用物理约束提升相场模型预测精度，加速材料演化模拟。
Physics-informed neural operator for predictive parametric phase-field modelling
- 将相场方程残差嵌入损失函数，强制学习过程满足物理规律。
- 在腐蚀、凝固等场景中，精度与长期稳定性显著优于传统FNO。
- 适合需要高精度、强泛化能力的材料微结构模拟研究者。
通过相场建模预测材料微观结构和形貌演化计算成本高昂，尤其在高通量参数研究中。尽管傅里叶神经算子（FNO）等神经算子在加速求解参数化偏微分方程方面展现出潜力，但缺乏显式物理约束可能限制其在复杂相场动力学中的泛化能力和长期准确性。本文提出一种物理信息神经算子框架（PF-PINO），用于学习参数化相场偏微分方程。通过将相场控制方程的残差嵌入数据保真度损失函数，训练过程中有效施加物理约束。我们在电化学腐蚀、枝晶晶体凝固和旋节分解等基准问题上验证了PF-PINO性能。结果表明，相较于传统FNO，PF-PINO在精度、泛化能力及长期稳定性方面均有显著提升。该工作为相场建模提供了高效可靠的计算工具，展示了物理信息神经算子在复杂界面演化问题科学机器学习中的巨大潜力。
原文摘要 · Abstract (English)
Predicting the microstructural and morphological evolution of materials through phase-field modelling is computationally intensive, particularly for high-throughput parametric studies. While neural operators such as the Fourier neural operator (FNO) show promise in accelerating the solution of parametric partial differential equations (PDEs), the lack of explicit physical constraints, may limit generalisation and long-term accuracy for complex phase-field dynamics. Here, we develop a physics-informed neural operator framework to learn parametric phase-field PDEs, namely PF-PINO. By embedding the residuals of phase-field governing equations into the data-fidelity loss function, our framework effectively enforces physical constraints during training. We validate PF-PINO against benchmark phase-field problems, including electrochemical corrosion, dendritic crystal solidification, and spinodal decomposition. Our results demonstrate that PF-PINO significantly outperforms conventional FNO in accuracy, generalisation capability, and long-term stability. This work provides a robust and efficient computational tool for phase-field modelling and highlights the potential of physics-informed neural operators to advance scientific machine learning for complex interfacial evolution problems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。