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

TL;DR

This paper introduces PGnet, a physics-informed generative neural network that improves troposphere temperature prediction accuracy and efficiency by refining initial physical model outputs through a mask-based deep learning approach.

Contribution

The paper presents a novel physics-informed generative neural network with a mask mechanism for improved temperature prediction in the troposphere, reducing error accumulation.

Findings

PGnet outperforms state-of-the-art methods in temperature prediction accuracy.

The mask and jump pattern strategies effectively prevent error accumulation.

Experiments on ERA5 data validate the model's refined predictions.

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.