Towards Spatio-Temporal Extrapolation of Phase-Field Simulations with Convolution-Only Neural Networks

arXiv 2601.04510 ↗First posted 8 Jan 2026cs.CE cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Phase-field simulations of liquid metal dealloying (LMD) can capture complex microstructural evolutions but can be prohibitively expensive for large domains and long time horizons. In this paper, we introduce a fully convolutional, conditionally parameterized U-Net surrogate designed to extrapolate far beyond its training data in both space and time. The architecture integrates convolutional self-attention, physically informed padding, and a flood-fill corrector method to maintain accuracy under extreme extrapolation, while conditioning on simulation parameters allows for flexible time-step skipping and adaptation to varying alloy compositions. To remove the need for costly solver-based initialization, we couple the surrogate with a conditional diffusion model that generates synthetic, physically consistent initial conditions. We train our surrogate on simulations generated over small domain sizes and short time spans, but, by taking advantage of the convolutional nature of U-Nets, we are able to run and extrapolate surrogate simulations for longer time horizons than what would be achievable with classic numerical solvers. Across multiple alloy compositions, the framework is able to reproduce the LMD physics accurately. It predicts key quantities of interest and spatial statistics with relative errors typically below 5% in the training regime and under 15% during large-scale, long time-horizon extrapolations. Our framework can also deliver speed-ups of up to 36,000 times, bringing the time to run weeks-long simulations down to a few seconds. This work is a first stepping stone towards high-fidelity extrapolation in both space and time of phase-field simulation for LMD.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 43 of its 109 references that are in the map. First posted on arXiv 8 Jan 2026.

Builds on

43 of 109 references.

References · 43

2017Attention Is All You Needcited by 59,932
2015Deep Residual Learning for Image Recognitioncited by 51,809
2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
2020Denoising Diffusion Probabilistic Modelscited by 20,851
2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
2021Zero-Shot Text-to-Image Generationcited by 4,276
2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,806
2017Non-local Neural Networkscited by 2,290

31 more

2015Variational Inference with Normalizing Flowscited by 2,161
2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 1,965
2018Self-Attention Generative Adversarial Networkscited by 809
2018Which Training Methods for GANs do actually Converge?cited by 672
2016Deep Convolutional Neural Network for Inverse Problems in Imagingcited by 431
2021Neural Operator: Learning Maps Between Function Spacescited by 413
2021U-FNO -- An enhanced Fourier neural operator-based deep-learning model for multiphase flowcited by 292
2015A note on the evaluation of generative modelscited by 291
2018Attention Gated Networks: Learning to Leverage Salient Regions in Medical Imagescited by 271
2021Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformerscited by 237
2023Convolutional Neural Operators for robust and accurate learning of PDEscited by 207
2022FourCastNet: Accelerating Global High-Resolution Weather Forecasting using Adaptive Fourier Neural Operatorscited by 188
2015DeepOrgan: Multi-level Deep Convolutional Networks for Automated Pancreas Segmentationcited by 158
2018Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations of Airfoil Flowscited by 147
2019Prediction of Aerodynamic Flow Fields Using Convolutional Neural Networkscited by 144
2018Survey of multifidelity methods in uncertainty propagation, inference, and optimizationcited by 141
2016The Importance of Skip Connections in Biomedical Image Segmentationcited by 126
2016Mode Regularized Generative Adversarial Networkscited by 123
2021PhyCRNet: Physics-informed Convolutional-Recurrent Network for Solving Spatiotemporal PDEscited by 97
2021Learned Coarse Models for Efficient Turbulence Simulationcited by 90
2022Learning two-phase microstructure evolution using neural operators and autoencoder architecturescited by 72
2017Variational Approaches for Auto-Encoding Generative Adversarial Networkscited by 52
2023Training neural operators to preserve invariant measures of chaotic attractorscited by 43
2023GPLaSDI: Gaussian Process-based Interpretable Latent Space Dynamics Identification through Deep Autoencodercited by 29
2023Rethinking materials simulations: Blending direct numerical simulations with neural operatorscited by 25
2024A Comprehensive Review of Latent Space Dynamics Identification Algorithms for Intrusive and Non-Intrusive Reduced-Order-Modelingcited by 22
2023Real-time Inference and Extrapolation via a Diffusion-inspired Temporal Transformer Operator (DiTTO)cited by 16
2021Effects of boundary conditions in fully convolutional networks for learning spatio-temporal dynamicscited by 14
2024Spatially-Aware Diffusion Models with Cross-Attention for Global Field Reconstruction with Sparse Observationscited by 13
2024Accelerating Phase Field Simulations Through a Hybrid Adaptive Fourier Neural Operator with U-Net Backbonecited by 10
2021How Are Learned Perception-Based Controllers Impacted by the Limits of Robust Control?cited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way