tested four individual fault blocks. The most promising structures were named after Roald Amundsen’s companions who reached the South Pole in 1911; Olav Bjaaland, Helmer Hanssen, Sverre Hassel, and Oscar Wisting. Based on the wells in the Wisting Central and Hanssen structures, the licence partners focused mainly on the Stø Formation (RG1) as the producible reservoir. IPN’s RG2 (Fruholmen Fm.) was inferred as representing isolated fluvial channels deposited within a flood plain with low vertical and horizontal communication. In addition, the mud intervals at the top of RG2 in wells E and B were considered to represent a major flooding event that works as a barrier to communication between RG1 and RG2.

Machine learning for detailed reservoir description — Wisting case study Figure 1
Figure 1. Location of study area and stratigraphic framework. Location of study area and stratigraphic framework.

Based on observations on very detailed seismic site survey data, IPN inferred an alternative model for RG2 as amalgamated channels of fluvial and estuarine origin filling more extensive incised valleys during a fall in sea level. The challenges have been to document that this unit comprises significant producible resources, and that the contact between RG1 and RG2 represents a regional unconformity known in the Barents Sea and throughout Arctic Canada as the ‘Rhaetian unconformity’ (Embry, 2011; Lord et al., 2019). Within the licence area, the biostratigraphic data show that there is a break in the stratigraphy from the Norian (RG2) to Pliensbachian (RG1.5). The mud intervals at the top of RG2 in wells E and B are most likely local infill of abandoned channels or oxbow lakes at different Norian stratigraphic levels.

The incisions into the RG3 and other intraformational mud layers during deposition of RG2 have left several intervals of mudclast-conglomerates within the fluvial channel deposits. IPN infers these mudclast-conglomerates as representing the outer bends of the fluvial channels eroding into older, mud-dominated facies. In contrast, the dominant part of the channel deposits is cleaner sands. In the cores from the Wisting and Hanssen discovery wells, the base of the channels within RG2 is dominated by the mud clasts. The mud clast intervals are characterized by high gamma response and low porosity. Based on the well logs, these intervals might be mistaken as mudstones. Except for a few scattered mud intervals, no typical flood plain deposits have been encountered within the RG2. The cored interval in well B shows more variation, including very good reservoir sands. The logs from the uncored wells, D and A, show the typical bell-shaped log response of some of the channels. This supports our understand- ing of the facies within the fluvial channels.

IPN saw the potential of using the machine learning capabilities of the Paradise software applied to the 3D high-resolution P-cable seismic data, which was acquired in 2016. The interpretation team expected the commercial software to assist in resolving the problem of documenting the more complex facies distribution indicated by the well data for the units below the RG1 (Stø Fm.)

Application of multi-attribute analysis using machine learning

Principal Component Analysis (PCA) was used first to determine the relative variance – ‘responsiveness’ — among a larger set of candidate attributes (Roden et al., 2015). Three attributes were identified that imparted the greatest energy to the study area: Acoustic Impedance (AI), Envelope, and Attenuation (Instantaneous Q), with AI and Envelope being significantly dominant. AI is the primary indicator of rock properties, and Envelope is a function of the complex seismic trace. The AI shows the absolute value (cumulative sum of seismic responses), while Envelope is a measure of the total energy involved in the seismic reflection response. In terms of application, AI detects rock bodies and layers while Envelope is a physical attribute that is effective in discriminating sequence boundaries. Though less dominant, Instantaneous Q has been known to correlate to physical rock properties such as porosity (Ogiesoba, 2016). The multi-attribute analysis used the Self-Organizing Map (SOM) machine learning process, which is a non-linear, robust classification method. The SOM process, developed initially by Teuvo Kohonen, reveals similarities in the classification results (Kohenen, 1982, 2001). The commercial machine learning software employed in the project produces the SOM classification results by different numbers of classes, the quantity of which are selected by the user, e.g., 16, 25, 64, etc. Each class within a given result set corresponds to a neuron that has learned and classified patterns in the data through an unsupervised process, limited only by time or depth, horizons, and Inline-Crossline. The goal of the SOM process is to identify patterns that exist among a set of attribute volumes due to changes in geology and stratigraphy.

The software enables the running of multiple classification results and the comparing of those results to the ground truth. It also has the advantage of running numerous classification results using different numbers of neurons, called ‘neural configurations’. However, like other machine learning processes that are statistically derived, the SOM must be correlated to well control to refine the interpretation. Some multi-attribute classification results may relate to formation properties, while others do not. After evaluating the different number of classes — neural configurations — using the above sets of three attributes, the geoscience team concluded that 64 neural classes resulted in an optimum size that best corroborated to well control and the geology of the area.

Initially, the SOM process was applied to Acoustic Impedance (AI) and Envelope alone. However, after studying the cores and well data, some of the features could not be delineated using amplitude-based attributes. For example, the mudclast-conglomerate within cleaner sand deposits, which does not exhibit significant acoustic contrast and could not be discriminated from mud layers, is therefore undetectable using AI and Envelope. The two latter attributes exhibit minor variation of seismic dispersion and attenuation, therefore Instantaneous Q was added as an input to the SOM ‘recipe’ or set of attributes.

Machine learning, correlation statistics, and quantitative interpretation

Understanding rock physics is critical for the interpreter to differentiate between physical and non-physical data and noise or reservoir-related effects, thereby establishing a reliable/meaningful relationship between seismic responses and reservoir properties. The next step in the process was to quantify and validate the individual neural classes, then reorganize and translate the classes to formation properties such as lithofacies, porosity, and Vclay. The input acoustic impedance attribute was created based on a post-stack inversion, in which the background model was generated using only a single well. No depth trend was applied to avoid a compaction trend influencing the prediction of facies. The workflow, shown in Figure 2, illustrates the combination of the SOM machine learning process and statistical data analysis. The objective of the combination of statistics and machine learning was to obtain two types of predictions across specific zones:

Machine learning for detailed reservoir description — Wisting case study Figure 2
Figure 2. Workflow for seismic reservoir characterization.

Correlation statistics were applied to the well log data and neural classification results to produce an overall quantitative analysis of the potential reservoir. Logs from five wells were statistically compared to the 64 neural classes (the neurons), while the log for a highly deviated, horizontal well was withheld as a blind test. The results show good correlation between specific neurons and the log data and justify being applied as guidance in the reservoir simulation model.

The relationships between AI and porosity (PHIT), AI and Vclay (VCL), and AI vs. individual neurons were evaluated (Figure 3). The relation between porosity and impedance aligns well with the rock physics trend, i.e., higher porosity, lower impedance, or opposite (Figure 3a). The presence of clay reduces porosity, thereby increasing impedance; however, a large amount of clay can also reduce impedance. For instance in the RG-3 unit, since clay has a lower bulk modulus than sand. A small amount of cementation (1-2%) for clean sandstone leads to stiffening of the rock matrix, thus increasing impedance in the case of RG1.
Together, these factors produce a non-linear and scattered relationship between porosity and AI; however, the reasonable correlation between AI and the neuron classes (Figure 3-c) demonstrate the following:

  • The AI attribute strongly dominates the SOM cube.
  • Neural classes from the SOM are a good predictor of porosity and are consistent with AI.
  • Data away from the main trend is influenced by other attributes and yields additional reservoir-related information that is not available through traditional interpretation methods.
Machine learning for detailed reservoir description — Wisting case study Figure 3
Figure 3. Rock physic relations: a) PHIT vs AI (log) , b) VCL vs AI (log), and c) AI (Pcable) and neuron classes (see text for details).
Property results vs. ground truth

The commercial machine-learning software includes a 2D Colourmap (Figure 3c) with the neurons arranged in a numbered array, in this case 1 to 64. Where two neurons are adjacent, their properties are most similar, while the farther apart they are located on the 2D ‘neural’ map, or neural topology, the more dissimilar the properties. The number of the neurons indicates a relative location on the map, starting with number 1 in the lower left and proceeding left to right, bottom to top. Given that the input to the SOM was three attributes, each neuron had a different mix or weight of attributes, and that relative make-up of each neuron is available for inspection within the software. An analysis of the composition of individual neurons to the attributes comprising each neural class demonstrated that AI was the main contributor. Since the SOM cube was found to be strongly dominated by AI, it also was a good predictor of porosity; however, the data away from the main trend was found to be governed by other attributes, which yielded additional reservoir-related information.

The large scatter in the data suggested that each neuron be examined independently relative to porosity (PHIT) and Vclay (VCL). The ordering of the neural classes (say neurons 40 vs. 41)does not have a continuous analog relationship within the 2D Colourmap. Rather, they exist as independent discrete classes, related only by similarity, according to the SOM Kohonen process. Therefore, gridding, interpolating, smoothing, and the removal of bad data was applied to the individual neurons within the 2D Colourmap to increase the neighbouring dependency among neurons, producing better lateral continuity and a more stable result.

Building on the idea of the 2D Colourmap, the prediction method involved creating a 2D property map, instead of 1D (Figure 4). The zones were subdivided into two: RG1 and RG2,3. RG1 has high porosity, but relatively high impedance due to a small amount of cementation. This is the opposite of the general trend between AI and porosity (higher porosity, lower impedance), such as in RG2,3, which made adding zonation necessary. As input to the training dataset, the log data was upscaled at 1.5 m to minimize the effect of differing scales. (The upscaling would also allow a direct input to the geological model later in the workflow.) To avoid overtraining and to generate a more stable result that was less sensitive to noise, data samples were used between +/- 1 inline and crossline around the well, yielding many more data samples while mitigating the effect of noise on the training data.

Machine learning for detailed reservoir description — Wisting case study Figure 4
Figure 4. SOM translate (2D SOM property maps): a) SOM neural classes are decomposed into 2D map (8 x 8), 2D property maps of porosity (b) and Vclay (c) in the zones for RG2 and 3.

Figure 4 shows 2D property maps of porosity (PHIT) and Vclay (VCL) in the zones for RG2 and 3. In general, the SOM 2D Colourmap (Figure 4b) shows high porosity, clean sand in the upper left corner, and low porosity, high VCL in the lower part.
For comparison and quality control, the prediction result from the new method was compared to the conventional method where porosity and clay content is derived from acoustic impedance (ref. Figure 3a-c). Figure 5 shows the predicted results versus the logs for wells A (Figure 5b) and B (Figure 5a), which are representative of the Wisting and Hanssen discoveries. The prediction of properties from AI alone is a fair match to the log data; however, the prediction from the SOM process using the three attributes referenced above shows the best match. AI is not sensitive to lithology variation in RG2, while the SOM multi-attribute classification can detect lithology variation (mud plug and mudclast-conglomerate) in RG2. The presence of lower porosity zones was also more accurately predicted by the machine learning results when compared to AI alone. Note that the SOM is optimized for the RG interval and is not valid for intervals above and below.

Machine learning for detailed reservoir description — Wisting case study Figure 5
Figure 5. Examples of well predictions for porosity and Vclay; well sections for B(a) and A(b) plotted with the columns as following, from left: Vclay from different sources plotted for comparison (col. 1), density-neutron (col. 2), total porosities from different sources plotted for comparison (col. 3), SOM neural classes (col. 4), AI from log and AI-derived from Pcable (col. 5) and Pcable seismic (col. 6).

Cross plots of porosity (PHIT) and Vclay (VCL) in Figure 6 show the improvement in correlation factors for the two properties. Version 1 (Figure 6a,b) was predicted directly from 64 neural classes without applying the neuron numbering dependency on the 2D Colourmap, and before subdividing the zones RG1 and RG2,3. Following these changes in the prediction method, the correlation factors increased respectively: porosity from 0.3 to 0.47 and VCL from 0.01 to 0.44, as shown in the charts on the right identified as Version 2 (Figure 6b,d). A correlation factor approaching 0.5 is considered very good since the prediction is based on seismic data, thereby enabling a reliable estimation of the trend away from the well.

Machine learning for detailed reservoir description — Wisting case study Figure 6
Figure 6. Prediction result cross-correlation, showing the improvement in correlation factors for porosity and Vclay from initial version(a,b) to version 2(c,d). See text for details

A physical rock trend for Vclay prediction was applied to obtain an optimal result, which improved prediction by avoiding overfitting and minimizing the impact of noise. With a hard rock trend (AI-VCL trend, ref. to Figure 3), those neural classes were removed for prediction away from the AI-VCL trend, retaining only those close to the main trend (Figure 7b). With the soft rock trend, those neural classes which are away from the main rock trend were included for prediction, i.e., including other attributes (Envelope and Inst. Q). To stabilize the prediction result and minimize noise effect, some neural classes, which predicted a large variance with the main rock trend, were also excluded.

Figure 7a shows Vclay prediction derived from AI, which is a fair match to the well, while the prediction with the hard rock trend (Figure 7b) is comparable to the one derived from AI. With the soft rock trend, including the contribution from other attributes, additional information, such as thin layer features, can be observed (Figure 7c). The mudclast-conglomerate channel features and patterns are detected using the soft rock trend, especially in middle and lower RG2, (ref. to red arrows), and are confirmed by nearby wells (B and C). The prediction result in 7c reflects the geological interpretation of RG2. Several intervals of mudclast-conglomerate within the fluvial channel represent the outer bends of the fluvial channels eroding into older mud dominated facies, while the dominant part of the channel deposits are comprised of cleaner sands. The prediction with the soft rock trend gives the best match to the well and is the final version.

Machine learning for detailed reservoir description — Wisting case study Figure 7
Figure 7. Cross-section for comparison of VCL predictions: VCL derived from AI(a), VCL from SOM classification with hard rock trend (b), VCL from SOM classification with soft rock trend (c); red arrows highlight the possible channel features which are apparent in (c), but not visible or unclear in (a, b).

Figure 8 shows Vclay maps at upper RG2, derived from acoustic impedance (8a), multi-attribute classification (SOM) with hard rock trend (8b), and the soft rock trend (8c). The acoustic impedance with low frequency can only detect thick layers. At the same time, the Vclay prediction with the soft rock trend, including other attributes, can pick up thin layers, including more channel features. Roden (Roden et al., 2017) identified the phenomenon of multi-attribute classification detecting thin beds below seismic tuning thickness when multiple attributes are classified simultaneously at a single-sample scale. The red arrows and polygons highlight the possible channel features, which are apparent in (8c), while those features are not visible or unclear are in (8a). The channel features crossing well 7324/8-3 (E-W direction) and well 7324/7-2 (N-S direction) appeared locally. These features are related to high Vclay and low porosity found in the wells, which are interpreted as mud plugs, according to the core description.

Machine learning for detailed reservoir description — Wisting case study Figure 8
Figure 8. Comparison of VCL prediction in map view at the uppermost RG2: a) VCL derived from AI, b) VCL from SOM classification with hard rock trend, c) VCL from SOM classification with soft rock trend; red arrows and polygons highlight the possible channel features which are apparent in (c), but not visible or unclear in (a).

Figure 9a shows a comparison of the core description, well logs, SOM, and prediction of PHIT and VCL for well B. The SOM classification to the left of the logs relates to the SOM 2D Colourmap in Figure 9b. Wireline logs GR, DEN, NEU, and AC (compressional sonic) are shown in the next column, followed to the right by the core description made by Ichron Ltd for PL537. The grain size is accentuated by these colours: yellow for clean fine-to-coarse sandstones; light yellow indicates argillaceous very-fine-to-fine sandstone; various shades of green indicate claystones-to-siltstones; and orange indicates the mud clast conglomerates. Sedimentary structures such as cross-bedding, lamination, and bioturbation are not readable at the presented scale but are designated between the lithology column to the left and the grain size curve to the right. The two columns to the right show the colour-shaded PHIT and VCL logs calculated from the soft rock trend as described above (Figures 5 and 7), the unshaded logs in the background are upscaled logs based on the well logs. Figure 9b shows a SOM with colour-coding based on visual comparison of the classification log, as shown in Figure 9a (left column) and the core descriptions and facies inferred from wireline logs of the vertical wells within the seismic survey.

Machine learning for detailed reservoir description — Wisting case study Figure 9
Figure 9. Comparison of core description, well logs, SOM, and prediction of PHIT and VCL. See text for details.

Figure 10 demonstrates the impact of using porosity prediction from multi-attribute classification (SOM) into the geological model. Figure 10a (extrapolation from wells) shows a large area (blue colour) surrounding wells 7324/8-3 and 7324/7-2 dominated by low porosity away from the wells, while the prediction from the SOM classification (10b) indicates low porosity channel features crossing the wells which are deposited locally. As a result, by applying this 3D cube as the trend for modelling, the porosity (10c) shows a higher average than the one using well only (10a) and seems to gain more geological details.

Machine learning for detailed reservoir description — Wisting case study Figure 10
Figure 10. Examples of geological models demonstrating porosity variation in the uppermost RG2: a) extrapolation from wells, b) re-gridded PHIT from SOM classification and c) co-kriged modelling based on the input from (b); (gridcell size: 50 m x 50 m x 1.5 m).
Observations and discussion

As summarized below, the results from the study using machine learning show better alignment with well data in comparison to the traditional QI approach, and it provides additional information such as the detection of thin layers and channel features.

  • Input attributes to SOM classification: AI is the primary indicator of rock properties, detecting rock bodies and layers, while Envelope is a function of the complex seismic trace and is effective in discriminating sequence boundaries. For thin layers. The sequence boundaries from Envelope are the same as the sequence bodies and therefore contribute to the detection of thin layers and channel features. Inst. Q represents seismic dispersion and attenuation, derived from instantaneous frequency, Envelope, and its derivative. Inst. Q is, therefore, susceptible to signal variation, thin layers, and channel features, but it is also sensitive to noise. Together, A.I., Envelope, and Inst. Q represent detailed signal characteristics of seismic.
  • Classification using machine learning (SOM): SOM gives a better representation of the multi-input data. Unlike supervised machine learning using well data, the SOM method does not require well data as input. Therefore, the training can be run on the whole dataset, searching for different combinations/classes, geological channel features, and patterns from seismic. After several tests with different numbers of classes (neural configurations) and close cooperation in the team, 64 neural classes were produced and organized by SOM classification, representing best corroboration to well control and the geology of the area.
  • Quantitative interpretation: SOM classification is unsupervised machine learning, based on a statistical approach. How- ever, the classification and ordering of the neural classes are well organized on the 2D-SOM map following their similarity characterization, i.e., neuron nr. 28 is in a family with neurons nr. 19, 20, 21, 27, 29 and 36. This clever organization is exploited and used for quantitative interpretation in this study. Using the information from wells and knowledge of rock physics, several exercises have been carried out to improve the results. These include property smoothing on a 2D SOMmap, subdividing the reservoir zones, and applying soft and hard rock trends, have been carried out to improve the results. The individual neural classes were quantified and validated, then reorganized and translated to formation properties. Classes irrelevant to formations, i.e., seismic noise and other artifacts, were eliminated or minimized.

The study shows promising results. However, there is potential for improvement in exploiting more information from seismic while eliminating noise and other artifacts.

Conclusions

Several wells were used to quantify the 64 neural classes and translate the classes to lithofacies and reservoir properties, such as porosity and Vclay. The following results show good correlation with the log data and may provide additional detailed input for the geological model and eventually the reservoir simulation model:

  • Distribution of the shale layer observed in RG2 at well B seems to be localized/limited. The limited amount of shale observed in RG2 may indicate good lateral and vertical
  • Blind test along the horizontal well path confirms a good relationship between the prediction result and the well

This study demonstrates a clear improvement in reservoir characterization compared to the traditional QI approach (quantitative interpretation). More information was gained from seismic data for input into reservoir prediction. The successful result is based on close cooperation of different disciplines and specialists, while applying machine learning, statistics, rock physics and a firm geological understanding of the region.

Acknowledgments

The authors would like to thank the PL 537 licence partners for permission to publish this paper. We would also like to thank to our colleagues in IPN: Toshiro Tamura, Tone Merete Øksenvåg and Marius Lunde for their contributions. Thanks also are extended to Geophysical Research, LLC (d/b/a Geophysical Insights) for the research and development of the Paradise AI workbench and the machine learning applications used in this paper. Finally, we would like to thank Hal Green for review of the manuscript and Leah Mann for editing the graphics.

Disclaimer

The names of the wells herein are anonymous on the well logs and cross-sections. The conclusions set forth above are those of the authors and do not necessarily represent the licence partners or policy of the licensing area.

References

Dalland, A., Worsley, D. and Ofstad, K. [1988]. A lithostratigraphical scheme for the Mesozoic and Cenozoic succession offshore mid- and northern Norway. NPD – Bulletin, 4, 65.

Embry, A. [2011]. Petroleum prospectivity of the Triassic-Jurassic succession of Sverdrup Basin, Canadian Artic Archipelago. In: (Eds.) Spencer, A.M., Embry, A.F., Gautier, D.L., Støupakova, A.V. and Sorensen, K., Arctic Petroleum Geology, Geological Society London, Memoir, 35, 545-558, Doi: 10.1144/M35.36

Lord, G.S., Mørk, M.B.E.,; Mørk, A. and Olaussen, S. [2019]. Sedi- mentology and petrography of the Svenskøya Formation on Hopen, Svalbard: an analogue to sandstone reservoirs in the Realgrunnen Subgroup. Polar Research, 38, Doi: 10.33265/polar.v38.3523.

Kohonen, T. [1982]. Self-organized formation of topologically correct feature maps. Biological Cybernetics, 43, 59-69.

Kohonen, T. [2001]. Self-Organizing Maps. Third Extended Edition. Springer Series in Information Sciences, 30, Springer-Verlag, Berlin, Germany.

Ogiesoba, O. [2016]. Application of the Instantaneous Quality Factor (Q) in the characterization of the Austin Chalk and Eagle Ford Shale, South Texas. AAPG Search and Discovery, #41781.

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

Roden, R., Smith, T., Santogrossi, P., Sacrey, D. and Jones, G. [2017]. Seismic Interpretation Below Tuning with Multi-attribute Analysis. The Leading Edge, 36 (4), 282-368.

Welcome Back!

Download PDF here

OR

Request access by filling the form below to download full PDF.
Name(Required)
Most Popular Papers
Case Study: An Integrated Machine Learning-Based Fault Classification Workflow
We build a fully automated machine learning-based fault detection workflow to compute the parameterized fault classification results ...
Case Study with Petrobras: Applying Unsupervised Multi-Attribute Machine Learning for 3D Stratigraphic Facies Classification in a Carbonate Field, Offshore Brazil
This study with Petrobras presents the results of a multi-attribute, machine learning study over a pre-salt carbonate field in the ...
Applying Machine Learning Technologies in the Niobrara Formation, DJ Basin, to Quickly Produce an Integrated Structural and Stratigraphic Seismic Classification Volume Calibrated to Wells
Carolan Laudon, Jie Qi, Yin-Kai Wang, Geophysical Research, LLC (d/b/a Geophysical Insights), University of Houston | Published with permission: Unconventional Resources ...
Shopping Cart
  • Registration confirmation will be emailed to you.

  • We're committed to your privacy. Geophysical Insights uses the information you provide to us to contact you about our relevant content, events, and products. You may unsubscribe from these communications at any time. For more information, check out our Privacy Policy

    Jan Van De MortelGeophysicist

    Jan Van De Mortel

    Jan is a geophysicist with a 30+ year international track record, including 20 years with Schlumberger, 4 years with Weatherford, and recent years actively involved in Machine Learning for both oilfield and non-oilfield applications. His work includes developing solutions and applications around transformer networks, probabilistic Machine Learning, etc. Jan currently works as a technical consultant at Geophysical Insights for Continental Europe, the Middle East, and Asia.

    Mike PowneyGeologist | Perceptum Ltd

    Mike Powney

    Mike began his career at SRC a consultancy formed from ECL where he worked extensively on seismic data offshore West Africa and the North Sea. Mike subsequently joined Geoex MCG where he provides global G&G technical expertise across their data portfolio. He also heads up the technical expertise within Geoex MCG on CCUS and natural hydrogen. Within his role at Perceptum, Mike leads the Machine Learning project investigating seismic and well data, offshore Equatorial Guinea.

    Tim GibbonsSales Representative

    Tim Gibbons

    Tim has a BA in Physics from the University of Oxford and an MSc in Exploration Geophysics from Imperial College, London. He started work as a geophysicist for BP in 1988 in London before moving to Aberdeen. There he also worked for Elf Exploration before his love of technology brought a move into the service sector in 1997. Since then, he has worked for Landmark, Paradigm, and TGS in a variety of managerial, sales, and business development roles. Since 2018, he has worked for Geophysical Insights, promoting Paradise throughout the European region.

    Dr. Carrie LaudonSenior Geophysical Consultant

    Applying Unsupervised Multi-Attribute Machine Learning for 3D Stratigraphic Facies Classification in a Carbonate Field, Offshore Brazil

    We present results of a multi-attribute, machine learning study over a pre-salt carbonate field in the Santos Basin, offshore Brazil. These results test the accuracy and potential of Self-organizing maps (SOM) for stratigraphic facies delineation. The study area has an existing detailed geological facies model containing predominantly reef facies in an elongated structure.

    Carrie LaudonSenior Geophysical Consultant - Geophysical Insights

    Automatic Fault Detection and Applying Machine Learning to Detect Thin Beds

    Rapid advances in Machine Learning (ML) are transforming seismic analysis. Using these new tools, geoscientists can accomplish the following quickly and effectively:

    • Run fault detection analysis in a few hours, not weeks
    • Identify thin beds down to a single seismic sample
    • Generate seismic volumes that capture structural and stratigraphic details

    Join us for a ‘Lunch & Learn’ sessions daily at 11:00 where Dr. Carolan (“Carrie”) Laudon will review the theory and results of applying a combination of machine learning tools to obtain the above results.  A detailed agenda follows.

    Agenda

    Automated Fault Detection using 3D CNN Deep Learning

    • Deep learning fault detection
    • Synthetic models
    • Fault image enhancement
    • Semi-supervised learning for visualization
    • Application results
      • Normal faults
      • Fault/fracture trends in complex reservoirs

    Demo of Paradise Fault Detection Thoughtflow®

    Stratigraphic analysis using machine learning with fault detection

    • Attribute Selection using Principal Component Analysis (PCA)
    • Multi-Attribute Classification using Self-Organizing Maps (SOM)
    • Case studies – stratigraphic analysis and fault detection
      • Fault-karst and fracture examples, China
      • Niobrara – Stratigraphic analysis and thin beds, faults
    Thomas ChaparroSenior Geophysicist - Geophysical Insights

    Paradise: A Day in The Life of the Geoscientist

    Over the last several years, the industry has invested heavily in Machine Learning (ML) for better predictions and automation. Dramatic results have been realized in exploration, field development, and production optimization. However, many of these applications have been single use ‘point’ solutions. There is a growing body of evidence that seismic analysis is best served using a combination of ML tools for a specific objective, referred to as ML Orchestration. This talk demonstrates how the Paradise AI workbench applications are used in an integrated workflow to achieve superior results than traditional interpretation methods or single-purpose ML products. Using examples from combining ML-based Fault Detection and Stratigraphic Analysis, the talk will show how ML orchestration produces value for exploration and field development by the interpreter leveraging ML orchestration.

    Aldrin RondonSenior Geophysical Engineer - Dragon Oil

    Machine Learning Fault Detection: A Case Study

    An innovative Fault Pattern Detection Methodology has been carried out using a combination of Machine Learning Techniques to produce a seismic volume suitable for fault interpretation in a structurally and stratigraphic complex field. Through theory and results, the main objective was to demonstrate that a combination of ML tools can generate superior results in comparison with traditional attribute extraction and data manipulation through conventional algorithms. The ML technologies applied are a supervised, deep learning, fault classification followed by an unsupervised, multi-attribute classification combining fault probability and instantaneous attributes.

    Thomas ChaparroSenior Geophysicist - Geophysical Insights

    Thomas Chaparro is a Senior Geophysicist who specializes in training and preparing AI-based workflows. Thomas also has experience as a processing geophysicist and 2D and 3D seismic data processing. He has participated in projects in the Gulf of Mexico, offshore Africa, the North Sea, Australia, Alaska, and Brazil.

    Thomas holds a bachelor’s degree in Geology from Northern Arizona University and a Master’s in Geophysics from the University of California, San Diego. His research focus was computational geophysics and seismic anisotropy.

    Aldrin RondonSenior Geophysical Engineer - Dragon Oil

    Bachelor’s Degree in Geophysical Engineering from Central University in Venezuela with a specialization in Reservoir Characterization from Simon Bolivar University.

    Over 20 years exploration and development geophysical experience with extensive 2D and 3D seismic interpretation including acquisition and processing.

    Aldrin spent his formative years working on exploration activity in PDVSA Venezuela followed by a period working for a major international consultant company in the Gulf of Mexico (Landmark, Halliburton) as a G&G consultant. Latterly he was working at Helix in Scotland, UK on producing assets in the Central and South North Sea.  From 2007 to 2021, he has been working as a Senior Seismic Interpreter in Dubai involved in different dedicated development projects in the Caspian Sea.

    Deborah SacreyOwner - Auburn Energy

    How to Use Paradise to Interpret Clastic Reservoirs

    The key to understanding Clastic reservoirs in Paradise starts with good synthetic ties to the wavelet data. If one is not tied correctly, then it will be easy to mis-interpret the neurons as reservoir, whin they are not. Secondly, the workflow should utilize Principal Component Analysis to better understand the zone of interest and the attributes to use in the SOM analysis. An important part to interpretation is understanding “Halo” and “Trailing” neurons as part of the stack around a reservoir or potential reservoir. Deep, high-pressured reservoirs often “leak” or have vertical percolation into the seal. This changes the rock properties enough in the seal to create a “halo” effect in SOM. Likewise, the frequency changes of the seismic can cause a subtle “dim-out”, not necessarily observable in the wavelet data, but enough to create a different pattern in the Earth in terms of these rock property changes. Case histories for Halo and trailing neural information include deep, pressured, Chris R reservoir in Southern Louisiana, Frio pay in Southeast Texas and AVO properties in the Yegua of Wharton County. Additional case histories to highlight interpretation include thin-bed pays in Brazoria County, including updated information using CNN fault skeletonization. Continuing the process of interpretation is showing a case history in Wharton County on using Low Probability to help explore Wilcox reservoirs. Lastly, a look at using Paradise to help find sweet spots in unconventional reservoirs like the Eagle Ford, a case study provided by Patricia Santigrossi.

    Mike DunnSr. Vice President of Business Development

    Machine Learning in the Cloud

    Machine Learning in the Cloud will address the capabilities of the Paradise AI Workbench, featuring on-demand access enabled by the flexible hardware and storage facilities available on Amazon Web Services (AWS) and other commercial cloud services. Like the on-premise instance, Paradise On-Demand provides guided workflows to address many geologic challenges and investigations. The presentation will show how geoscientists can accomplish the following workflows quickly and effectively using guided ThoughtFlows® in Paradise:

    • Identify and calibrate detailed stratigraphy using seismic and well logs
    • Classify seismic facies
    • Detect faults automatically
    • Distinguish thin beds below conventional tuning
    • Interpret Direct Hydrocarbon Indicators
    • Estimate reserves/resources

    Attend the talk to see how ML applications are combined through a process called "Machine Learning Orchestration," proven to extract more from seismic and well data than traditional means.

    Sarah Stanley
    Senior Geoscientist

    Stratton Field Case Study – New Solutions to Old Problems

    The Oligocene Frio gas-producing Stratton Field in south Texas is a well-known field. Like many onshore fields, the productive sand channels are difficult to identify using conventional seismic data. However, the productive channels can be easily defined by employing several Paradise modules, including unsupervised machine learning, Principal Component Analysis, Self-Organizing Maps, 3D visualization, and the new Well Log Cross Section and Well Log Crossplot tools. The Well Log Cross Section tool generates extracted seismic data, including SOMs, along the Cross Section boreholes and logs. This extraction process enables the interpreter to accurately identify the SOM neurons associated with pay versus neurons associated with non-pay intervals. The reservoir neurons can be visualized throughout the field in the Paradise 3D Viewer, with Geobodies generated from the neurons. With this ThoughtFlow®, pay intervals previously difficult to see in conventional seismic can finally be visualized and tied back to the well data.

    Laura Cuttill
    Practice Lead, Advertas

    Young Professionals – Managing Your Personal Brand to Level-up Your Career

    No matter where you are in your career, your online “personal brand” has a huge impact on providing opportunity for prospective jobs and garnering the respect and visibility needed for advancement. While geoscientists tackle ambitious projects, publish in technical papers, and work hard to advance their careers, often, the value of these isn’t realized beyond their immediate professional circle. Learn how to…

    • - Communicate who you are to high-level executives in exploration and development
    • - Avoid common social media pitfalls
    • - Optimize your online presence to best garner attention from recruiters
    • - Stay relevant
    • - Create content of interest
    • - Establish yourself as a thought leader in your given area of specialization
    Laura Cuttill
    Practice Lead, Advertas

    As a 20-year marketing veteran marketing in oil and gas and serial entrepreneur, Laura has deep experience in bringing technology products to market and growing sales pipeline. Armed with a marketing degree from Texas A&M, she began her career doing technical writing for Schlumberger and ExxonMobil in 2001. She started Advertas as a co-founder in 2004 and began to leverage her upstream experience in marketing. In 2006, she co-founded the cyber-security software company, 2FA Technology. After growing 2FA from a startup to 75% market share in target industries, and the subsequent sale of the company, she returned to Advertas to continue working toward the success of her clients, such as Geophysical Insights. Today, she guides strategy for large-scale marketing programs, manages project execution, cultivates relationships with industry media, and advocates for data-driven, account-based marketing practices.

    Fabian Rada
    Sr. Geophysicist, Petroleum Oil & Gas Services

    Statistical Calibration of SOM results with Well Log Data (Case Study)

    The first stage of the proposed statistical method has proven to be very useful in testing whether or not there is a relationship between two qualitative variables (nominal or ordinal) or categorical quantitative variables, in the fields of health and social sciences. Its application in the oil industry allows geoscientists not only to test dependence between discrete variables, but to measure their degree of correlation (weak, moderate or strong). This article shows its application to reveal the relationship between a SOM classification volume of a set of nine seismic attributes (whose vertical sampling interval is three meters) and different well data (sedimentary facies, Net Reservoir, and effective porosity grouped by ranges). The data were prepared to construct the contingency tables, where the dependent (response) variable and independent (explanatory) variable were defined, the observed frequencies were obtained, and the frequencies that would be expected if the variables were independent were calculated and then the difference between the two magnitudes was studied using the contrast statistic called Chi-Square. The second stage implies the calibration of the SOM volume extracted along the wellbore path through statistical analysis of the petrophysical properties VCL and PHIE, and SW for each neuron, which allowed to identify the neurons with the best petrophysical values in a carbonate reservoir.

    Heather Bedle
    Assistant Professor, University of Oklahoma

    Heather Bedle received a B.S. (1999) in physics from Wake Forest University, and then worked as a systems engineer in the defense industry. She later received a M.S. (2005) and a Ph. D. (2008) degree from Northwestern University. After graduate school, she joined Chevron and worked as both a development geologist and geophysicist in the Gulf of Mexico before joining Chevron’s Energy Technology Company Unit in Houston, TX. In this position, she worked with the Rock Physics from Seismic team analyzing global assets in Chevron’s portfolio. Dr. Bedle is currently an assistant professor of applied geophysics at the University of Oklahoma’s School of Geosciences. She joined OU in 2018, after instructing at the University of Houston for two years. Dr. Bedle and her student research team at OU primarily work with seismic reflection data, using advanced techniques such as machine learning, attribute analysis, and rock physics to reveal additional structural, stratigraphic and tectonic insights of the subsurface.

    Jie Qi
    Research Geophysicist

    An Integrated Fault Detection Workflow

    Seismic fault detection is one of the top critical procedures in seismic interpretation. Identifying faults are significant for characterizing and finding the potential oil and gas reservoirs. Seismic amplitude data exhibiting good resolution and a high signal-to-noise ratio are key to identifying structural discontinuities using seismic attributes or machine learning techniques, which in turn serve as input for automatic fault extraction. Deep learning Convolutional Neural Networks (CNN) performs well on fault detection without any human-computer interactive work. This study shows an integrated CNN-based fault detection workflow to construct fault images that are sufficiently smooth for subsequent fault automatic extraction. The objectives were to suppress noise or stratigraphic anomalies subparallel to reflector dip, and sharpen fault and other discontinuities that cut reflectors, preconditioning the fault images for subsequent automatic extraction. A 2D continuous wavelet transform-based acquisition footprint suppression method was applied time slice by time slice to suppress wavenumber components to avoid interpreting the acquisition footprint as artifacts by the CNN fault detection method. To further suppress cross-cutting noise as well as sharpen fault edges, a principal component edge-preserving structure-oriented filter is also applied. The conditioned amplitude volume is then fed to a pre-trained CNN model to compute fault probability. Finally, a Laplacian of Gaussian filter is applied to the original CNN fault probability to enhance fault images. The resulting fault probability volume is favorable with respect to traditional human-interpreter generated on vertical slices through the seismic amplitude volume.

    Dr. Jie Qi
    Research Geophysicist

    An integrated machine learning-based fault classification workflow

    We introduce an integrated machine learning-based fault classification workflow that creates fault component classification volumes that greatly reduces the burden on the human interpreter. We first compute a 3D fault probability volume from pre-conditioned seismic amplitude data using a 3D convolutional neural network (CNN). However, the resulting “fault probability” volume delineates other non-fault edges such as angular unconformities, the base of mass transport complexes, and noise such as acquisition footprint. We find that image processing-based fault discontinuity enhancement and skeletonization methods can enhance the fault discontinuities and suppress many of the non-fault discontinuities. Although each fault is characterized by its dip and azimuth, these two properties are discontinuous at azimuths of φ=±180° and for near vertical faults for azimuths φ and φ+180° requiring them to be parameterized as four continuous geodetic fault components. These four fault components as well as the fault probability can then be fed into a self-organizing map (SOM) to generate fault component classification. We find that the final classification result can segment fault sets trending in interpreter-defined orientations and minimize the impact of stratigraphy and noise by selecting different neurons from the SOM 2D neuron color map.

    Ivan Marroquin
    Senior Research Geophysicist

    Connecting Multi-attribute Classification to Reservoir Properties

    Interpreters rely on seismic pattern changes to identify and map geologic features of importance. The ability to recognize such features depends on the seismic resolution and characteristics of seismic waveforms. With the advancement of machine learning algorithms, new methods for interpreting seismic data are being developed. Among these algorithms, self-organizing maps (SOM) provides a different approach to extract geological information from a set of seismic attributes.

    SOM approximates the input patterns by a finite set of processing neurons arranged in a regular 2D grid of map nodes. Such that, it classifies multi-attribute seismic samples into natural clusters following an unsupervised approach. Since machine learning is unbiased, so the classifications can contain both geological information and coherent noise. Thus, seismic interpretation evolves into broader geologic perspectives. Additionally, SOM partitions multi-attribute samples without a priori information to guide the process (e.g., well data).

    The SOM output is a new seismic attribute volume, in which geologic information is captured from the classification into winning neurons. Implicit and useful geological information are uncovered through an interactive visual inspection of winning neuron classifications. By doing so, interpreters build a classification model that aids them to gain insight into complex relationships between attribute patterns and geological features.

    Despite all these benefits, there are interpretation challenges regarding whether there is an association between winning neurons and geological features. To address these issues, a bivariate statistical approach is proposed. To evaluate this analysis, three cases scenarios are presented. In each case, the association between winning neurons and net reservoir (determined from petrophysical or well log properties) at well locations is analyzed. The results show that the statistical analysis not only aid in the identification of classification patterns; but more importantly, reservoir/not reservoir classification by classical petrophysical analysis strongly correlates with selected SOM winning neurons. Confidence in interpreted classification features is gained at the borehole and interpretation is readily extended as geobodies away from the well.

    Heather Bedle
    Assistant Professor, University of Oklahoma

    Gas Hydrates, Reefs, Channel Architecture, and Fizz Gas: SOM Applications in a Variety of Geologic Settings

    Students at the University of Oklahoma have been exploring the uses of SOM techniques for the last year. This presentation will review learnings and results from a few of these research projects. Two projects have investigated the ability of SOMs to aid in identification of pore space materials – both trying to qualitatively identify gas hydrates and under-saturated gas reservoirs. A third study investigated individual attributes and SOMs in recognizing various carbonate facies in a pinnacle reef in the Michigan Basin. The fourth study took a deep dive of various machine learning algorithms, of which SOMs will be discussed, to understand how much machine learning can aid in the identification of deepwater channel architectures.

    Fabian Rada
    Sr. Geophysicist, Petroleum Oil & Gas Servicest

    Fabian Rada joined Petroleum Oil and Gas Services, Inc (POGS) in January 2015 as Business Development Manager and Consultant to PEMEX. In Mexico, he has participated in several integrated oil and gas reservoir studies. He has consulted with PEMEX Activos and the G&G Technology group to apply the Paradise AI workbench and other tools. Since January 2015, he has been working with Geophysical Insights staff to provide and implement the multi-attribute analysis software Paradise in Petróleos Mexicanos (PEMEX), running a successful pilot test in Litoral Tabasco Tsimin Xux Asset. Mr. Rada began his career in the Venezuelan National Foundation for Seismological Research, where he participated in several geophysical projects, including seismic and gravity data for micro zonation surveys. He then joined China National Petroleum Corporation (CNPC) as QC Geophysicist until he became the Chief Geophysicist in the QA/QC Department. Then, he transitioned to a subsidiary of Petróleos de Venezuela (PDVSA), as a member of the QA/QC and Chief of Potential Field Methods section. Mr. Rada has also participated in processing land seismic data and marine seismic/gravity acquisition surveys. Mr. Rada earned a B.S. in Geophysics from the Central University of Venezuela.

    Hal GreenDirector, Marketing & Business Development - Geophysical Insights

    Introduction to Automatic Fault Detection and Applying Machine Learning to Detect Thin Beds

    Rapid advances in Machine Learning (ML) are transforming seismic analysis. Using these new tools, geoscientists can accomplish the following quickly and effectively: a combination of machine learning (ML) and deep learning applications, geoscientists apply Paradise to extract greater insights from seismic and well data for these and other objectives:

    • Run fault detection analysis in a few hours, not weeks
    • Identify thin beds down to a single seismic sample
    • Overlay fault images on stratigraphic analysis

    The brief introduction will orient you with the technology and examples of how machine learning is being applied to automate interpretation while generating new insights in the data.

    Sarah Stanley
    Senior Geoscientist and Lead Trainer

    Sarah Stanley joined Geophysical Insights in October, 2017 as a geoscience consultant, and became a full-time employee July 2018. Prior to Geophysical Insights, Sarah was employed by IHS Markit in various leadership positions from 2011 to her retirement in August 2017, including Director US Operations Training and Certification, the Operational Governance Team, and, prior to February 2013, Director of IHS Kingdom Training. Sarah joined SMT in May, 2002, and was the Director of Training for SMT until IHS Markit’s acquisition in 2011.

    Prior to joining SMT Sarah was employed by GeoQuest, a subdivision of Schlumberger, from 1998 to 2002. Sarah was also Director of the Geoscience Technology Training Center, North Harris College from 1995 to 1998, and served as a voluntary advisor on geoscience training centers to various geological societies. Sarah has over 37 years of industry experience and has worked as a petroleum geoscientist in various domestic and international plays since August of 1981. Her interpretation experience includes tight gas sands, coalbed methane, international exploration, and unconventional resources.

    Sarah holds a Bachelor’s of Science degree with majors in Biology and General Science and minor in Earth Science, a Master’s of Arts in Education and Master’s of Science in Geology from Ball State University, Muncie, Indiana. Sarah is both a Certified Petroleum Geologist, and a Registered Geologist with the State of Texas. Sarah holds teaching credentials in both Indiana and Texas.

    Sarah is a member of the Houston Geological Society and the American Association of Petroleum Geologists, where she currently serves in the AAPG House of Delegates. Sarah is a recipient of the AAPG Special Award, the AAPG House of Delegates Long Service Award, and the HGS President’s award for her work in advancing training for petroleum geoscientists. She has served on the AAPG Continuing Education Committee and was Chairman of the AAPG Technical Training Center Committee. Sarah has also served as Secretary of the HGS, and Served two years as Editor for the AAPG Division of Professional Affairs Correlator.

    Dr. Tom Smith
    President & CEO

    Dr. Tom Smith received a BS and MS degree in Geology from Iowa State University. His graduate research focused on a shallow refraction investigation of the Manson astrobleme. In 1971, he joined Chevron Geophysical as a processing geophysicist but resigned in 1980 to complete his doctoral studies in 3D modeling and migration at the Seismic Acoustics Lab at the University of Houston. Upon graduation with the Ph.D. in Geophysics in 1981, he started a geophysical consulting practice and taught seminars in seismic interpretation, seismic acquisition and seismic processing. Dr. Smith founded Seismic Micro-Technology in 1984 to develop PC software to support training workshops which subsequently led to development of the KINGDOM Software Suite for integrated geoscience interpretation with world-wide success.

    The Society of Exploration Geologists (SEG) recognized Dr. Smith’s work with the SEG Enterprise Award in 2000, and in 2010, the Geophysical Society of Houston (GSH) awarded him an Honorary Membership. Iowa State University (ISU) has recognized Dr. Smith throughout his career with the Distinguished Alumnus Lecturer Award in 1996, the Citation of Merit for National and International Recognition in 2002, and the highest alumni honor in 2015, the Distinguished Alumni Award. The University of Houston College of Natural Sciences and Mathematics recognized Dr. Smith with the 2017 Distinguished Alumni Award.

    In 2009, Dr. Smith founded Geophysical Insights, where he leads a team of geophysicists, geologists and computer scientists in developing advanced technologies for fundamental geophysical problems. The company launched the Paradise® multi-attribute analysis software in 2013, which uses Machine Learning and pattern recognition to extract greater information from seismic data.

    Dr. Smith has been a member of the SEG since 1967 and is a professional member of SEG, GSH, HGS, EAGE, SIPES, AAPG, Sigma XI, SSA and AGU. Dr. Smith served as Chairman of the SEG Foundation from 2010 to 2013. On January 25, 2016, he was recognized by the Houston Geological Society (HGS) as a geophysicist who has made significant contributions to the field of geology. He currently serves on the SEG President-Elect’s Strategy and Planning Committee and the ISU Foundation Campaign Committee for Forever True, For Iowa State.

    Carrie LaudonSenior Geophysical Consultant - Geophysical Insights

    Applying Machine Learning Technologies in the Niobrara Formation, DJ Basin, to Quickly Produce an Integrated Structural and Stratigraphic Seismic Classification Volume Calibrated to Wells

    This study will demonstrate an automated machine learning approach for fault detection in a 3D seismic volume. The result combines Deep Learning Convolution Neural Networks (CNN) with a conventional data pre-processing step and an image processing-based post processing approach to produce high quality fault attribute volumes of fault probability, fault dip magnitude and fault dip azimuth. These volumes are then combined with instantaneous attributes in an unsupervised machine learning classification, allowing the isolation of both structural and stratigraphic features into a single 3D volume. The workflow is illustrated on a 3D seismic volume from the Denver Julesburg Basin and a statistical analysis is used to calibrate results to well data.

    Ivan Marroquin
    Senior Research Geophysicist

    Iván Dimitri Marroquín is a 20-year veteran of data science research, consistently publishing in peer-reviewed journals and speaking at international conference meetings. Dr. Marroquín received a Ph.D. in geophysics from McGill University, where he conducted and participated in 3D seismic research projects. These projects focused on the development of interpretation techniques based on seismic attributes and seismic trace shape information to identify significant geological features or reservoir physical properties. Examples of his research work are attribute-based modeling to predict coalbed thickness and permeability zones, combining spectral analysis with coherency imagery technique to enhance interpretation of subtle geologic features, and implementing a visual-based data mining technique on clustering to match seismic trace shape variability to changes in reservoir properties.

    Dr. Marroquín has also conducted some ground-breaking research on seismic facies classification and volume visualization. This lead to his development of a visual-based framework that determines the optimal number of seismic facies to best reveal meaningful geologic trends in the seismic data. He proposed seismic facies classification as an alternative to data integration analysis to capture geologic information in the form of seismic facies groups. He has investigated the usefulness of mobile devices to locate, isolate, and understand the spatial relationships of important geologic features in a context-rich 3D environment. In this work, he demonstrated mobile devices are capable of performing seismic volume visualization, facilitating the interpretation of imaged geologic features.  He has definitively shown that mobile devices eventually will allow the visual examination of seismic data anywhere and at any time.

    In 2016, Dr. Marroquín joined Geophysical Insights as a senior researcher, where his efforts have been focused on developing machine learning solutions for the oil and gas industry. For his first project, he developed a novel procedure for lithofacies classification that combines a neural network with automated machine methods. In parallel, he implemented a machine learning pipeline to derive cluster centers from a trained neural network. The next step in the project is to correlate lithofacies classification to the outcome of seismic facies analysis.  Other research interests include the application of diverse machine learning technologies for analyzing and discerning trends and patterns in data related to oil and gas industry.

    Dr. Jie Qi
    Research Geophysicist

    Dr. Jie Qi is a Research Geophysicist at Geophysical Insights, where he works closely with product development and geoscience consultants. His research interests include machine learning-based fault detection, seismic interpretation, pattern recognition, image processing, seismic attribute development and interpretation, and seismic facies analysis. Dr. Qi received a BS (2011) in Geoscience from the China University of Petroleum in Beijing, and an MS (2013) in Geophysics from the University of Houston. He earned a Ph.D. (2017) in Geophysics from the University of Oklahoma, Norman. His industry experience includes work as a Research Assistant (2011-2013) at the University of Houston and the University of Oklahoma (2013-2017). Dr. Qi was with Petroleum Geo-Services (PGS), Inc. in 2014 as a summer intern, where he worked on a semi-supervised seismic facies analysis. In 2017, he served as a postdoctoral Research Associate in the Attributed Assisted-Seismic Processing and Interpretation (AASPI) consortium at the University of Oklahoma from 2017 to 2020.

    Rocky R. Roden
    Senior Consulting Geophysicist

    The Relationship of Self-Organization, Geology, and Machine Learning

    Self-organization is the nonlinear formation of spatial and temporal structures, patterns or functions in complex systems (Aschwanden et al., 2018). Simple examples of self-organization include flocks of birds, schools of fish, crystal development, formation of snowflakes, and fractals. What these examples have in common is the appearance of structure or patterns without centralized control. Self-organizing systems are typically governed by power laws, such as the Gutenberg-Richter law of earthquake frequency and magnitude. In addition, the time frames of such systems display a characteristic self-similar (fractal) response, where earthquakes or avalanches for example, occur over all possible time scales (Baas, 2002).

    The existence of nonlinear dynamic systems and ordered structures in the earth are well known and have been studied for centuries and can appear as sedimentary features, layered and folded structures, stratigraphic formations, diapirs, eolian dune systems, channelized fluvial and deltaic systems, and many more (Budd, et al., 2014; Dietrich and Jacob, 2018). Each of these geologic processes and features exhibit patterns through the action of undirected local dynamics and is generally termed “self-organization” (Paola, 2014).

    Artificial intelligence and specifically neural networks exhibit and reveal self-organization characteristics. The reason for the interest in applying neural networks stems from the fact that they are universal approximators for various kinds of nonlinear dynamical systems of arbitrary complexity (Pessa, 2008). A special class of artificial neural networks is aptly named self-organizing map (SOM) (Kohonen, 1982). It has been found that SOM can identify significant organizational structure in the form of clusters from seismic attributes that relate to geologic features (Strecker and Uden, 2002; Coleou et al., 2003; de Matos, 2006; Roy et al., 2013; Roden et al., 2015; Zhao et al., 2016; Roden et al., 2017; Zhao et al., 2017; Roden and Chen, 2017; Sacrey and Roden, 2018; Leal et al, 2019; Hussein et al., 2020; Hardage et al., 2020; Manauchehri et al., 2020). As a consequence, SOM is an excellent machine learning neural network approach utilizing seismic attributes to help identify self-organization features and define natural geologic patterns not easily seen or seen at all in the data.

    Rocky R. Roden
    Senior Consulting Geophysicist

    Rocky R. Roden started his own consulting company, Rocky Ridge Resources Inc. in 2003 and works with several oil companies on technical and prospect evaluation issues. He is also a principal in the Rose and Associates DHI Risk Analysis Consortium and was Chief Consulting Geophysicist with Seismic Micro-technology. Rocky is a proven oil finder with 37 years in the industry, gaining extensive knowledge of modern geoscience technical approaches.

    Rocky holds a BS in Oceanographic Technology-Geology from Lamar University and a MS in Geological and Geophysical Oceanography from Texas A&M University. As Chief Geophysicist and Director of Applied Technology for Repsol-YPF, his role comprised of advising corporate officers, geoscientists, and managers on interpretation, strategy and technical analysis for exploration and development in offices in the U.S., Argentina, Spain, Egypt, Bolivia, Ecuador, Peru, Brazil, Venezuela, Malaysia, and Indonesia. He has been involved in the technical and economic evaluation of Gulf of Mexico lease sales, farmouts worldwide, and bid rounds in South America, Europe, and the Far East. Previous work experience includes exploration and development at Maxus Energy, Pogo Producing, Decca Survey, and Texaco. Rocky is a member of SEG, AAPG, HGS, GSH, EAGE, and SIPES; he is also a past Chairman of The Leading Edge Editorial Board.

    Bob A. Hardage

    Bob A. Hardage received a PhD in physics from Oklahoma State University. His thesis work focused on high-velocity micro-meteoroid impact on space vehicles, which required trips to Goddard Space Flight Center to do finite-difference modeling on dedicated computers. Upon completing his university studies, he worked at Phillips Petroleum Company for 23 years and was Exploration Manager for Asia and Latin America when he left Phillips. He moved to WesternAtlas and worked 3 years as Vice President of Geophysical Development and Marketing. He then established a multicomponent seismic research laboratory at the Bureau of Economic Geology and served The University of Texas at Austin as a Senior Research Scientist for 28 years. He has published books on VSP, cross-well profiling, seismic stratigraphy, and multicomponent seismic technology. He was the first person to serve 6 years on the Board of Directors of the Society of Exploration Geophysicists (SEG). His Board service was as SEG Editor (2 years), followed by 1-year terms as First VP, President Elect, President, and Past President. SEG has awarded him a Special Commendation, Life Membership, and Honorary Membership. He wrote the AAPG Explorer column on geophysics for 6 years. AAPG honored him with a Distinguished Service award for promoting geophysics among the geological community.

    Bob A. Hardage

    Investigating the Internal Fabric of VSP data with Attribute Analysis and Unsupervised Machine Learning

    Examination of vertical seismic profile (VSP) data with unsupervised machine learning technology is a rigorous way to compare the fabric of down-going, illuminating, P and S wavefields with the fabric of up-going reflections and interbed multiples created by these wavefields. This concept is introduced in this paper by applying unsupervised learning to VSP data to better understand the physics of P and S reflection seismology. The zero-offset VSP data used in this investigation were acquired in a hard-rock, fast-velocity, environment that caused the shallowest 2 or 3 geophones to be inside the near-field radiation zone of a vertical-vibrator baseplate. This study shows how to use instantaneous attributes to backtrack down-going direct-P and direct-S illuminating wavelets to the vibrator baseplate inside the near-field zone. This backtracking confirms that the points-of-origin of direct-P and direct-S are identical. The investigation then applies principal component (PCA) analysis to VSP data and shows that direct-S and direct-P wavefields that are created simultaneously at a vertical-vibrator baseplate have the same dominant principal components. A self-organizing map (SOM) approach is then taken to illustrate how unsupervised machine learning describes the fabric of down-going and up-going events embedded in vertical-geophone VSP data. These SOM results show that a small number of specific neurons build the down-going direct-P illuminating wavefield, and another small group of neurons build up-going P primary reflections and early-arriving down-going P multiples. The internal attribute fabric of these key down-going and up-going neurons are then compared to expose their similarities and differences. This initial study indicates that unsupervised machine learning, when applied to VSP data, is a powerful tool for understanding the physics of seismic reflectivity at a prospect. This research strategy of analyzing VSP data with unsupervised machine learning will now expand to horizontal-geophone VSP data.

    Tom Smith
    President and CEO, Geophysical Insights

    Machine Learning for Incomplete Geoscientists

    This presentation covers big-picture machine learning buzz words with humor and unassailable frankness. The goal of the material is for every geoscientist to gain confidence in these important concepts and how they add to our well-established practices, particularly seismic interpretation. Presentation topics include a machine learning historical perspective, what makes it different, a fish factory, Shazam, comparison of supervised and unsupervised machine learning methods with examples, tuning thickness, deep learning, hard/soft attribute spaces, multi-attribute samples, and several interpretation examples. After the presentation, you may not know how to run machine learning algorithms, but you should be able to appreciate their value and avoid some of their limitations.

    Deborah Sacrey
    Owner, Auburn Energy

    Deborah is a geologist/geophysicist with 44 years of oil and gas exploration experience in Texas, Louisiana Gulf Coast and Mid-Continent areas of the US. She received her degree in Geology from the University of Oklahoma in 1976 and immediately started working for Gulf Oil in their Oklahoma City offices.

    She started her own company, Auburn Energy, in 1990 and built her first geophysical workstation using Kingdom software in 1996. She helped SMT/IHS for 18 years in developing and testing the Kingdom Software. She specializes in 2D and 3D interpretation for clients in the US and internationally. For the past nine years she has been part of a team to study and bring the power of multi-attribute neural analysis of seismic data to the geoscience public, guided by Dr. Tom Smith, founder of SMT. She has become an expert in the use of Paradise software and has seven discoveries for clients using multi-attribute neural analysis.

    Deborah has been very active in the geological community. She is past national President of SIPES (Society of Independent Professional Earth Scientists), past President of the Division of Professional Affairs of AAPG (American Association of Petroleum Geologists), Past Treasurer of AAPG and Past President of the Houston Geological Society. She is also Past President of the Gulf Coast Association of Geological Societies and just ended a term as one of the GCAGS representatives on the AAPG Advisory Council. Deborah is also a DPA Certified Petroleum Geologist #4014 and DPA Certified Petroleum Geophysicist #2. She belongs to AAPG, SIPES, Houston Geological Society, South Texas Geological Society and the Oklahoma City Geological Society (OCGS).

    Mike Dunn
    Senior Vice President Business Development

    Michael A. Dunn is an exploration executive with extensive global experience including the Gulf of Mexico, Central America, Australia, China and North Africa. Mr. Dunn has a proven a track record of successfully executing exploration strategies built on a foundation of new and innovative technologies. Currently, Michael serves as Senior Vice President of Business Development for Geophysical Insights.

    He joined Shell in 1979 as an exploration geophysicist and party chief and held increasing levels or responsibility including Manager of Interpretation Research. In 1997, he participated in the launch of Geokinetics, which completed an IPO on the AMEX in 2007. His extensive experience with oil companies (Shell and Woodside) and the service sector (Geokinetics and Halliburton) has provided him with a unique perspective on technology and applications in oil and gas. Michael received a B.S. in Geology from Rutgers University and an M.S. in Geophysics from the University of Chicago.

    Hal GreenDirector, Marketing & Business Development - Geophysical Insights

    Hal H. Green is a marketing executive and entrepreneur in the energy industry with more than 25 years of experience in starting and managing technology companies. He holds a B.S. in Electrical Engineering from Texas A&M University and an MBA from the University of Houston. He has invested his career at the intersection of marketing and technology, with a focus on business strategy, marketing, and effective selling practices. Mr. Green has a diverse portfolio of experience in marketing technology to the hydrocarbon supply chain – from upstream exploration through downstream refining & petrochemical. Throughout his career, Mr. Green has been a proven thought-leader and entrepreneur, while supporting several tech start-ups.

    He started his career as a process engineer in the semiconductor manufacturing industry in Dallas, Texas and later launched an engineering consulting and systems integration business. Following the sale of that business in the late 80’s, he joined Setpoint in Houston, Texas where he eventually led that company’s Manufacturing Systems business. Aspen Technology acquired Setpoint in January 1996 and Mr. Green continued as Director of Business Development for the Information Management and Polymer Business Units.

    In 2004, Mr. Green founded Advertas, a full-service marketing and public relations firm serving clients in energy and technology. In 2010, Geophysical Insights retained Advertas as their marketing firm. Dr. Tom Smith, President/CEO of Geophysical Insights, soon appointed Mr. Green as Director of Marketing and Business Development for Geophysical Insights, in which capacity he still serves today.

    Hana Kabazi
    Product Manager

    Hana Kabazi joined Geophysical Insights in October of 201, and is now one of our Product Managers for Paradise. Mrs. Kabazi has over 7 years of oil and gas experience, including 5 years and Halliburton – Landmark. During her time at Landmark she held positions as a consultant to many E&P companies, technical advisor to the QA organization, and as product manager of Subsurface Mapping in DecsionSpace. Mrs. Kabazi has a B.S. in Geology from the University of Texas Austin, and an M.S. in Geology from the University of Houston.

    Dr. Carrie LaudonSenior Geophysical Consultant - Geophysical Insights

    Carolan (Carrie) Laudon holds a PhD in geophysics from the University of Minnesota and a BS in geology from the University of Wisconsin Eau Claire. She has been Senior Geophysical Consultant with Geophysical Insights since 2017 working with Paradise®, their machine learning platform. Prior roles include Vice President of Consulting Services and Microseismic Technology for Global Geophysical Services and 17 years with Schlumberger in technical, management and sales, starting in Alaska and including Aberdeen, Scotland, Houston, TX, Denver, CO and Reading, England. She spent five years early in her career with ARCO Alaska as a seismic interpreter for the Central North Slope exploration team.