Support-vector-machine with Bayesian optimization for lithofacies classification using elastic properties

TL;DR

This paper demonstrates that Bayesian optimization can effectively tune SVM hyperparameters for classifying lithofacies using elastic properties, reducing human bias and improving classification accuracy in geological data analysis.

Contribution

The study introduces a workflow combining Bayesian optimization with SVM for lithofacies classification, enhancing hyperparameter tuning and reducing subjectivity in geological data analysis.

Findings

Successful classification of facies with non-linear boundaries

Bayesian optimization reduces human bias in SVM hyperparameter selection

Potential benefits for resource exploration and subsurface evaluation

Abstract

We investigate an applicability of Bayesian-optimization (BO) to optimize hyperparameters associated with support-vector-machine (SVM) in order to classify facies using elastic properties derived from well data in the East Central Graben, UKCS. The cross-plot products of the field dataset appear to be successfully classified with non-linear boundaries. Although there are a few factors to be predetermined in the BO scheme such as an iteration number to deal with a trade-off between the prediction accuracy and the computational cost, this approach effectively reduces possible human subjectivity connected to the architecture of the SVM. Our proposed workflow might be beneficial in resource-exploration and development in terms of subsurface objective technical evaluations.