Dr. Kurt Marfurt of the AASPI Consortium at The University of Oklahoma presents an example of how interpreters are using machine learning to enhance understanding of the seismic response.
Tags
3-D analysis
Amplitude
AOGR
Austin Chalk
automated seismic interpretation
Average Energy
AVO
below tuning
big data
blog
CNN
convolutional neural networks
deep learning
DHIs
Direct Hydrocarbon Indicators
EAGE
Eagle Ford
Envelope
fault detection
Geophysical Insights
Geophysical Society of Houston
machine learning
multi-attribute analysis
multiattribute
neural networks
PCA
principal component analysis
seismic attributes
Seismic Data
seismic facies classification
seismic interpretation
Self-Organizing Map
Self Organizing Maps
SOM
SOM analysis
spectral decomp
spectral decomposition
sub-seismic
supervised neural networks
thin beds
tight carbonate reservoirs
unsupervised neural networks
Webinar
well calibration
workflow