Enhancing lithological interpretation from petrophysical well log of IODP expedition 390/393 using machine learning

TL;DR

This study applies various machine learning algorithms to well log data from IODP expeditions 390 and 393, significantly improving lithological interpretation accuracy over traditional methods.

Contribution

It introduces a joint supervised and unsupervised machine learning approach for enhanced lithological classification from multivariate well logs.

Findings

Decision Tree and Gradient Boosting achieved near-perfect accuracy (~99.5%).

Supervised ML improved lithology classification compared to traditional methods.

Unsupervised ML provided foundational clustering support for classification.

Abstract

Enhanced lithological interpretation from well logs plays a key role in geological resource exploration and mapping, as well as in geo-environmental modeling studies. Core and cutting information is useful for making sound interpretations of well logs; however, these are rarely collected at each depth due to high costs. Moreover, well log interpretation using traditional methods is constrained by poor borehole conditions. Traditional statistical methods are mostly linear, often failing to discriminate between lithology and rock facies, particularly when dealing with overlapping well log signals characterized by the structural and compositional variation of rock types. In this study, we develop multiple supervised and unsupervised machine learning algorithms to jointly analyze multivariate well log data from Integrated Ocean Drilling Program (IODP) expeditions 390 and 393 for enhanced lithological interpretations. Among the algorithms, Logistic Regression, Decision Trees, Gradient Boosting, Support Vector Machines (SVM), k-Nearest Neighbors (KNN), and Multi-Layer Perceptron (MLP) neural network models, the Decision Tree and Gradient Boosting models outperformed the others, achieving an accuracy of 0.9950 and an F1-score of 0.9951. While unsupervised machine learning (ML) provides the foundation for cluster information that inherently supports the classification algorithm, supervised ML is applied to devise a data-driven lithology clustering mechanism for IODP datasets. The joint ML-based method developed here has the potential to be further explored for analyzing other well log datasets from the world's oceans.