Benchmarking neural surrogates on realistic spatiotemporal multiphysics flows

• URL: http://arxiv.org/abs/2512.18595v1
• Date: Sun, 21 Dec 2025 05:04:13 GMT
• Title: Benchmarking neural surrogates on realistic spatiotemporal multiphysics flows
• Authors: Runze Mao, Rui Zhang, Xuan Bai, Tianhao Wu, Teng Zhang, Zhenyi Chen, Minqi Lin, Bocheng Zeng, Yangchen Xu, Yingxuan Xiang, Haoze Zhang, Shubham Goswami, Pierre A. Dawe, Yifan Xu, Zhenhua An, Mengtao Yan, Xiaoyi Lu, Yi Wang, Rongbo Bai, Haobu Gao, Xiaohang Fang, Han Li, Hao Sun, Zhi X. Chen,
• Abstract summary: We present REALM (REalistic AI Learning for Multiphysics), a rigorous benchmarking framework designed to test neural surrogates on challenging, application-driven reactive flows.<n>We benchmark over a dozen representative surrogate model families, including spectral operators, convolutional models, Transformers, pointwise operators, and graph/mesh networks.<n>We identify three robust trends: (i) a scaling barrier governed jointly by dimensionality, stiffness, and mesh irregularity, leading to rapidly growing rollout errors; (ii) performance primarily controlled by architectural inductive biases rather than parameter count; and (iii) a persistent gap between nominal accuracy metrics and physically
• Score: 18.240532888032394
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Predicting multiphysics dynamics is computationally expensive and challenging due to the severe coupling of multi-scale, heterogeneous physical processes. While neural surrogates promise a paradigm shift, the field currently suffers from an "illusion of mastery", as repeatedly emphasized in top-tier commentaries: existing evaluations overly rely on simplified, low-dimensional proxies, which fail to expose the models' inherent fragility in realistic regimes. To bridge this critical gap, we present REALM (REalistic AI Learning for Multiphysics), a rigorous benchmarking framework designed to test neural surrogates on challenging, application-driven reactive flows. REALM features 11 high-fidelity datasets spanning from canonical multiphysics problems to complex propulsion and fire safety scenarios, alongside a standardized end-to-end training and evaluation protocol that incorporates multiphysics-aware preprocessing and a robust rollout strategy. Using this framework, we systematically benchmark over a dozen representative surrogate model families, including spectral operators, convolutional models, Transformers, pointwise operators, and graph/mesh networks, and identify three robust trends: (i) a scaling barrier governed jointly by dimensionality, stiffness, and mesh irregularity, leading to rapidly growing rollout errors; (ii) performance primarily controlled by architectural inductive biases rather than parameter count; and (iii) a persistent gap between nominal accuracy metrics and physically trustworthy behavior, where models with high correlations still miss key transient structures and integral quantities. Taken together, REALM exposes the limits of current neural surrogates on realistic multiphysics flows and offers a rigorous testbed to drive the development of next-generation physics-aware architectures.

Related papers

• PhysicsAgentABM: Physics-Guided Generative Agent-Based Modeling [47.029742241618635]
  Large language model (LLM)-based multi-agent systems enable expressive agent reasoning but are expensive to scale and poorly calibrated for timestep-aligned state-transition simulation.<n>We propose PhysicsAgentABM, which shifts inference to behaviorally coherent agent clusters.<n> Experiments across public health, finance, and social sciences show consistent gains in event-time accuracy and calibration over mechanistic, neural, and LLM baselines.
  arXiv  Detail & Related papers  (2026-02-05T18:59:01Z)
• Smooth embeddings in contracting recurrent networks driven by regular dynamics: A synthesis for neural representation [45.88028371034407]
  Recent empirical work has documented topology-preserving latent organization in trained recurrent models.<n>Recent theoretical results in reservoir computing establish conditions under which the synchronization map is an embedding.<n>Our contribution is an integrated framework that assembles generalized synchronization and embedding guarantees for contracting reservoirs.
  arXiv  Detail & Related papers  (2026-01-26T23:10:39Z)
• Unlocking Out-of-Distribution Generalization in Dynamics through Physics-Guided Augmentation [46.40087254928057]
  We present SPARK, a physics-guided quantitative augmentation plugin.<n>Experiments on diverse benchmarks demonstrate that SPARK significantly outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-10-28T09:30:35Z)
• Rethinking the Role of Dynamic Sparse Training for Scalable Deep Reinforcement Learning [58.533203990515034]
  Scaling neural networks has driven breakthrough advances in machine learning, yet this paradigm fails in deep reinforcement learning (DRL)<n>We show that dynamic sparse training strategies provide module-specific benefits that complement the primary scalability foundation established by architectural improvements.<n>We finally distill these insights into Module-Specific Training (MST), a practical framework that exploits the benefits of architectural improvements and demonstrates substantial scalability gains across diverse RL algorithms without algorithmic modifications.
  arXiv  Detail & Related papers  (2025-10-14T03:03:08Z)
• Drift No More? Context Equilibria in Multi-Turn LLM Interactions [58.69551510148673]
  contexts drift is the gradual divergence of a model's outputs from goal-consistent behavior across turns.<n>Unlike single-turn errors, drift unfolds temporally and is poorly captured by static evaluation metrics.<n>We show that multi-turn drift can be understood as a controllable equilibrium phenomenon rather than as inevitable decay.
  arXiv  Detail & Related papers  (2025-10-09T04:48:49Z)
• Models of Heavy-Tailed Mechanistic Universality [62.107333654304014]
  We propose a family of random matrix models to explore attributes that give rise to heavy-tailed behavior in trained neural networks.<n>Under this model, spectral densities with power laws on tails arise through a combination of three independent factors.<n> Implications of our model on other appearances of heavy tails, including neural scaling laws, trajectories, and the five-plus-one phases of neural network training, are discussed.
  arXiv  Detail & Related papers  (2025-06-04T00:55:01Z)
• Time Marching Neural Operator FE Coupling: AI Accelerated Physics Modeling [3.0635300721402228]
  This work introduces a novel hybrid framework that integrates physics-informed deep operator network with FEM through domain decomposition.<n>To address the challenges of dynamic systems, we embed a time stepping scheme directly into the DeepONet, substantially reducing long-term error propagation.<n>Our framework shows accelerated convergence rates (up to 20% improvement in convergence rates compared to conventional FE coupling approaches) while preserving solution fidelity with error margins consistently below 3%.
  arXiv  Detail & Related papers  (2025-04-15T16:54:04Z)
• Implicit Neural Differential Model for Spatiotemporal Dynamics [5.1854032131971195]
  We introduce Im-PiNDiff, a novel implicit physics-integrated neural differentiable solver for stabletemporal dynamics.<n>Inspired by deep equilibrium models, Im-PiNDiff advances the state using implicit fixed-point layers, enabling robust long-term simulation.<n>Im-PiNDiff achieves superior predictive performance, enhanced numerical stability, and substantial reductions in memory and cost.
  arXiv  Detail & Related papers  (2025-04-03T04:07:18Z)
• Model Hemorrhage and the Robustness Limits of Large Language Models [119.46442117681147]
  Large language models (LLMs) demonstrate strong performance across natural language processing tasks, yet undergo significant performance degradation when modified for deployment.<n>We define this phenomenon as model hemorrhage - performance decline caused by parameter alterations and architectural changes.
  arXiv  Detail & Related papers  (2025-03-31T10:16:03Z)
• StFT: Spatio-temporal Fourier Transformer for Long-term Dynamics Prediction [10.64762092324374]
  We propose an autoregressive Spatio-temporal Transformer (FTStours) to learn the system dynamics at a distinct scale.<n>FTStours captures the underlying dynamics across both macro- and micro- spatial scales.<n> Evaluations conducted on three benchmark datasets demonstrate the advantages of our approach over state-of-the-art ML methods.
  arXiv  Detail & Related papers  (2025-03-14T22:04:03Z)
• AttNS: Attention-Inspired Numerical Solving For Limited Data Scenarios [51.94807626839365]
  We propose the attention-inspired numerical solver (AttNS) to solve differential equations due to limited data.<n>AttNS is inspired by the effectiveness of attention modules in Residual Neural Networks (ResNet) in enhancing model generalization and robustness.
  arXiv  Detail & Related papers  (2023-02-05T01:39:21Z)
• Robust Graph Representation Learning via Predictive Coding [46.22695915912123]
  Predictive coding is a message-passing framework initially developed to model information processing in the brain. In this work, we build models that rely on the message-passing rule of predictive coding. We show that the proposed models are comparable to standard ones in terms of performance in both inductive and transductive tasks.
  arXiv  Detail & Related papers  (2022-12-09T03:58:22Z)
• Interfacing Finite Elements with Deep Neural Operators for Fast Multiscale Modeling of Mechanics Problems [4.280301926296439]
  In this work, we explore the idea of multiscale modeling with machine learning and employ DeepONet, a neural operator, as an efficient surrogate of the expensive solver. DeepONet is trained offline using data acquired from the fine solver for learning the underlying and possibly unknown fine-scale dynamics. We present various benchmarks to assess accuracy and speedup, and in particular we develop a coupling algorithm for a time-dependent problem.
  arXiv  Detail & Related papers  (2022-02-25T20:46:08Z)
• Physics-aware, probabilistic model order reduction with guaranteed stability [0.0]
  We propose a generative framework for learning an effective, lower-dimensional, coarse-grained dynamical model. We demonstrate its efficacy and accuracy in multiscale physical systems of particle dynamics.
  arXiv  Detail & Related papers  (2021-01-14T19:16:51Z)
• Action-Conditional Recurrent Kalman Networks For Forward and Inverse Dynamics Learning [17.80270555749689]
  Estimating accurate forward and inverse dynamics models is a crucial component of model-based control for robots. We present two architectures for forward model learning and one for inverse model learning. Both architectures significantly outperform exist-ing model learning frameworks as well as analytical models in terms of prediction performance.
  arXiv  Detail & Related papers  (2020-10-20T11:28:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.