Physics-informed Neural Networks for Solving Inverse Problems of Nonlinear Biot's Equations: Batch Training

Abstract

In biomedical engineering, earthquake prediction, and underground energy harvesting, it is crucial to indirectly estimate the physical properties of porous media since the direct measurement of those are usually impractical/prohibitive. Here we apply the physics-informed neural networks to solve the inverse problem with regard to the nonlinear Biot's equations. Specifically, we consider batch training and explore the effect of different batch sizes. The results show that training with small batch sizes, i.e., a few examples per batch, provides better approximations (lower percentage error) of the physical parameters than using large batches or the full batch. The increased accuracy of the physical parameters, comes at the cost of longer training time. Specifically, we find the size should not be too small since a very small batch size requires a very long training time without a corresponding improvement in estimation accuracy. We find that a batch size of 8 or 32 is a good compromise, which is also robust to additive noise in the data. The learning rate also plays an important role and should be used as a hyperparameter.

arXiv commentarXiv admin note: text overlap with arXiv:2002.08235

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• Inferring solutions of differential equations using noisy multi-fidelity data
• Quantifying and Reducing Model-Form Uncertainties in Reynolds-Averaged Navier-Stokes Simulations: A Data-Driven, Physics-Based Bayesian Approach
• Physics-informed Neural Networks for Solving Nonlinear Diffusivity and Biot's equations
• A deep learning framework for solution and discovery in solid mechanics
• Efficient Deep Learning Techniques for Multiphase Flow Simulation in Heterogeneous Porous Media

Cited by in corpus (3)

• A Locally Conservative Mixed Finite Element Framework for Coupled Hydro-Mechanical-Chemical Processes in Heterogeneous Porous Media
• Non-intrusive reduced order modeling of poroelasticity of heterogeneous media based on a discontinuous Galerkin approximation
• Enriched Galerkin Discretization for Modeling Poroelasticity and Permeability Alteration in Heterogeneous Porous Media