LegONet: 可插拔的结构保持神经算子块用于组合偏微分方程学习
LegONet: Plug-and-Play Structure-Preserving Neural Operator Blocks for Compositional PDE Learning
AI总结:
LegONet通过可插拔的结构保持算子块构建PDE求解器,实现跨PDE和边界条件的稳定求解。
摘要:
已学习的PDE求解器通常被训练为单体代理,用于特定的方程、边界条件和离散化。这使得它们在机制变化时难以重用,并且在长时间滚动时可能限制稳定性。我们介绍了类似积木的算子网络(LegONet),这是一种组合框架,通过可插拔、结构保持的算子块构建PDE求解器,这些块定义在共享的边界适应谱表示上。LegONet将边界处理与机制学习分离,通过构造满足边界条件。它还分离了机制学习与时间积分,使预训练的块可以组装成新的求解器而无需重新训练。我们还推导出一个有限时间误差分解,将块不匹配与分裂误差分开,并为长时间滚动预测提供机制层面的诊断。在十个时间相关的PDE上,LegONet在跨PDE重组和边界重新配置下实现了更稳定的准确闭环滚动。更广泛地说,这种模块化形式表明了一条从任务特定神经求解器到科学计算的可插拔算子库的道路。
英文摘要:
Learned PDE solvers are often trained as monolithic surrogates for a specific equation, boundary condition and discretization. This makes them difficult to reuse when mechanisms change and it can limit stability under long-horizon rollout. We introduce Lego-like Operator Network (LegONet), a compositional framework that builds PDE solvers from plug-and-play, structure-preserving operator blocks defined on shared boundary-adapted spectral representations. LegONet separates boundary handling from mechanism learning, satisfying boundary conditions by construction. It also separates mechanism learning from time integration, enabling pretrained blocks to be assembled into new solvers without retraining. We also derive a finite-horizon error decomposition that separates block mismatch from splitting error and provides mechanism-level diagnostics for long-horizon predictions. Across ten time-dependent PDEs, LegONet delivers accurate closed-loop rollouts with improved stability under cross-PDE recombination and boundary reconfiguration. More broadly, this modular formulation suggests a path from task-specific neural solvers towards plug-and-play operator libraries for scientific computing.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。