What question did this study set out to answer?

The aim is to develop a machine learning framework to predict the minimum horizontal stress using geomechanical parameters.

May 20, 2026Open Access

Prediction of Minimum Horizontal Stress Using Machine Learning for Unconventional Reservoir Applications

Key Points

The aim is to develop a machine learning framework to predict the minimum horizontal stress using geomechanical parameters.
Utilized a dataset of 21,499 records from 200 horizontal wells in the Marcellus Shale.
Employed ensemble models including random forest, gradient boosting, and artificial neural network.
Evaluated model performance using RMSE, MAE, and coefficient of determination.
Random forest model achieved RMSE of 6.5846 and R2 of 0.9988, indicating excellent baseline performance.
Gradient boosting model improved after tuning with RMSE approximately 6.59.
The stacking regressor model delivered an RMSE of 7.4963, while the ANN had an RMSE of 55.5008, showing limited performance.

Abstract

This study presents a leakage‐aware machine learning framework for predicting minimum horizontal stress ( σ h min) using structured geomechanical and fracture‐related parameters. A dataset comprising 21,499 records from approximately 200 horizontal wells in the Marcellus Shale was preprocessed using a strictly leakage‐controlled pipeline, including feature refinement, outlier capping, and training‐fold–based transformations. Three ensemble models—random forest (RF), gradient boosting regressor (GBR), and extreme gradient boosting (XGBoost)—along with a stacking regressor and artificial neural network (ANN), were evaluated using root mean squared error (RMSE), mean absolute error (MAE), and coefficient of determination ( R 2 ). The RF model achieved the best baseline performance (RMSE = 6.5846, R 2 = 0.9988), while gradient boosting showed improved performance after tuning (RMSE ≈ 6.59). The stacking model delivered competitive results (RMSE = 7.4963), whereas the ANN showed lower performance (RMSE = 55.5008), indicating limited suitability for structured tabular data. A scenario‐based evaluation using Nigerian reservoir data demonstrated reasonable pr3332edictive consistency but was not treated as external validation due to data limitations. The results confirm that leakage‐aware ensemble learning provides a robust and physically consistent approach for predicting minimum horizontal stress, with potential application in reservoir characterization and hydraulic fracturing design.

Read Full Paperexternally

اسأل الذكاء الاصطناعي

Bookmark

View Full Paper