Numerous physics theories are rooted in partial differential equations (PDEs). However, the increasingly intricate physics equations, especially those that lack analytic solutions or closed forms, have impeded the further development of physics. Computationally solving PDEs by classic numerical approaches suffers from the trade-off between accuracy and efficiency and is not applicable to the empirical data generated by unknown latent PDEs. To overcome this challenge, we present KoopmanLab, an efficient module of the Koopman neural operator family, for learning PDEs without analytic solutions or closed forms. Our module consists of multiple variants of the Koopman neural operator (KNO), a kind of mesh-independent neural-network-based PDE solvers developed following dynamic system theory. The compact variants of KNO can accurately solve PDEs with small model sizes while the large variants of KNO are more competitive in predicting highly complicated dynamic systems govern by unknown, high-dimensional, and non-linear PDEs. All variants are validated by mesh-independent and long-term prediction experiments implemented on representative PDEs (e.g., the Navier-Stokes equation and the Bateman-Burgers equation in fluid mechanics) and ERA5 (i.e., one of the largest high-resolution global-scale climate data sets in earth physics). These demonstrations suggest the potential of KoopmanLab to be a fundamental tool in diverse physics studies related to equations or dynamic systems.
翻译:大量物理理论植根于部分差异方程式(PDEs)中。然而,日益复杂的物理方程式,特别是那些缺乏分析解决方案或封闭形式的物理方程式,阻碍了物理的进一步发展。通过经典数字方法计算解决PDE的做法,在精确度和效率之间取舍,不适用于未知潜在PDEs产生的实验数据。为了克服这一挑战,我们介绍了Koopman神经操作员大家庭的一个高效模块KoopmanLab,这是一个高效的模块,用于学习PDEs,而没有分析解决方案或封闭形式。我们的模块由Koopman神经操作员(KNO)的多种变体组成,这是根据动态系统理论开发的一种基于超视离线神经网络的PDE解决方案。KNO的简单变体可以精确地用小的模型大小解决PDEs。而KNO的大型变体在预测以未知、高维度和非线性PDEman PDEs,所有变体都是由具有代表性的光度和长期预测的Koopman神经操作器操作器(在具有代表性的PDES-S-Cal-Cal-Cal-Calliumal-S-Cal-Cal-Cal-Cal-Cal-Cal-Cal-Cal-Cal-IG-S-IG-S-S-IG-IG-IG-S-S-S-S-S-IG-I 和E-I-S-S-S-S-S-S-S-S-S-IL-IL-S-S-S-S-ID-ID-IG-IG-ID-IG-ID-ID-S-C-I-ID-ID-ID-ID-ID-S-S-ID-ID-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-