Explainable Probabilistic Machine Learning for Predicting Drilling Fluid Loss of Circulation in Marun Oil Field

TL;DR

This paper introduces an explainable probabilistic machine learning approach using Gaussian Process Regression to accurately predict drilling fluid loss, enhancing safety and decision-making in complex oil field operations.

Contribution

The study develops a novel GPR-based framework with interpretability tools for predicting fluid loss and managing uncertainties in drilling operations.

Findings

GPR effectively models nonlinear dependencies in drilling data.

LIME provides clear explanations of feature influences.

The approach improves risk prediction and operational decision-making.

Abstract

Lost circulation remains a major and costly challenge in drilling operations, often resulting in wellbore instability, stuck pipe, and extended non-productive time. Accurate prediction of fluid loss is therefore essential for improving drilling safety and efficiency. This study presents a probabilistic machine learning framework based on Gaussian Process Regression (GPR) for predicting drilling fluid loss in complex formations. The GPR model captures nonlinear dependencies among drilling parameters while quantifying predictive uncertainty, offering enhanced reliability for high-risk decision-making. Model hyperparameters are optimized using the Limited memory Broyden Fletcher Goldfarb Shanno (LBFGS) algorithm to ensure numerical stability and robust generalization. To improve interpretability, Local Interpretable Model agnostic Explanations (LIME) are employed to elucidate how individual features influence model predictions. The results highlight the potential of explainable probabilistic learning for proactive identification of lost-circulation risks, optimized design of lost circulation materials (LCM), and reduction of operational uncertainties in drilling applications.