Latest Physics-Informed Neural Nets Research Papers
The newest Physics-Informed Neural Nets papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Physics-Informed Neural Nets so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.
Get the latest Physics-Informed Neural Nets papers in your inbox — free →Recent papers
- Session 1: Platform Development IDr. Kevin A. Adkins, Dr. Gustavo B.H. de Azevedo, Brendon A. Cavainolo, Swety Sarker et al. · Scholarly Commons (Embry–Ri... · Aug 25, 2026
Presentations Cavainolo, Sarker, Kinzel, Bird, Dyer, & Berk: WindSDK: A Unified Framework for Querying Atmospheric Data Sarker, Cavainolo, Bird, Berk & Kinzel: A Study of Physics-Informed Neural Networks applied to Real-Time Atmospheric Flo…
- PG-KINN: A Physics-Informed Petrov-Galerkin Kolmogorov-Arnold Network for Solving Forward and Inverse PDEsAmirhossein Sadr, Nima Soltani, Vahideh Moghtadaiee, Aida Pakniyat et al. · arXiv · Jul 22, 2026
Physics-informed learning of partial differential equations (PDEs) has been dominated by multilayer perceptrons (MLPs), whose spectral bias and dense parameterization limit both accuracy and interpretability. Kolmogorov Arnold Networks (KAN…
- Label-Free Finite-Volume-Residual Training of Attention Graph Neural Networks for Coupled Thermo-Fluid FieldsTianyu Li, Zhiwei Cao, Qingang Zhang, Ruihang Wang et al. · arXiv · Jul 22, 2026
Neural surrogates are widely used in scientific machine learning for fast prediction of three-dimensional (3D) thermo-fluid fields. However, generating training data using conventional numerical solvers often incurs substantial computationa…
- PIER: Physics-Informed Environmental Retrieval for Time-Series ModelingShiyuan Luo, Runlong Yu, Chonghao Qiu, Yue Qin et al. · arXiv · Jul 22, 2026
Accurate modeling of environmental systems is fundamental to scientific understanding and decision-making, yet remains challenging because observations are limited and physical dynamics vary across systems. Retrieval-augmented approaches of…
- Variational Boosting for Physics-Informed Neural NetworksPavlos Protopapas, Kaylee Vo · OpenAlex · Jul 22, 2026
- Physics-Informed Neural Networks for Dissipative Micropolar Nanofluid Flow with Microrotation Dynamics and Zero Nanoparticle Mass FluxHamid Reza Soltani Motlagh, A. M. Amer, Nourhan I. Ghoneim, Ahmed M. Megahed et al. · Modelling—International Ope... · Jul 22, 2026
This research presents a physics-informed deep learning framework for investigating the magnetohydrodynamic flow of a dissipative non-Newtonian micropolar nanofluid induced by a stretching sheet, incorporating Stefan blowing, internal heat …
- DATA & LEAN of Loss Spikes in Physics-Informed Neural Networks: A Single Mechanism, Its Predictions, and Practical ControlGONG CHUYAO · Zenodo (CERN European Organ... · Jul 21, 2026
- Evaluation of <sup>235,238</sup> U fission product yields using Bayesian neural networks: Comparison of baseline and physics-informed modelsChun-Yuan Qiao, Ya-Xuan Wang, Jun-Chen Pei, Chun-Wang Ma et al. · Frontiers of Physics · Jul 21, 2026
235U and 238U are fundamental materials in thermal and fast neutron breeding studies. Accurate evaluation of their fission product yields is of critical importance for advanced reactor design and nuclear waste management. In this work, a ba…
- Neural spectral element methods for stiff multiphysics PDEs with electrochemical transport benchmarksConrard Giresse Tetsassi Feugmo, David Pankaczy · Machine Learning Science an... · Jul 21, 2026
Abstract Physics-informed neural networks (PINNs) face an empirical accuracy floor of approximately O(10^-2) when applied to stiff multiphysics problems like electrochemical transport. This limitation stems from the "PINN trilemma": Monte C…
- Conformal Uncertainty-Aware Physics-Informed Neural Networks for Reliable Electromagnetic Field Prediction in VLSI InterconnectsSofia Duarte, Benjamin Hart · Academic Journal of Applied... · Jul 21, 2026
Electromagnetic field prediction in very-large-scale integration (VLSI) interconnects is increasingly constrained by two competing requirements: field solvers must remain physically faithful near conductor edges and material interfaces, yet…
- AI/ML in Chemical Engineering: From molecular design to industrial process optimizationFatemeh Valizadeh Hajidehi, Azam Mina · Chemical and Process Engine... · Jul 21, 2026
The integration of artificial intelligence and machine learning into chemical engineering represents a paradigm transformation that fundamentally reconceptualizes practice across molecular, process, and industrial scales. This comprehensive…
- Multi-Fidelity Physics-Informed Neural Networks for Fast Electromagnetic Simulation of RF Integrated-Circuit PassivesMarina Petrova, Leo Fernandez · Journal of Computing and El... · Jul 20, 2026
Full-wave electromagnetic (EM) analysis of radio-frequency (RF) integrated-circuit passives is accurate but too slow for the many-query loops of modern design automation, whereas quasi-static approximations are fast but miss frequency-depen…
- Hybrid deep unrolling and graph neural networks for super-resolution direction-of-arrival estimation in physics-informed antenna arraysSai Vinay Thattukolla · Frontiers in Antennas and P... · Jul 20, 2026
Background Traditional subspace methods like SS-MUSIC often degrade under low sample support. This is further exacerbated by strong mutual coupling within antenna arrays. While deep learning offers a potential alternative, standard architec…
- Wind Pressure Prediction for Ridge–Valley Membrane Structures Using a Multi-Mechanism Enhanced Physics-Informed Neural NetworkSun Fang-jin, Qing-cheng He, Quan Luo, Da-Ming Zhang · Buildings · Jul 20, 2026
To address the challenge of reconstructing statistical wind pressure fields of membrane structures under sparse measurement conditions, this study proposes an FF-Res-GP-PINN framework based on wind tunnel test data from a ridge–valley membr…
- Method for Real-Time Monitoring of the Lubrication Regimes in Dynamically Loaded Radial Sliding Bearings Using Physics-Informed Neural Networks (PINNs)Ahmed Saleh, Georg Jacobs, Wenxi Chen, Mattheüs Lucassen et al. · Lubricants · Jul 20, 2026
This study proposes a model-based method for real-time monitoring of the lubrication regimes in dynamically loaded radial sliding bearings using Physics-Informed Neural Networks (PINN). The proposed method replaces computationally intensive…
- AI-Driven Iterative Model for Accelerated ATC Computation under Transmission Congestion using Hybrid Forecasting, Deep Feature Compression, and Physics-Informed OptimizationsSandeep A. Kale, Nitin D. Ghawghawe · WSEAS TRANSACTIONS ON POWER... · Jul 20, 2026
The Modern power systems face rising complexity from demand expansion and renewable integration, requiring faster and more accurate Available Transfer Capability (ATC) estimation. Real-time congestion management is limited by traditional ap…
- A gradient-enhanced physics-informed neural network with adaptive loss weighting for high-dimensional non-linear sine-Gordon problemsAlemayehu Tamirie Deresse, Tamirat Temesgen Dufera · Scientific Reports · Jul 19, 2026
- Physics-informed multi-task learning for permeability prediction and probabilistic HFU modeling: a case study from the Lower Bahariya Reservoir, Shahd SE field EgyptKhaled Saleh, Walid M. Mabrouk, Ahmed Metwally · Scientific Reports · Jul 19, 2026
Abstract Accurate permeability prediction is essential for reliable reservoir characterization and simulation, yet remains challenging due to complex nonlinear relationships and subsurface heterogeneity. Conventional hydraulic flow unit (HF…
- Early-stage degradation mechanism and PINN-based state-of-health prediction of a PEMFC stack under typical ship operating conditionsXi Zhang, Bowen Zhang, Shuai Wang, Huan Kang et al. · Applied Energy · Jul 18, 2026
- A unified multi-objective physics-informed neural network framework for thermo-mechanical parameter inversion of arch dams with adaptive loss weighting and pareto-based optimizationHaifeng Jiang, Dongjian Zheng, Xin Wu · ENGINEERING Structure and C... · Jul 18, 2026
- Parameter identification of the viscoelastic constitutive model for particle filled polymer composites based on physics-informed neural operatorXM. Wang, T A Zhang, Yi Yang, Jiming Cheng et al. · Acta Mechanica Sinica · Jul 18, 2026
- Topology–kinematic synthesis and physics-informed dynamic modeling of a high-frequency fast tool servo for vibration-assisted turningTan Thang Nguyen, Nhat Linh Ho, Hieu Giang Le, Thanh-Phong Dao · The International Journal o... · Jul 18, 2026
- Physics-Informed CycleGAN Framework Combining GNN and Transformer for Domain AdaptationShang-Jun CHEN, Chuan-Chuan Hou, Stefano Mariani · e-Journal of Nondestructive... · Jul 17, 2026
In this study, a physics-informed Cycle-Consistent Generative Adversarial Network (CycleGAN) framework is proposed for vibration-based structural health monitoring of structures subjected to lateral impacts. The proposed method aims to tran…
- Structural parameter identification with hybrid physics informed neural networkNikhil Mahar, Gajendra Yadav, Kajal Thakur, Subhamoy Sen et al. · e-Journal of Nondestructive... · Jul 17, 2026
System identification (SI) is critical for ensuring the reliability of structural and mechanical components across engineering applications. Traditional model-based SI methods often struggle with complex dynamics and the scarcity of accurat…
- Comparative Evaluation of Physics-Informed and Data-Driven Neural Networks for Reservoir Water Balance Simulation During Hydrological ExtremesS. Tharuka, Luminda Gunawardhana, B. C. Dissanayake, Lalith Rajapakse · Water Resources Management · Jul 17, 2026
- Physics-Informed Neural Network for baseline-free damage diagnosis using Ultrasonic Guided WavesALBERTO CASARTELLI, Luca Lomazzi, Marco Giglio, Francesco Cadini · e-Journal of Nondestructive... · Jul 17, 2026
Ultrasonic Guided Waves (UGWs) are among the most effective tools for damage diagnosis and Structural Health Monitoring (SHM) of thin-walled structures. However, traditional SHM methods based on UGWs typically require baseline measurements …
- Data-Guided Physics-Informed Neural Network with Fourier Features Enhancement for Euler-Bernoulli Beam AnalysisHailong Liu, Flanders Make-Motions, Saeid Hedayatrasa, Yunpeng Zhu et al. · e-Journal of Nondestructive... · Jul 17, 2026
Physics-informed neural networks (PINNs) have emerged as a powerful paradigm in scientific machine learning by embedding governing physical laws into neural network training through loss functions. They have demonstrated remarkable success …
- Internal 3D full-field deformation measurement method based on physics-informed neural networksChuanyi Wang, Boda Li, Yong Su, Yu Xiao et al. · Optics and Lasers in Engine... · Jul 17, 2026
- Modified-inverse physics informed neural networks for determination of orthotropic thermal conductivitiesGudipati Sai Krishna, J. Jithu, Muthusaran Coimbatore Vijayakumar, C. Balaji et al. · International Journal of Nu... · Jul 17, 2026
Purpose This study aims to propose a modified inverse physics-informed neural network (MIPINN) framework for accurate and efficient simultaneous multiparameter identification in three-dimensional heat conduction problems under sparse experi…
- Physics-Informed Neural Network Framework for Input Load Estimation and Virtual Sensing of Offshore Wind TurbinesAzin Mehrjoo, Eleonora M. Tronci, Babak Moaveni · e-Journal of Nondestructive... · Jul 17, 2026
Recent advances in Physics-Informed Neural Networks (PINNs) have opened new possibilities for integrating structural dynamics and data-driven learning in Structural Health Monitoring (SHM). This work presents a physics-informed framework fo…