Advances in physics-constrained and data-driven dual paradigm for artificial intelligence in oil and gas
Abstract
Integrating physical mechanisms with data-driven methods overcomes the limitations of purely data-driven artificial intelligence and purely mechanism-based models. Purely data-driven approaches suffer from poor interpretability and weak generalization under sparse data, while purely physics-based models are computationally expensive and struggle with complex nonlinearities. This work highlights advances in the physics-constrained, data-driven dual paradigm across petroleum engineering: mechanism–artificial intelligence fusion via Bayesian networks provides traceable hydrocarbon spatial distribution predictions; knowledge–data-driven modelling ensures geological realism; and collaborative physics–data fault diagnosis enhances well monitoring under noise. These advances demonstrate that deep fusion of domain knowledge, physical laws, and multi-source data is essential for creating interpretable, reliable, and efficient intelligent systems for complex subsurface resource development.
Document Type: Perspective
Cited as: Hui, G., Wang, M., Cheng, H. Advances in physics-constrained and data-driven dual paradigm for artificial intelligence in oil and gas. Advances in Geo-Energy Research, 2026, 20(3): 201-204. https://doi.org/10.46690/ager.2026.06.01
DOI:
https://doi.org/10.46690/ager.2026.06.01Keywords:
Physics-constrained, data-driven, knowledge-based, geological, modellingReferences
Bao, P., Hui, G., Hu, Y., et al. Comprehensive characterization of hydraulic fracture propagations and prevention of pre-existing fault failure in Duvernay shale reservoirs. Engineering Failure Analysis, 2025, 173: 109461.
Bhavsar, F., Desassis, N., Ors, F., et al. A stable deep adversarial learning approach for geological facies generation. Computers & Geosciences, 2024, 190: 105638.
Cao, L., Jiang, F., Chen, Z., et al. Data-driven interpretable machine learning for prediction of porosity and permeability of tight sandstone reservoir. Advances in GeoEnergy Research, 2025, 16(1): 21-35.
Fan, X., Zhao, F., Yu, J., et al. DWOA-BNC: Discrete whale optimization algorithm for Bayesian network classifier learning and its application. Pattern Recognition, 2026, 173: 112661.
He, Y., Cheng, H., Zeng, P., et al. Working condition recognition of sucker rod pumping system based on 4-segment time-frequency signature matrix and deep learning. Petroleum Science, 2024, 21(1): 641-653.
Hui, G., Chen, S., He, Y., et al. Machine learning-based production forecast for shale gas in unconventional reservoirs via integration of geological and operational factors. Journal of Natural Gas Science and Engineering, 2021, 94: 104045.
Hussain, A., Pan, P. Z., Hussain, J., et al. Data-driven machine learning models for predicting deliverability of underground natural gas storage in aquifer and depleted reservoirs. Energy, 2025, 319: 134974.
Karagiorgi, G., Kasieczka, G., Kravitz, S., et al. Machine learning in the search for new fundamental physics. Nature Reviews Physics, 2022, 4(6): 399-412.
Nagao, M., Datta-Gupta, A., Onishi, T., et al. Physics informed machine learning for reservoir connectivity identification and robust production forecasting. SPE Journal, 2024, 29(9): 4527–4541.
Ren, H., Fan, X., Liang, K., et al. Prediction method for the spatial distribution of oil and gas resources based on a Bayesian network classifier: A case study of the Shahejie formation in southeastern Jizhong Depression, Bohai Bay Basin, China. Mathematical Geosciences, 2026, 58(2): 381-402.
Sinha, U., Dindoruk, B. Review of physics-informed machine learning (PIML) methods applications in subsurface engineering. Geoenergy Science and Engineering, 2025, 250: 213713.
Wang, M., Wang, H., Hui, G., et al. A hybrid tabular spatial-temporal model with 3D Geomodel for production prediction in shale gas formations. SPE Journal, 2025, 30(6): 3281-3293.
Zhuang, X., Liu, Y., Hu, Y., et al. Prediction of rock fracture pressure in hydraulic fracturing with interpretable machine learning and mechanical specific energy theory. Rock Mechanics Bulletin, 2025, 4(2): 100173.
Downloads
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Gang Hui, Muming Wang, Haibo Cheng
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.