Neural Surrogate Modeling

Ask about this topic

Overview

Neural surrogate modeling replaces repeated calls to expensive simulators with learned approximations of physical fields, system dynamics, or quantities of interest, making tasks such as design search, control, and Bayesian inference more practical. Common approaches include neural operators for PDE solution maps, graph neural networks for meshes and networks, reduced-order latent models, and physics-informed or hybrid models that combine learned components with governing equations. Researchers also use multi-fidelity training, active learning, and probabilistic models to reduce data needs and estimate uncertainty. A central challenge is that good one-step or in-distribution accuracy does not guarantee stable long rollouts, reliable extrapolation, physical consistency, or improved downstream decisions; classical solvers remain important when stringent accuracy and verification are required.

Latest papers

CardsList

418 papers45 papers in the last four weeks, down 15% on the four weeks before. 0.3% of all new papers.

  1. A finite-element-inspired bipartite graph learned simulator for manufacturability assessment in large-deformation sheet forming

    May 14, 2026Yingxue Zhao, Haoran Li, Haosu Zhou +2Neural Surrogate ModelingGraph Neural Networks

    Dyson School of Design Engineering, Imperial College London, London, UK · NVIDIA, UK

  2. Real-time virtual circuits for plasma shape control via neural network emulators

    May 14, 2026Alasdair Ross, George K. Holt, Kamran Pentland +7Neural Surrogate ModelingFeedback Control

    STFC Hartree Centre, Sci-Tech Daresbury, Keckwick Lane, Daresbury, Warrington, WA4 4AD, United Kingdom · United Kingdom Atomic Energy Authority, Culham Campus, Abingdon, Oxfordshire, OX14 3DB, United Kingdom

  3. Scalable Solution of the Stochastic Multi-path Traveling Salesman Problem via Neural Networks

    May 14, 2026Xiaochen Chou, Ludovica Di Marco, Enza MessinaNeural Surrogate ModelingStochastic Optimization

    Department of Informatics, Systems and Communication, University of Milano-Bicocca, Viale Sarca 336, Milan, 20125, Italy.

  4. All-atomistic Transferable Neural Potentials for Protein Solvation

    May 14, 2026Rishabh Dey, Salvina Sharipova, Konstantin PopovNeural Surrogate ModelingMachine Learning Interatomic Potentials

    University of North Carolina at Chapel Hill - Eshelman School of Pharmacy

  5. Learning Scenario Reduction for Two-Stage Robust Optimization with Discrete Uncertainty

    May 14, 2026Tianjue Lin, Jianan Zhou, Jieyi Bi +4Neural Surrogate ModelingRobust Optimization

    Nanyang Technological University · Eindhoven University of Technology · Shandong University +1

  6. Mask-Morph Graph U-Net: A Generalisable Mesh-Based Surrogate for Crashworthiness Field Prediction under Large Geometric Variation

    May 13, 2026Haoran Li, Tobias Lehrer, Yingxue Zhao +5Neural Surrogate ModelingGraph Neural Networks

    Dyson School of Design Engineering, Imperial College London, London, UK · TUM School of Engineering and Design, Technical University of Munich, Munich, Germany · Faculty of Mechanical Engineering, OTH Regensburg, Regensburg, Germany +1

  7. Toward AI-Driven Digital Twins for Metropolitan Floods: A Conditional Latent Dynamics Network Surrogate of the Shallow Water Equations

    May 13, 2026Phillip Si, Yuan Qiu, Omar Sallam +4Digital TwinsPDE Surrogate Modeling

    School of Computational Science and Engineering, Georgia Institute of Technology, 756 West Peachtree Street Northwest, Atlanta, 30308, GA, USA · Environmental Science Division, Argonne National Laboratory, 9700 S Cass Ave, Lemont, 60439, IL, USA

  8. Neural Surrogate Forward Modelling For Electrocardiology Without Explicit Intracellular Conductivity Tensor

    May 13, 2026Shaheim Ogbomo-Harmitt, Cesare Magnetti, Jakub Grzelak +1Neural Surrogate ModelingElectrocardiography

    King’s College London, Floor 3, Lambeth Wing St Thomas’ Hospital Westminster Bridge Road, London, SE1 7EH · Floor 3, Lambeth Wing St Thomas’ Hospital Westminster Bridge Road, London, SE1 7EH · PhysicsX, 1 Leonard Circus, London EC2A 4DQ

  9. Local Inverse Geometry Can Be Amortized

    May 13, 2026Aaditya L. KachhadiyaNeural Surrogate ModelingInference-Time Optimization

    Independent Researcher Surat, India

  10. StampFormer: A Physics-Guided Material-Geometry-Coupled Multimodal Model for Rapid Prediction of Physical Fields in Sheet Metal Stamping

    May 13, 2026Jiajie Luo, Mohamed Mohamed, Osama Hassan +8Neural Surrogate ModelingSurrogate Modeling

  11. Keeping Score: Adaptive, Tuning-Free Loss Weighting for Score-Augmented Neural Ratio Estimation

    May 12, 2026Alexander Shen, Mikael KuuselaNeural Surrogate ModelingSimulation-Based Inference

    Department of Statistics and Data Science Carnegie Mellon University Pittsburgh, PA 15213

  12. When Does Equivariance Help? Canonical Alignment in Neural Fluid Surrogates

    May 12, 2026Patryk Rygiel, Julian Suk, Kak Khee Yeung +2Neural Surrogate ModelingEquivariant Neural Networks

    Department of Applied Mathematics Technical Medical Centre Cardiovascular Health Technology Centre University of Twente · Department of Computer Science Munich Center for Machine Learning Technical University of Munich · Department of Surgery Amsterdam UMC, Location University of Amsterdam Atherosclerosis & Aortic diseases Amsterdam Cardiovascular Sciences

  13. Crash Assessment via Mesh-Based Graph Neural Networks and Physics-Aware Attention

    May 12, 2026Gabriel Curtosi, Carlos Manuel Ruiz Ruiz, Fabiola Cavaliere +1Neural Surrogate ModelingGraph Neural Networks

    SEAT S.A., Barcelona, Spain · IDIADA Automotive Technology S.A., Santa Oliva, Spain

  14. Neural Statistical Functions

    May 11, 2026Daniel Xu, Yuxin Xie, Minghao Guo +2Neural Surrogate ModelingEfficient Neural Network Inference

    Columbia University · MIT CSAIL

  15. From Regression to Inference: Meta-Learning Predictors for Neural Architecture Search

    May 10, 2026Liping Deng, MingQing XiaoNeural Surrogate ModelingMeta-Learning

    Department of Mathematics University of California, Riverside Riverside, CA 92507 USA · School of Mathematical and Statistical Sciences Southern Illinois University Carbondale Carbondale, IL 62901 USA

  16. M3^3: Reframing Training Measures for Discretized Physical Simulations

    May 9, 2026Yuan Mei, Xingyu Song, Xiaowen Song +1Neural Surrogate ModelingAdaptive Sampling

    1Zhejiang University · *Visiting student at The University of Tokyo from Zhejiang University. · 2The University of Tokyo

  17. Inpainting physics: self-supervised learning for context-driven fluid simulation

    May 9, 2026Jonas Weidner, Yeray Martin-Ruisanchez, Daniel Rueckert +2Neural Surrogate ModelingSelf-Supervised Learning

    AI for Image-Guided Diagnosis and Therapy, Technical University of Munich · Munich Center for Machine Learning (MCML) · AI in Healthcare and Medicine, Technical University of Munich +1

  18. Neural Operators as Efficient Function Interpolators

    May 8, 2026Vasilis Niarchos, Angelos Sirbu, Sokratis TrifinopoulosNeural Surrogate ModelingFourier Neural Operator

    Department of Physics, CCTP and ITCP, University of Crete, 71303, Greece · Theoretical Physics Department, CERN, Geneva, Switzerland · Physik-Institut, Universität Zürich, 8057 Zürich, Switzerland

  19. GNN for Structural Displacement Prediction

    May 8, 2026Hung-Fu Chang, Tzu-Kang Lin, Yung-Li ChengNeural Surrogate ModelingGraph Neural Networks

    R. B. Annis School of Engineering University of Indianapolis Indianapolis United States · Department of Civil Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan

  20. CarCrashNet: A Large-Scale Dataset and Hierarchical Neural Solver for Data-Driven Structural Crash Simulation

    May 8, 2026Mohamed Elrefaie, Dule Shu, Matthew Klenk +1Neural Surrogate ModelingStructural Mechanics

    Department of Mechanical Engineering MIT Cambridge, MA, USA · Future Product Innovation Toyota Research Institute Los Altos, CA, USA

  21. Physics-Based Flow Matching for Full-Field Prediction of Silicon Photonic Devices

    May 7, 2026Joseph Quaratiello, Anthony RizzoNeural Surrogate ModelingPhysics-Informed ML

    Thayer School of Engineering, Dartmouth College, Hanover, NH 03755

  22. BRICKS: Compositional Neural Markov Kernels for Zero-Shot Radiation-Matter Simulation

    May 7, 2026Richard Hildebrandt, Evangelos Kourlitis, Baran Hashemi +7Neural Surrogate ModelingRiemannian Flow Matching

    Technical University of Munich · Max-Planck Institute for Mathematics in the Sciences, Leipzig, Germany · SLAC National Accelerator Laboratory +3

  23. Geometric Kolmogorov--Arnold Network (GeoKAN)

    May 7, 2026Abhijit Sen, Bikram Keshari Parida, Giridas Maiti +2Neural Surrogate ModelingMetric Learning

    Department of Physics and Engineering Physics, Tulane University, New Orleans, Louisiana 70118, USA. · Institute of Applied Geosciences, Karlsruhe Institute of Technology, Karlsruhe 76131, Germany.

  24. Hierarchical Multi-Fidelity Learning for Predicting Three-Dimensional Flame Wrinkling and Turbulent Burning Velocity

    May 6, 2026Saghar Zolfaghari, Yu Xie, Junfeng Yang +1Neural Surrogate ModelingMultifidelity Modeling

    Department of Mechanical and Industrial Engineering, Northeastern University, Boston, MA 02115, USA · School of Mechanical Engineering, University of Leeds, Leeds, UK

  25. Full-chip CMP modelling based on Fully Convolutional Network leveraging White Light Interferometry

    May 6, 2026Jules Exbrayat, Renan Bouis, Elie Sezestre +4Neural Surrogate ModelingSemiconductor Manufacturing

    Univ. Grenoble Alpes, CEA, Leti, F-38000 Grenoble, France

  26. Reduced-order Neural Modeling with Differentiable Simulation for High-Detail Tactile Perception

    May 6, 2026Yuhu Guo, Zhikai Shen, Jiasheng Qu +4Neural Surrogate ModelingMaterial Point Method

    The University of Manchester, UK · The Chinese University of Hong Kong, Hong Kong SAR, China · University of Leeds, UK +1

  27. Counter-Dyna: Data-Efficient RL-Based HVAC Control using Counterfactual Building Models

    May 6, 2026Jan Marco Ruiz de Vargas, Fabian Raisch, Zoltan Nagy +2Neural Surrogate ModelingBuilding Energy Management

    Technical University of Munich Munich, Germany · Technical University of Applied Sciences Rosenheim Rosenheim, Germany · Eindhoven University of Technology Eindhoven, Netherlands +1

  28. Geometry-Aware Neural Optimizer for Shape Optimization and Inversion

    May 6, 2026Guoze Sun, Tianya Miao, Haoyang Huang +4Neural Surrogate ModelingGeometric Representation Learning

    Gaoling School of Artificial Intelligence, Renmin University of China

  29. Capabilities of Auto-encoders and Principal Component Analysis of the Reduction of Microstructural Images; Application on the Acceleration of Phase-Field Simulations

    May 5, 2026Seifallah Fetni, Thinh Quy Duc Pham, Truong Vinh Hoang +4Neural Surrogate ModelingAutoencoders

    University of Liège, UEE Research Unit, MSM division, allée de la Découverte, 9 B52/3, B 4000 Liège, Belgium · Chair of Mathematics for Uncertainty Quantification, RWTH-Aachen University, 52056 Aachen, Germany · Institute of Strategy Development, Thu Dau Mot University, 75100 Binh Duong Province, Viet Nam

  30. Model synthesis and identifiability analysis of stiff chemical reaction systems with inVAErt networks

    May 5, 2026Sreejata Dey, Guoxiang Grayson Tong, Jonathan F. MacArt +1Neural Surrogate ModelingParameter Identifiability

    Department of Applied and Computational Mathematics and Statistics, University of Notre Dame · Department of Pediatrics, Stanford University · Department of Aerospace and Mechanical Engineering, University of Notre Dame