Physics-Informed Neural Networks for Methane Sorption: Cross-Gas Transfer Learning, Ensemble Collapse Under Physics Constraints, and Monte Carlo Dropout Uncertainty Quantification

• URL: http://arxiv.org/abs/2604.13992v1
• Date: Wed, 15 Apr 2026 15:35:44 GMT
• Title: Physics-Informed Neural Networks for Methane Sorption: Cross-Gas Transfer Learning, Ensemble Collapse Under Physics Constraints, and Monte Carlo Dropout Uncertainty Quantification
• Abstract summary: We present a physics-informed transfer learning framework that adapts a hydrogen sorption PINN to methane sorption prediction.<n>The framework achieves R2 = 0.932 on held-out coal samples, a 227% improvement over pressure-only classical isotherms.
• Score: 2.3808295372660253
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Accurate methane sorption prediction across heterogeneous coal ranks requires models that combine thermodynamic consistency, efficient knowledge transfer across data-scarce geological systems, and calibrated uncertainty estimates, capabilities that are rarely addressed together in existing frameworks. We present a physics-informed transfer learning framework that adapts a hydrogen sorption PINN to methane sorption prediction via Elastic Weight Consolidation, coal-specific feature engineering, and a three-phase curriculum that progressively balances transfer preservation with thermodynamic fine-tuning. Trained on 993 equilibrium measurements from 114 independent coal experiments spanning lignite to anthracite, the framework achieves R2 = 0.932 on held-out coal samples, a 227% improvement over pressure-only classical isotherms, while hydrogen pre-training delivers 18.9% lower RMSE and 19.4% faster convergence than random initialization. Five Bayesian uncertainty quantification approaches reveal a systematic divergence in performance across physics-constrained architectures. Monte Carlo Dropout achieves well-calibrated uncertainty at minimal overhead, while deep ensembles, regardless of architectural diversity or initialization strategy, exhibit performance degradation because shared physics constraints narrow the admissible solution manifold. SHAP and ALE analyses confirm that learned representations remain physically interpretable and aligned with established coal sorption mechanisms: moisture-volatile interactions are most influential, pressure-temperature coupling captures thermodynamic co-dependence, and features exhibit non-monotonic effects. These results identify Monte Carlo Dropout as the best-performing UQ method in this physics-constrained transfer learning framework, and demonstrate cross-gas transfer learning as a data-efficient strategy for geological material modeling.

Related papers

• ATLAS: A Foundation Neural Sampler for Amorphous Materials [38.39923274691799]
  ATLAS is an efficient sampler that learns a diffusion process to generate Boltzmann-distributed amorphous structures.<n>In two-dimensionalersen systems, ATLAS reproduces parallel tempering Markov chain Monte Carlo structural distributions.<n>In Cu-Zr and Cr-Co-Ni metallic glasses, ATLAS recovers experimentally observed short-range-order trends and steers structures toward prescribed order parameters.
  arXiv  Detail & Related papers  (2026-07-21T15:31:49Z)
• Entropy-Constrained Machine Learning with Residual Data Augmentation for Modeling Chemical Kinetics [0.0]
  The model replaces the direct evaluation of detailed chemical source terms with a surrogate that predicts reaction rates from a reduced thermochemical state.<n>To improve physical consistency, the second law of thermodynamics is incorporated as a training constraint.<n>The model reproduces detailed-chemistry results with high fidelity while achieving more than an order-of-magnitude reduction in computational cost.
  arXiv  Detail & Related papers  (2026-07-10T16:31:40Z)
• Physics-informed reservoir characterization from bulk and extreme pressure events with a differentiable simulator [42.95123707634075]
  We introduce a physics-informed machine learning method that embeds a differentiable subsurface flow simulator directly into neural network training.<n>The network infers heterogeneous permeability fields from limited pressure observations, while training minimizes both permeability and pressure losses through the simulator, enforcing physical consistency.<n>Overall, the proposed method enables rapid, physics-consistent subsurface inversion for real-time reservoir characterization and risk-aware decision-making.
  arXiv  Detail & Related papers  (2026-04-14T20:52:45Z)
• Physics-Informed Neural Networks for Predicting Hydrogen Sorption in Geological Formations: Thermodynamically Constrained Deep Learning Integrating Classical Adsorption Theory [1.5749416770494706]
  prediction of hydrogen sorption in fine-grained geological materials is essential for evaluating underground hydrogen storage capacity, assessing caprock integrity, and characterizing hydrogen migration in subsurface energy systems.<n>We present a multi-scale physics-informed neural network framework that addresses this limitation by embedding classical adsorbation theory and thermodynamic constraints directly into the learning process.
  arXiv  Detail & Related papers  (2026-03-30T11:59:36Z)
• A Machine Learning-Enhanced Hopf-Cole Formulation for Nonlinear Gas Flow in Porous Media [0.0]
  We present an integrated modeling framework for gas transport in porous media.<n>It combines a Klinkenberg-enhanced relation, Hopf-Cole-transformed mixed-form linear governing equations, and a Deep Least-Squares (DeepLS) solver.<n>Results demonstrate accurate recovery of flow dynamics and parameters across a wide range of pressure regimes.
  arXiv  Detail & Related papers  (2026-03-11T19:17:18Z)
• Differentiable Thermodynamic Phase-Equilibria for Machine Learning [39.691553958657764]
  DISCOMAX is a differentiable algorithm for phase-equilibrium calculation that guarantees thermodynamic consistency at both training and inference.<n>We evaluate the approach on binary liquid-liquid equilibrium data and demonstrate that it outperforms existing surrogate-based methods.
  arXiv  Detail & Related papers  (2026-03-11T19:14:04Z)
• Physics-constrained Gaussian Processes for Predicting Shockwave Hugoniot Curves [39.92721695835137]
  A physics-constrained Gaussian Process regression framework is developed for predicting shocked material states along the Hugoniot curve.<n>The framework reproduces the Hugoniot curve with satisfactory accuracy while also quantifying the uncertainty in the predictions.
  arXiv  Detail & Related papers  (2026-01-10T18:54:24Z)
• Anomaly to Resource: The Mpemba Effect in Quantum Thermometry [0.0]
  We show that nonequilibrium quantum thermometry can transiently outperform both equilibrium strategies and colder states.<n>Our results establish anomalous relaxation as a general design principle for nonequilibrium quantum thermometry.
  arXiv  Detail & Related papers  (2026-01-08T15:51:47Z)
• BITS for GAPS: Bayesian Information-Theoretic Sampling for hierarchical GAussian Process Surrogates [45.88028371034407]
  We introduce the Bayesian Information-Theoretic Sampling for hierarchical GAussian Process Surrogates (BITS for GAPS) framework.<n>BITS for GAPS supports serial hybrid modeling, where known physics governs part of the system.<n>We derive entropy-based acquisition functions that quantify expected information gain from candidate input locations.
  arXiv  Detail & Related papers  (2025-11-20T21:36:21Z)
• Discovery of Sustainable Refrigerants through Physics-Informed RL Fine-Tuning of Sequence Models [12.04169043797071]
  Refgen is a generative pipeline that integrates machine learning with physics-grounded inductive biases.<n>We present Refgen, a generative pipeline that integrates machine learning with physics-grounded inductive biases.
  arXiv  Detail & Related papers  (2025-09-23T21:24:35Z)
• Adaptive Physics-Informed Neural Networks with Multi-Category Feature Engineering for Hydrogen Sorption Prediction in Clays, Shales, and Coals [1.5749416770494706]
  This study introduces an adaptive physics-informed neural network (PINN) framework to enhance hydrogen sorption prediction.<n>The PINN employs deep residual networks with multi-head attention, optimized via adaptive loss functions and Monte Carlo dropout for uncertainty quantification.<n>The framework demonstrates robust lithology-specific performance across clay minerals, shales, and coals, maintaining 85-91% reliability scores.
  arXiv  Detail & Related papers  (2025-08-24T19:41:33Z)
• Neural-network quantum states for ultra-cold Fermi gases [49.725105678823915]
  This work introduces a novel Pfaffian-Jastrow neural-network quantum state that includes backflow transformation based on message-passing architecture. We observe the emergence of strong pairing correlations through the opposite-spin pair distribution functions. Our findings suggest that neural-network quantum states provide a promising strategy for studying ultra-cold Fermi gases.
  arXiv  Detail & Related papers  (2023-05-15T17:46:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.