TY - JOUR
T1 - Elastic impedance based facies classification using support vector machine and deep learning
AU - Nishitsuji, Yohei
AU - Exley, Russell
PY - 2018/8/27
Y1 - 2018/8/27
N2 - Machine learning methods including support-vector-machine and deep learning are applied to facies classification problems using elastic impedances acquired from a Paleocene oil discovery in the UK Central North Sea. Both of the supervised learning approaches showed similar accuracy when predicting facies after the optimization of hyperparameters derived from well data. However, the results obtained by deep learning provided better correlation with available wells and more precise decision boundaries in cross-plot space when compared to the support-vector-machine approach. Results from the support-vector-machine and deep learning classifications are compared against a simplified linear projection based classification and a Bayes-based approach. Differences between the various facies classification methods are connected by not only their methodological differences but also human interactions connected to the selection of machine learning parameters. Despite the observed differences, machine learning applications, such as deep learning, have the potential to become standardized in the industry for the interpretation of amplitude versus offset cross-plot problems, thus providing an automated facies classification approach.
AB - Machine learning methods including support-vector-machine and deep learning are applied to facies classification problems using elastic impedances acquired from a Paleocene oil discovery in the UK Central North Sea. Both of the supervised learning approaches showed similar accuracy when predicting facies after the optimization of hyperparameters derived from well data. However, the results obtained by deep learning provided better correlation with available wells and more precise decision boundaries in cross-plot space when compared to the support-vector-machine approach. Results from the support-vector-machine and deep learning classifications are compared against a simplified linear projection based classification and a Bayes-based approach. Differences between the various facies classification methods are connected by not only their methodological differences but also human interactions connected to the selection of machine learning parameters. Despite the observed differences, machine learning applications, such as deep learning, have the potential to become standardized in the industry for the interpretation of amplitude versus offset cross-plot problems, thus providing an automated facies classification approach.
KW - Elastics
KW - Interpretation
KW - Inversion
KW - Reservoir geophysics
KW - Rock physics
UR - http://www.scopus.com/inward/record.url?scp=85053328519&partnerID=8YFLogxK
UR - http://resolver.tudelft.nl/uuid:9be25d41-8234-47c6-bc21-82309e344255
U2 - 10.1111/1365-2478.12682
DO - 10.1111/1365-2478.12682
M3 - Article
AN - SCOPUS:85053328519
SN - 0016-8025
VL - 67 (2019)
SP - 1040
EP - 1054
JO - Geophysical Prospecting
JF - Geophysical Prospecting
IS - 4
ER -