Prediction of rock unconfined compressive strength for subsurface formation CO2 storage using physics augmented machine learning: A comparative performance evaluation
Iraqi Journal of Chemical and Petroleum Engineering · 30.06.2026 · 27 (2) · 45-58
DOI: 10.31699/ijcpe.2026.2.4 ↗Kurz gefasst
Fachartikel in der Zeitschrift Iraqi Journal of Chemical and Petroleum Engineering, online erschienen am 30.06.2026. Verfasst von Fatimah F. Mutashar und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The paper introduces a state-of-the-art Physics Augmented Machine Learning framework to predict the critical geomechanical property – Unconfined Compressive Strength (UCS) – in the Zubair reservoir of the Zubair field for mitigating the risk of CO2 storage. The geomechanical results and modeling workflow were obtained via an integrated software system that was developed in Python, while all computational processes and model training were conducted in the Deepnote interactive cloud computing environment; thus, all of the necessary libraries and the high-performance processing capacities were seamlessly integrated. Through the comparison of six ensemble algorithms which are Categorical Boosting (CatBoost), XGBoost )Extreme Gradient Boosting(, RF(Random Forest Regressor), ExtraTrees (Extremely Randomized Trees), GBM (Gradient Boosting Machine), and Deep ANN (Deep Artificial Neural Networks), the research determined the most dependable models, while the Gradient Boosting model stood out by achieving UCS prediction with the best metrics of (R2=0.9995, MAE=3.64). The models are not only providing a precise and reliable but also a scalable assessment tool for subsurface stability, containment integrity, and real-time reservoir monitoring.
Zitieren
APA
Mutashar, F. F., & Hussein, H. A. A. (2026). Prediction of rock unconfined compressive strength for subsurface formation CO2 storage using physics augmented machine learning: A comparative performance evaluation. Iraqi Journal of Chemical and Petroleum Engineering, 27(2), 45-58. https://doi.org/10.31699/ijcpe.2026.2.4
Vancouver
Mutashar FF, Hussein HAA. Prediction of rock unconfined compressive strength for subsurface formation CO2 storage using physics augmented machine learning: A comparative performance evaluation. Iraqi Journal of Chemical and Petroleum Engineering. 2026;27(2):45-58. doi:10.31699/ijcpe.2026.2.4
BibTeX
@article{Mutashar2026,
author = {Mutashar, Fatimah F. and Hussein, Hassan A. Abdul},
title = {Prediction of rock unconfined compressive strength for subsurface formation CO2 storage using physics augmented machine learning: A comparative performance evaluation},
journal = {Iraqi Journal of Chemical and Petroleum Engineering},
year = {2026},
volume = {27},
number = {2},
pages = {45--58},
doi = {10.31699/ijcpe.2026.2.4}
}
EUVIMED