Physics-Informed Neural Networks for Coupled Non-Isothermal Two-Phase Flow in Porous Media: Training Pathologies, Remedies, and the Role of Gradient Conflict
Open Access
- 1 September 2026
- journal article
- research article
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 8 (9) , 266
Abstract
Physics-informed neural networks (PINNs) are difficult to train on strongly coupled, multi-objective systems: with fixed loss weights an otherwise identical run succeeds or diverges with the random seed, and a leading explanation attributes the failures to conflict between the loss-term gradients. We test that explanation on a coupled non-isothermal Buckley–Leverett displacement with a passive tracer, a three-front hot-water flood with an exact analytical solution as ground truth. The test produces an exactly verified counterexample: the conflict-free update ConFIG attains its alignment objective yet converges to a stable solution that violates the equations, while a quasi-second-order optimizer (SOAP) and per-term gradient surgery (PCGrad) train the network reliably with no loss-weight search. The most aligned update is thus the one that fails: gradient alignment is neither necessary nor sufficient for trainability, and the conflict is a diagnostic of the loss rather than its cause. The same formulation serves the forward, parametric, and inverse problems: it predicts the movable-oil recovery with a relative error of about 5%, returns the solution for any oil viscosity in a trained range from one network, and, from sparse near-injector monitoring, recovers the thermal front speed and one transport coefficient when the other is known. To our knowledge this is the first PINN solution of this coupled displacement, which is central to thermal oil recovery.Keywords
Funding Information
- Committee of Science of the Ministry of Science and Higher Education of the Republic of Kazakhstan (AP22688606)
This publication has 63 references indexed in Scilit:
- Physics-informed neural networks for PDE problems: a comprehensive reviewArtificial Intelligence Review, 2025
- From PINNs to PIKANs: recent advances in physics-informed machine learningMachine Learning for Computational Science and Engineering, 2025
- A comprehensive study of non-adaptive and residual-based adaptive sampling for physics-informed neural networksComputer Methods in Applied Mechanics and Engineering, 2022
- A review of tracer testing techniques in porous media specially attributed to the oil and gas industryJournal of Petroleum Exploration and Production Technology, 2022
- Physics-informed neural network simulation of multiphase poroelasticity using stress-split sequential trainingComputer Methods in Applied Mechanics and Engineering, 2022
- Residual-based adaptivity for two-phase flow simulation in porous media using Physics-informed Neural NetworksComputer Methods in Applied Mechanics and Engineering, 2022
- Physics-informed neural networks (PINNs) for fluid mechanics: a reviewActa Mechanica Sinica, 2021
- Conservative physics-informed neural networks on discrete domains for conservation laws: Applications to forward and inverse problemsComputer Methods in Applied Mechanics and Engineering, 2020
- Modeling Phenomena of Flow and Transport in Porous Media2018
- On the limited memory BFGS method for large scale optimizationMathematical Programming, 1989