CLGAN: a generative adversarial network (GAN)-based video prediction model for precipitation nowcasting

• Published in: Geoscientific Model Development Vol. 16; no. 10; pp. 2737 - 2752
• Main Authors: Ji, Yan, Gong, Bing, Langguth, Michael, Mozaffari, Amirpasha, Zhi, Xiefei
• Format: Journal Article
• Language: English
• Published: Katlenburg-Lindau Copernicus GmbH 23.05.2023; Copernicus Publications
• Subjects: Algorithms; Analysis; Architecture; Artificial neural networks; Coders; Competitors; Datasets; Decision making; Deep learning; Early warning systems; Generative adversarial networks; Heavy precipitation; Liquors; Long short-term memory; Modelling; Neural networks; Nowcasting; Optical flow (image analysis); Precipitation; Precipitation (Meteorology); Precipitation patterns; Prediction models; Predictions; Recurrent neural networks; Sensitivity analysis; Warning systems; Weather forecasting
• ISSN: 1991-9603; 1991-959X; 1991-962X; 1991-9603; 1991-962X
• DOI: 10.5194/gmd-16-2737-2023

The prediction of precipitation patterns up to 2 h ahead, also known as precipitation nowcasting, at high spatiotemporal resolutions is of great relevance in weather-dependent decision-making and early warning systems. In this study, we are aiming to provide an efficient and easy-to-understand deep neural network – CLGAN (convolutional long short-term memory generative adversarial network) – to improve the nowcasting skills of heavy precipitation events. The model constitutes a generative adversarial network (GAN) architecture, whose generator is built upon a u-shaped encoder–decoder network (U-Net) and is equipped with recurrent long short-term memory (LSTM) cells to capture spatiotemporal features. The optical flow model DenseRotation and the competitive video prediction models ConvLSTM (convolutional LSTM) and PredRNN-v2 (predictive recurrent neural network version 2) are used as the competitors. A series of evaluation metrics, including the root mean square error, the critical success index, the fractions skill score, and object-based diagnostic evaluation, are utilized for a comprehensive comparison against competing baseline models. We show that CLGAN outperforms the competitors in terms of scores for dichotomous events and object-based diagnostics. A sensitivity analysis on the weight of the GAN component indicates that the GAN-based architecture helps to capture heavy precipitation events. The results encourage future work based on the proposed CLGAN architecture to improve the precipitation nowcasting and early warning systems.