Precipitation Nowcasting using CNN-RNN - Use case: North of Algeria

Hayat HACHEMI, Leila Hamdad, Oussama DOUBA

Research Square · 20 March 2023

In one sentence. CNN-RNN models predict northeast Algeria precipitation from synoptic station data and NWP outputs, showing gains over NWP-based prediction.

Abstract

Abstract Precipitation nowcasting is very important to secure individuals and property against adverse events that may be triggered, as well as to optimize the management of water resources and so-called weather-sensitive economic activities. Achieving effective temporal and spatial nowcasting resolution poses additional challenges to the meteorological community due to the chaotic dynamics that characterize the atmosphere as well as the spatio-temporal variability of this phenomenon. In this work, we aim to use deep learning architectures as Convolutional Neural Network or/and Recurrent Neural Network for the prediction of precipitation to better capture the spatio-temporal variability of meteorological data which are complex. We are particularly interested in rainfall data from northeastern Algeria, where the previously prediction was based on Numerical Weather Prediction. Two types of meteorological data will be used. Firstly, we predict precipitations on synoptic data and secondly, we predict precipitation using synoptic data and previous numerical predicted data obtained by Numerical Weather Prediction. The results were evaluated according to several metrics and a comparison between different approaches was conducted showing the effectiveness of Deep Learning in this field.

Labels

Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.