Improvements to short-term weather prediction with recurrent-convolutional networks

TL;DR

This paper enhances short-term weather prediction models using recurrent-convolutional networks by implementing a shallower architecture, adopting AdaBelief optimizer, improving variable handling, and ensembling, leading to better accuracy and uncertainty modeling.

Contribution

The paper introduces a shallower model variant, optimizer improvements, and ensembling techniques to advance weather prediction accuracy over previous models.

Findings

Model ensembling significantly improved results.

Increased training data led to better predictions.

Qualitative results show effective motion prediction over time.

Abstract

The Weather4cast 2021 competition gave the participants a task of predicting the time evolution of two-dimensional fields of satellite-based meteorological data. This paper describes the author's efforts, after initial success in the first stage of the competition, to improve the model further in the second stage. The improvements consisted of a shallower model variant that is competitive against the deeper version, adoption of the AdaBelief optimizer, improved handling of one of the predicted variables where the training set was found not to represent the validation set well, and ensembling multiple models to improve the results further. The largest quantitative improvements to the competition metrics can be attributed to the increased amount of training data available in the second stage of the competition, followed by the effects of model ensembling. Qualitative results show that the model can predict the time evolution of the fields, including the motion of the fields over time, starting with sharp predictions for the immediate future and blurring of the outputs in later frames to account for the increased uncertainty.