Deeplearning-based approach to improving numerical weather forecasts

Abstract

This paper briefly describes the history of numerical weather prediction development. The difficulties, which occur in the modelling of atmospheric processes, their nature and possible ways of their mitigation, are described. It also indicates alternative methods of improving the quality of meteorological forecasts. A brief history of deep learning and possible ways of its application to meteorological problems are given. Then, the paper describes the format used to store the 2m temperature forecasts of the COSMO numerical regional model. The proposed neural network architecture enables correcting the forecast errors of the numerical model. We conducted the experiments on the data of eight meteorological stations of the Kyiv region, so we obtained eight trained neural network models. The results showed that the proposed architecture enables obtaining better-quality forecasts in more than 50% of cases. Root-mean-square errors of the resulting forecasts decreased, and it is a widespread skill-score of improved-quality forecasts in meteorological science.