physics-informed-learning

A physics-informed self-supervised learning framework is introduced for calibrating and reconstructing positions in multi-wire parallel plate avalanche counters using only detector geometry and charge constraints, eliminating the need for labeled data or dedicated calibration runs.

PhyRestore introduces a physics-structured framework for restoring corrupted physical factors in soil-loss estimation, improving the recovery of temporal changes through known physical relationships.

This paper introduces a diagnostic method for reinforcement learning simulators and world models using exact polynomial invariants, developing screening and attribution procedures to localize broken constraints and identify faulty parameters.

This research proposes a multifidelity method combining time-delay neural network and physics-informed residual learning to enhance railway-bogie response prediction by integrating simulation and experimental data.

SS-eSOAP introduces a self-scaled adaptive preconditioning method for physics-informed neural networks, improving optimization by reducing residuals and achieving higher accuracy on various PDE benchmarks compared to baseline methods.

This paper investigates physics-informed and hybrid machine learning strategies to predict bond quality and porosity in fused filament fabrication, showing accurate models even with limited experimental data.

Introduces PI-Splines, a structured spline-based architecture for physics-informed learning that parametrizes unknown fields with trainable B-spline coefficients, providing compact support, analytical derivatives, and strong boundary condition enforcement, demonstrated as a competitive alternative to neural network-based methods.