New PIE-PINN framework enhances elastic property estimation from noisy data

By PulseAugur Editorial · [2 sources] · 2026-07-16 04:43

Researchers have developed a Probabilistic Inverse Elasticity Physics-Informed Neural Network (PIE-PINN) framework designed to robustly estimate heterogeneous elastic properties from noisy and low-resolution displacement data. This new framework models observation, strain-discrepancy, and equilibrium residuals using Laplace distributions. It incorporates a B-spline-guided displacement network and a hierarchical half-Cauchy model to improve accuracy and adaptively downweight fitting errors, demonstrating significant robustness in case studies with varying noise levels and resolutions. AI

IMPACT This framework could improve the accuracy of material property estimations in engineering and scientific applications by handling noisy and low-resolution data more effectively.

RANK_REASON The cluster contains a research paper describing a new method.

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

New PIE-PINN framework enhances elastic property estimation from noisy data

COVERAGE [2]

arXiv cs.LG TIER_1 English(EN) · Jaesung Lee · 2026-07-16 04:43

Probabilistic Physics-Informed Neural Networks for Estimating Heterogeneous Elastic Properties from Low-Resolution and Noisy Displacement Data

Estimating spatially heterogeneous elastic properties from low-resolution displacement measurements is a severely ill-posed inverse elasticity problem because low resolution obscures spatial details needed to distinguish heterogeneous property variations, and small measurement pe…
arXiv stat.ML TIER_1 English(EN) · Tatthapong Srikitrungruang, Jaesung Lee · 2026-07-17 04:00

Probabilistic Physics-Informed Neural Networks for Estimating Heterogeneous Elastic Properties from Low-Resolution and Noisy Displacement Data

arXiv:2607.14563v1 Announce Type: cross Abstract: Estimating spatially heterogeneous elastic properties from low-resolution displacement measurements is a severely ill-posed inverse elasticity problem because low resolution obscures spatial details needed to distinguish heterogen…

COVERAGE [2]

Probabilistic Physics-Informed Neural Networks for Estimating Heterogeneous Elastic Properties from Low-Resolution and Noisy Displacement Data

Probabilistic Physics-Informed Neural Networks for Estimating Heterogeneous Elastic Properties from Low-Resolution and Noisy Displacement Data

RELATED ENTITIES

RELATED TOPICS