Missing Physics Discovery through Fully Differentiable Finite Element-Based Machine Learning
By: Ado Farsi, Nacime Bouziani, David A Ham
Potential Business Impact:
Learns missing science rules for better computer predictions.
Although many problems in science and engineering are modelled by well-established PDEs, they often involve unknown or incomplete relationships, such as material constitutive laws or thermal response, that limit accuracy and generality. Existing surrogate-modelling approaches directly approximate PDE solutions but remain tied to a specific geometry, boundary conditions, and set of physical constraints. To address these limitations, we introduce a fully differentiable finite element-based machine learning (FEBML) framework that embeds trainable operators for unknown physics within a state-of-the-art, general FEM solver, enabling true end-to-end differentiation. At its core, FEBML represents each unknown operator as an encode-process-decode pipeline over finite-element degrees of freedom: field values are projected to nodal coefficients, transformed by a neural network, and then lifted back to a continuous FE function, ensuring the learned physics respects the variational structure. We demonstrate its versatility by recovering nonlinear stress-strain laws from laboratory tests, applying the learned model to a new mechanical scenario without retraining, and identifying temperature-dependent conductivity in transient heat flow.
Similar Papers
Towards a Foundation Model for Partial Differential Equations Across Physics Domains
Machine Learning (CS)
Predicts how things move and change using math.
Physics-based Machine Learning for Computational Fracture Mechanics
Numerical Analysis
Predicts how materials break, even with little data.
A Machine Learning and Finite Element Framework for Inverse Elliptic PDEs via Dirichlet-to-Neumann Mapping
Numerical Analysis
Find hidden things inside objects using math.