The Flow has not summarised this story yet — read it at arXiv Machine Learning.
arXiv:2607. 07863v1 Announce Type: new Abstract: In physically dominated machining processes, experimental datasets are small, expensive, and material-specific; in this regime, data curation, evaluation design, and the form of physics integration can matter as much as the learning algorithm.
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.
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.
arXiv:2608. 09998v1 Announce Type: new Abstract: Artificial Intelligence (AI) and Machine Learning (ML) have become powerful tools for supporting and automating complex human tasks.
Biologically-informed neural networks (BINNs) are a subclass of physics-informed neural networks tailored for learning partial differential equations in biological systems, where equations are nonlinear and data are sparse. The paper introduces a diagnostic workflow for selecting hyperparameters—network capacity, training epochs, and term stability—without requiring known ground-truth equations. By applying this workflow to synthetic systems, the authors show that validation loss tracks true error and provide practical guidelines and starting values for BINN hyperparameter tuning.
arXiv:2606. 06164v1 Announce Type: new Abstract: Physics-informed neural operators (PINOs) aim to learn solution operators for partial differential equations by using the governing physics as supervision, rather than relying solely on paired input-output simulation data.