arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.09795cs.LGcs.NAmath.NA
收藏

DeltaPhi:面向数据受限PDE求解中神经算子的物理状态残差学习

DeltaPhi: Physical States Residual Learning for Neural Operators in Data-Limited PDE Solving

College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院);The State Key Lab of Brain-Machine Intelligence, Zhejiang University(浙江大学脑机智能国家重点实验室)

Xihang Yue, Yi Yang, Linchao Zhu

AI总结:

针对数据驱动PDE求解中高质量训练数据不足的问题,提出架构无关的DeltaPhi框架,通过学习相似物理状态残差实现隐式数据增强,可适配现有神经算子并在多场景下显著提升性能。

摘要:

高质量训练数据的有限可用性是数据驱动偏微分方程(PDE)求解面临的主要障碍,其中昂贵的数据采集与分辨率约束严重影响了神经算子网络学习并泛化底层物理系统的能力。为应对这一挑战,我们提出DeltaPhi——一种全新的学习框架,它将PDE求解任务从学习直接的输入-输出映射,转变为学习相似物理状态之间的残差,这是一种本质上区别于现有方法的神经算子学习思路。该重构通过利用物理系统的固有稳定性实现隐式数据增强,即初始状态越接近,演化轨迹就越接近。DeltaPhi是架构无关的,可无缝集成到现有神经算子中以提升其性能。大量实验表明,该方法在规则与不规则域、不同神经架构、多种训练数据量以及跨分辨率场景等多样物理系统中均取得了一致且显著的提升,证实了其作为数据受限PDE求解中神经算子通用增强方案的有效性。

英文摘要:

The limited availability of high-quality training data poses a major obstacle in data-driven PDE solving, where expensive data collection and resolution constraints severely impact the ability of neural operator networks to learn and generalize the underlying physical system. To address this challenge, we propose DeltaPhi, a novel learning framework that transforms the PDE solving task from learning direct input-output mappings to learning the residuals between similar physical states, a fundamentally different approach to neural operator learning. This reformulation provides implicit data augmentation by exploiting the inherent stability of physical systems where closer initial states lead to closer evolution trajectories. DeltaPhi is architecture-agnostic and can be seamlessly integrated with existing neural operators to enhance their performance. Extensive experiments demonstrate consistent and significant improvements across diverse physical systems including regular and irregular domains, different neural architectures, multiple training data amount, and cross-resolution scenarios, confirming its effectiveness as a general enhancement for neural operators in data-limited PDE solving.

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。

↑