Hard Encoding of Physics for Learning Spatiotemporal Dynamics

Abstract

Modeling nonlinear spatiotemporal dynamical systems has primarily relied on partial differential equations (PDEs). However, the explicit formulation of PDEs for many underexplored processes, such as climate systems, biochemical reaction and epidemiology, remains uncertain or partially unknown, where very limited measurement data is yet available. To tackle this challenge, we propose a novel deep learning architecture that forcibly encodes known physics knowledge to facilitate learning in a data-driven manner. The coercive encoding mechanism of physics, which is fundamentally different from the penalty-based physics-informed learning, ensures the network to rigorously obey given physics. Instead of using nonlinear activation functions, we propose a novel elementwise product operation to achieve the nonlinearity of the model. Numerical experiment demonstrates that the resulting physics-encoded learning paradigm possesses remarkable robustness against data noise/scarcity and generalizability compared with some state-of-the-art models for data-driven modeling.

arXiv commentICLR 2021 SimDL Workshop. arXiv admin note: substantial text overlap with arXiv:2106.04781

References in corpus (8)

• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
• PhyGeoNet: Physics-Informed Geometry-Adaptive Convolutional Neural Networks for Solving Parameterized Steady-State PDEs on Irregular Domain
• Modeling the Dynamics of PDE Systems with Physics-Constrained Deep Auto-Regressive Networks
• Understanding and mitigating gradient pathologies in physics-informed neural networks
• Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex
• Multi-level Residual Networks from Dynamical Systems View

Cited by in corpus (2)

• PhyCRNet: Physics-informed Convolutional-Recurrent Network for Solving Spatiotemporal PDEs
• ModalPINN: an extension of Physics-Informed Neural Networks with enforced truncated Fourier decomposition for periodic flow reconstruction using a limited number of imperfect sensors