Auto-weighted Bayesian physics-informed neural networks and robust estimations for multitask inverse problems in pore-scale imaging of dissolution

DOI10.1007/s10596-024-10313-xMaRDI QIDQ6662478

Sarah Perez, Philippe Poncet

Publication date: 14 January 2025

Published in: Computational Geosciences (Search for Journal in Brave)

zbMATH Keywords

artificial intelligenceuncertainty quantificationHamiltonian Monte CarloBayesian physics-informed neural networksmulti-objective trainingimaging inverse problempore-scale porous media

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Inverse problems in geophysics (86A22) Geostatistics (86A32)

Cites Work

• Unnamed Item
• The No-U-Turn Sampler: Adaptively Setting Path Lengths in Hamiltonian Monte Carlo
• Limitations of polynomial chaos expansions in the Bayesian solution of inverse problems
• Dimensionality reduction and polynomial chaos acceleration of Bayesian inference in inverse problems
• A velocity-vorticity method for highly viscous 3D flows with application to digital rock physics
• B-PINNs: Bayesian physics-informed neural networks for forward and inverse PDE problems with noisy data
• Multi-fidelity Bayesian neural networks: algorithms and applications
• Adaptive multi-fidelity polynomial chaos approach to Bayesian inference in inverse problems
• A lattice-Boltzmann study of permeability-porosity relationships and mineral precipitation patterns in fractured porous media
• Simulation of mineral dissolution at the pore scale with evolving fluid-solid interfaces: review of approaches and benchmark problem set
• A benchmark study on problems related to CO\(_{2}\) storage in geologic formations. Summary and discussion of the results
• Robust control of parabolic stochastic partial differential equations under model uncertainty
• Bayesian physics informed neural networks for real-world nonlinear dynamical systems
• Uncertainty quantification in scientific machine learning: methods, metrics, and comparisons
• Pore-scale modelling of multiphase reactive flow: application to mineral dissolution with production of
• Homogenization of reactive flows in porous media and competition between bulk and surface diffusion
• Mineral dissolution and wormholing from a pore-scale perspective
• A Convex Optimization Framework for the Inverse Problem of Identifying a Random Parameter in a Stochastic Partial Differential Equation
• An Adaptive Surrogate Modeling Based on Deep Neural Networks for Large-Scale Bayesian Inverse Problems
• Adaptive weighting of Bayesian physics informed neural networks for multitask and multiscale forward and inverse problems
• Physics-informed information field theory for modeling physical systems with uncertainty quantification

This page was built for publication: Auto-weighted Bayesian physics-informed neural networks and robust estimations for multitask inverse problems in pore-scale imaging of dissolution