Physics-Informed ML

ML: Machine Learning

Follow this topic Ask about this topic

Momentum

60 papers in the last four weeks, up 131% on the four weeks before. 0.6% of all new papers.

Jul 13Week of Sep 28

Latest papers 561

All topics

Derivative Computation in PINNs: Automatic Differentiation, Finite Differences and Beyond
Aug 11, 2026Maciej J. Mikulski, Tadeusz UhlAutomatic Differentiation Neural PDE Solvers
AGH University of Krakow
HNDiff: Haze-Noise Diffusion for Image Dehazing
Aug 11, 2026Jin-Ting He, Fu-Jen Tsai, Yan-Tsung Peng +3Physics-Informed Diffusion Models Diffusion Models for Image Restoration
Department of Computer Science, National Yang Ming Chiao Tung University, Taiwan · National Tsing Hua University, Taiwan · National Chengchi University, Taiwan +1
Physics-informed Diffusion Generative Model for Time-Series Data Synthesis in Dynamic Systems
Aug 11, 2026Haiteng Wang, Yunfei Zhu, Tao Wang +4Synthetic Data Augmentation Synthetic Data Generation
School of Automation Science and Electrical Engineering, Beihang University, Beijing, 100191, China. · School of Software, Beihang University, Beijing, 100191, China. · Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Kowloon, 100191, Hong Kong. +1
Physics-Informed Implicit Neural Representations for Improved Myocardial Perfusion MRI Quantification
Aug 11, 2026Christos Tsepas, Chang Yan, Maximilian Fuetterer +2Implicit Neural Representations Medical Image Analysis
Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands · Institute for Biomedical Engineering, University and ETH Zurich, Zurich, Switzerland
Efficient Weak-Entropy PINN for Solving Hyperbolic Conservation Laws
Aug 11, 2026Qi Gao, Kuang Huang, Xuan DiNeural PDE Solvers PDE Solving
Department of Civil Engineering and Engineering Mechanics, Columbia University · Department of Mathematics, The Chinese University of Hong Kong · Center for Smart Cities, Data Science Institute, Columbia University
Physics-Informed Machine Learning in Prognostics and Health Management: A Systematic Literature Review
Aug 10, 2026Christopher Braun, Julian Raible, Marco F. HuberPredictive Maintenance Physics-Informed ML
Institute of Industrial Manufacturing and Management IFF, University of Stuttgart, Allmandring 35, Stuttgart, 70569, Baden-Württemberg, Germany. · Fraunhofer Institute for Manufacturing Engineering and Automation IPA, Nobelstraße 12, Stuttgart, 70569, Baden-Württemberg, Germany.
Hierarchical rank-evolving representation for physics-informed neural networks
Aug 10, 2026Ruoyang Su, Xi-Le Zhao, Kun Li +1Tensor Networks Neural PDE Solvers
University of Electronic Science and Technology of China, No.2006, Xiyuan Ave, West Hi-Tech Zone, Chengdu, 611731, Sichuan, P.R.China · Southwestern University of Finance and Economics, 555, Liutai Avenue, Wenjiang District, Chengdu, 611130, Sichuan, P.R.China
Coordinate-Residual Physics-Driven Neural Network for Inverse Scattering Imaging
Aug 10, 2026Yutong Du, Zicheng Liu, Bo Qi +2Image Reconstruction Physics-Informed ML
Department of Electronic Engineering, School of Electronics and Information, Northwestern Polytechnical University, Xi’an 710029, China
VeinCast: Physics-Guided Dynamic Field Graphs with Graph-Conditioned Fusion for Global Medium-Range Weather Forecasting
Aug 10, 2026Zhisheng Chen, Jinhan Li, Yuxuan Li +6Dynamic Graph Learning Physics-Informed ML
1Nanyang Technological University · 2Tsinghua University · 3Peking University +1
Physics-Informed Learning for Robust Acoustic Localization with Calibrated Uncertainty
Aug 9, 2026Jennifer N. Kampe, Changwoo J. Lee, Xin Shen +5Physics-Informed ML Bioacoustics
Department of Biological and Environmental Science, University of Jyväskylä, Jyväskylä, Finland · Department of Statistical Science, Duke University, Durham, NC, USA · 3Digital Services, University of Jyväskylä, Jyväskylä, Finland +1
Quantum-Classical Physics-Informed Kolmogorov-Arnold Networks for Solving Fuzzy Differential Equations
Aug 9, 2026Xiang Rao, Yuxuan ShenPDE Solving Hybrid Quantum-Classical ML
1. School of Petroleum Engineering, Yangtze University, Wuhan 430100, China · 2. College of Future Technology, Yangtze University, Wuhan 430100, China · 3. School of Computer Science, Yangtze University, Jingzhou 434023, China +2
A Structural Dynamics Graph World Model: Unified Modeling, Constrained Rollout, and Interpretable Calibration
Aug 9, 2026Wei Wang, Yaosen Chen, Han Yang +5World Model Learning World Models
Sobey Media Intelligence Laboratory
Physics-Informed Condition Monitoring of SiC Power Modules
Aug 8, 2026Mattia Scarpa, Evgeny Kusmenko, Francesco Toso +3Predictive Maintenance Physics-Informed ML
Department of Information Engineering, University of Padova, Padova, Italy · Newtwen S.r.l., Padova, Italy · Infineon Technologies Dresden GmbH & Co. KG, Dresden, Germany +1
Stochastic Physics-Informed Neural Networks on Lie Groups for Learning Underwater Vehicle Dynamics
Aug 8, 2026Evan F. Palmer, Ross L. Hatton, Geoffrey A. HollingerRobot Dynamics Identification Underwater Robotics
Collaborative Robotics and Intelligent Systems (CoRIS) Institute, Oregon State University, Corvallis OR 97331, USA
Eikonal Regularisation in Physics-Informed Neural Networks for Three-Dimensional Level-Set Advection: Transferability of Two-Dimensional Design Principles
Aug 8, 2026Muhammad Akbar KhanNeural PDE Solvers Physics-Informed ML
Department of Mathematics, NED University of Engineering and Technology, Karachi 75270, Pakistan
Finite basis physics-informed neural networks with hard constraints for viscous fluid flow in highly perforated domains
Aug 8, 2026Jeeeun Lee, Denis Korolev, Miro Duhovic +1Neural PDE Solvers Physics-Informed ML
Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, 291 Daehak-ro, Yuseong-gu, Daejeon, 34141, Republic of Korea · Weierstrass-Institute for Applied Analysis and Stochastics, Anton-Wilhelm-Amo-Str. 39, Berlin, 10117, Germany · Leibniz-Institut für Verbundwerkstoffe GmbH, Erwin-Schrödinger-Str. 58, Kaiserslautern, 67663, Germany
Vision Meets WiFi: Physics-Grounded Estimation of Volumetric Mechanical Properties
Aug 7, 2026Ali Bahri, Hongliang Li, Soufiane Lamghari +2Object-Centric Representation Learning Materials Property Prediction
Huawei Noah’s Ark Lab, Canada · Huawei Noah’s Ark Lab, Hong Kong SAR, China
PhysAttNet: Enhancing Predictive Performance in Industrial and Astrophysical Time Series via Physics-Informed Attention
Aug 7, 2026Amal Saadallah, Julia Tjus, Petra Wiederkeher +1Time Series Forecasting Physics-Informed ML
Faculty of Physics and Astronomy, Ruhr University Bochum, Germany · Virtual Machining Group, TU Dortmund, Germnay · Faculty of Physics, Germany
Unsupervised Adaptation of PDE Foundation Models
Aug 7, 2026Ziye Song, Zhao Wei, Xin Yu +2Unsupervised Domain Adaptation Low-Rank Adaptation
Nanyang Technological University · CFAR, A*STAR · Adelaide University
Alternating Levenberg-Marquardt Training of Physics-Informed Neural Networks with Fourier-Enhanced Features
Aug 6, 2026Yulun Wu, Matthieu Barreau, Miguel Aguiar +1Neural PDE Solvers Spectral Bias
Division of Decision and Control Systems, School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology, Stockholm, 100 44, Sweden
Discrete energy as an exact label-free training objective for finite-element surrogates
Aug 5, 2026Ruifeng Cao, Xidan SongSurrogate Modeling Structural Mechanics
The University of Manchester · The University of Manchester, Manchester, United Kingdom · Wuhan University +1
Continual-Learning Physics-Informed Neural Networks for Parameterized Partial Differential Equations
Aug 5, 2026Xujia Chen, Xinyue Hu, Letian Chen +2PDE Surrogate Modeling Replay-Based Continual Learning
Department of Automation, Tsinghua University, Beijing, 100084, China
Wrong Operator or Blind Design? A Reference-Free Diagnostic for Physics-Informed Coefficient Learning
Aug 4, 2026Eric FockParameter Estimation Parameter Identifiability
PIMENT Laboratory, Universit´e de La R´eunion, Le Tampon 97430, La R´eunion, France
Transferable Dual-Stream Representations for Mesoscale-Preserving Sea Surface Temperature Downscaling
Aug 4, 2026Parth Doshi, Priyanka Aravindan, Vaishnav Vaidheeswaran +2Geospatial Representation Learning Climate Science
Dalhousie University, Halifax, NS, Canada
From Non-Convex Self-Concordant Regularization to Scalable Quasi-Newton Training of PINNs
Aug 4, 2026Chenhao Si, Kang An, Shiqian Ma +1Neural PDE Solvers Second-Order Optimization
School of Data Science, The Chinese University of Hong Kong, Shenzhen, 2001 Longxiang Road, Longgang District, Shenzhen, 518172, Guangdong, China · Department of Computational Applied Mathematics and Operations Research, Rice University, 6100 Main Street, MS 134, Houston, 77005-1827, Texas, USA · Data Science and AI Institute, and Department of Applied Mathematics and Statistics, Johns Hopkins University, 3400 N. Charles Street, Baltimore, 21218, Maryland, USA
A Physics-Flavored Transformer Network for Parametrizing Contraction Dynamics of Engineered Skeletal Muscle Tissues
Aug 4, 2026Mattias Luber, Timo BetzPhysics-Informed ML
CIDAS: Campus-Institute Data Science, Goldschmidtstraße 1, Göttingen, 37077, Lower Saxony, Germany · Third Institute of Physics, University of Göttingen, Friedrich-Hund-Platz 1, Göttingen, 37077, Lower Saxony, Germany
FlowForm: Synergizing Fluid Physics with Topological Consistency for Satellite Flood Synthesis
Aug 4, 2026Zhang Weihui, Wang Ruizhi, Xu Hongye +3Physics-Informed Generative Modeling Synthetic Data Augmentation
Zhejiang University, Zhejiang, China
ED-DiT: Physics-Guided Diffusion Pretraining for Transferable Molecular Representations from Electron Density
Aug 4, 2026Liang Shuang, Haocheng Wang, Jiayi Song +2Diffusion Transformer Self-Supervised Pre-Training
Fudan University, Shanghai, China · Shenzhen Loop Area Institute, Shenzhen, China · The Chinese University of Hong Kong, Hong Kong SAR, China
ScoreField: Neural Inverse Scattering with Score-Based Generative Priors
Aug 3, 2026Wenhan Guo, Yuan Gao, Yu SunPhysics-Informed ML Inverse Problems
Hopkins Computational Imaging Group · Johns Hopkins University
From fragmented data to actionable design: Physics-calibrated learning for plastic upcycling
Aug 3, 2026Jingyang Bai, Zijia Wang, Xiangyi Long +3Mixture of Experts Learning with Missing Data
Department of Chemical Engineering, Imperial College London, South Kensington Campus, London SW7 2AZ, UK · Department of Electrical and Electronic Engineering, Imperial College London, South Kensington Campus, London SW7 2AZ, UK · Interdisciplinary Research Center for Refining and Advanced Chemicals, King Fahd University of Petroleum and Minerals, Dhahran 31261, Saudi Arabia +4

Aug 11, 2026, cs.LGJ/K move · Enter open · S save

Derivative Computation in PINNs: Automatic Differentiation, Finite Differences and Beyond

Maciej J. Mikulski, Tadeusz Uhl

AGH University of Krakow

Automatic Differentiation Neural PDE Solvers PDE Solving Physics-Informed ML

Open paper AskPDF arXiv

We systematically investigate finite-difference (FD) derivative computation in Physics-Informed Neural Networks (PINNs) as an alternative to automatic differentiation (AD). On three benchmark PDEs we show that, with a properly calibrated step size, FD matches AD in accuracy on every problem while running faster across the full tested batch-size range and using substantially less GPU memory, and that a stochastic variant we propose outperforms AD on a stationary problem. We further show that for neural architectures with inter-sample dependencies (e.g. BatchNorm, self-attention) the standard PyTorch autograd idiom is silently incorrect; the correct per-sample alternative is computationally infeasible at PINN-relevant batch sizes, while FD provides a forward-only approximation that is empirically an order of magnitude closer to the true per-sample derivative.

Momentum

Related topics

Latest papers 561