← Back to all news
arXiv Machine Learning

Information fusion and machine learning for sensitivity analysis using physics knowledge and experimental data

The paper explores global sensitivity analysis (GSA) when both physics-based models and experimental data are available, focusing on physics-informed machine learning to improve sensitivity estimates. It evaluates two ML approaches—deep neural networks (DNN) and Gaussian processes (GP)—and two physics integration strategies: physics-constrained loss functions and sequential pre‑training with simulation followed by experimental fine‑tuning. Four models per ML type are constructed, incorporating model uncertainties into Sobol index calculations, and results show DNNs yield tighter sensitivity bounds than GP models, demonstrated on additive manufacturing and lake temperature examples.

Related stories

Hugging Face Trending Papers
Aug 18

Information fusion and machine learning for sensitivity analysis using physics knowledge and experimental data

When computational models (either physics-based or data-driven) are used for the sensitivity analysis of engineering systems, the sensitivity estimate is affected by the accuracy and uncertainty of the model. This paper considers global sensitivity analysis (GSA) for situations where both a physics-based model and experimental observations are available, and investigates physics-informed machine learning strategies to effectively combine the two sources of information in order to maximize the accuracy of the sensitivity estimate.

More like this →
arXiv Machine Learning
Aug 19

Physics-Informed and Hybrid Machine Learning in Additive Manufacturing: Application to Fused Filament Fabrication

The article explores physics-informed and hybrid machine learning approaches for predicting bond quality and porosity in fused filament fabrication (FFF) parts. It examines three strategies—embedding physics constraints in the loss function, adding physics model outputs as inputs, and pre‑training with physics data—to enforce consistency with physical laws. Eight combinations of these strategies are tested, showing that integrating multiple approaches yields accurate predictions even with limited experimental data.

By Berkcan Kapusuzoglu, Sankaran Mahadevan
More like this →
arXiv Machine Learning
Aug 27

Physics-Informed Error Field Learning: A Post-Training Optimization Framework for Physics-Informed Neural Networks

Physics-Informed Error Field Learning (PIEFL) is a post‑training optimization framework for Physics‑Informed Neural Networks (PINNs). After a primary network reaches satisfactory accuracy, PIEFL introduces an auxiliary error network that learns the discrepancy between the current approximation and the exact solution by deriving error control equations under physical constraints. The learned error correction is then combined with the primary prediction, improving solution accuracy without modifying the primary network architecture and focusing computational resources on correcting existing prediction errors.

By Jiuyun Sun, Yong Zhang
More like this →
arXiv Machine Learning
Aug 31

Examining the robustness of Physics-Informed Neural Networks to noise for Inverse Problems

The paper evaluates the robustness of Physics‑Informed Neural Networks (PINNs) against noisy data in inverse problems, comparing them to a finite element method (FEM) plus optimizer baseline. Experiments on viscosity identification in 1D Burgers’ equation and 2D/3D Taylor‑Green Vortex with additive Gaussian noise show that PINNs, while requiring less human expertise, are outperformed by the traditional FEM approach in accuracy (e.g., RMSE 0.01 vs. 0.0013 for 2D Taylor‑Green with σ=1). PINNs do, however, exhibit better scaling with problem complexity, and the study highlights specific training failures that must be addressed for PINNs to become more competitive.

By Aleksandra Jekic, Afroditi Natsaridou, Signe Riemer-S{\o}rensen, Helge Langseth, Odd Erik Gundersen
More like this →