Advancing Multiphase Reservoir Simulation
Physics-Guided Expansion from Two-Phase to Three-Phase Datasets
Abstract
Physics-Guided Data Augmentation (PGDA) refers to a data augmentation approach that integrates physical laws, constraints, or properties of a system to generate new training samples in a machine learning model. In [3] PGDA was combined with unsupervised learning and improves the accuracy and stability of a bit wear machine learning model in drilling applications. In [2], a PGDA method is introduced to enhance the accuracy and generalization of neural operator models, leveraging the physical properties of differential equations. Here, we introduce a physics-guided gas estimator to expand our two-phase dataset to a three-phase dataset. [...]
Downloads
References
E. J. R. Coutinho, M. Dall’Aqua, and E. Gildin. “Physics-Aware Deep-Learning-Based Proxy Reservoir Simulation Model Equipped With State and Well Output Prediction”. In: Frontiers in Applied Mathematics and Statistics 7 (2021). issn: 2297-4687. doi: 10.3389/fams. 2021.651178.
Y. Li, Y. Pang, and B. Shan. “Physics-guided Data Augmentation for Learning the Solution Operator of Linear Differential Equations”. In: vol. 2022 IEEE 8th International Conference on Cloud Computing and Intelligent Systems (CCIS). 2022, pp. 543–547. doi: 10 . 1109 / CCIS57298.2022.10016380.
H. Xu, T. P. Luu, G. D. Zhan, Y. S. Qiu, A. S. Aljohar, T. Furlong, and J. Bomidi. “Physics-Guided Data Augmentation Combined with Unsupervised Learning Improves Stability and Accuracy of Bit Wear Deep Learning Model”. In: IADC/SPE International Drilling Conference and Exhibition. 2024, D021S014R004. doi: 10.2118/217954-MS.
