Precipitation nowcasting is of great importance for weather forecast users, for activities ranging from outdoor activities and sports competitions to airport traffic management. In contrast to long-term precipitation forecasts which are traditionally obtained from numerical models, precipitation nowcasting needs to be very fast. It is therefore more challenging to obtain because of this time constraint. Recently, many machine learning based methods had been proposed. We propose the use three popular deep learning models (U-net, ConvLSTM and SVG-LP) trained on two-dimensional precipitation maps for precipitation nowcasting. We proposed an algorithm for patch extraction to obtain high resolution precipitation maps. We proposed a loss function to solve the blurry image issue and to reduce the influence of zero value pixels in precipitation maps.
@article{arxiv.2203.13263,
title = {Precipitaion Nowcasting using Deep Neural Network},
author = {Mohamed Chafik Bakkay and Mathieu Serrurier and Valentin Kivachuk Burda and Florian Dupuy and Naty Citlali Cabrera-Gutierrez and Michael Zamo and Maud-Alix Mader and Olivier Mestre and Guillaume Oller and Jean-Christophe Jouhaud and Laurent Terray},
journal= {arXiv preprint arXiv:2203.13263},
year = {2022}
}