Physics-informed generative neural network: an application to troposphere temperature prediction

Abstract

The troposphere is one of the atmospheric layers where most weather phenomena occur. Temperature variations in the troposphere, especially at 500 hPa, a typical level of the middle troposphere, are significant indicators of future weather changes. Numerical weather prediction is effective for temperature prediction, but its computational complexity hinders a timely response. This paper proposes a novel temperature prediction approach in framework ofphysics-informed deep learning. The new model, called PGnet, builds upon a generative neural network with a mask matrix. The mask is designed to distinguish the low-quality predicted regions generated by the first physical stage. The generative neural network takes the mask as prior for the second-stage refined predictions. A mask-loss and a jump pattern strategy are developed to train the generative neural network without accumulating errors during making time-series predictions. Experiments on ERA5 demonstrate that PGnet can generate more refined temperature predictions than the state-of-the-art.

References in corpus (8)

• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
• LSTM: A Search Space Odyssey
• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Solving high-dimensional partial differential equations using deep learning
• Explainable Machine Learning for Scientific Insights and Discoveries
• PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network
• Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge
• Data-driven discovery of PDEs in complex datasets

Cited by in corpus (2)

• Random matrix analysis of deep neural network weight matrices
• Boundary between noise and information applied to filtering neural network weight matrices