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

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

Blog Article

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 read more 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 of physics-informed deep learning.

The new model, called PGnet, builds upon color touch 7/97 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.