Improving Tropical Cyclone Precipitation Forecasting With Deep Learning and Satellite Image Sequencing

• Published in: Journal of geophysical research. Machine learning and computation Vol. 1; no. 2
• Main Authors: Yang, Nan, Wang, Chong, Li, Xiaofeng
• Format: Journal Article
• Language: English
• Published: 01.06.2024
• Subjects: deep learning; precipitation; remote sensing; satellite image
• ISSN: 2993-5210; 2993-5210
• DOI: 10.1029/2024JH000175

Precipitation forecasting in tropical cyclones (TC) is vital for warning systems and disaster management. Artificial intelligence (AI)‐based methods show promise in this domain. Here, we investigate two aspects of AI forecasting for TC precipitation: modeling satellite image sequencing and analyzing predictability. To the former, using the Global Precipitation Measurement, we establish a high‐accuracy regional and intensity forecasting method. Through an analysis of precipitation patterns and intensities, we have demonstrated the effectiveness, reliability, and robustness of forecasting TC precipitation. To the latter, we conduct predictability research, which covers different intensity categories and landfall versus non‐landfall TC precipitation. The conclusions are: (a) TC precipitation varies regionally with predictability differences among intensity categories; (b) Forecasting landfalling TC precipitation is less challenging than non‐landfalling, considering TC intensity and paths. The proposed method also demonstrates strong forecasting capabilities in handling extreme and accumulated precipitation within 0–120 min, achieving an accuracy rate of 87%. Plain Language Summary Tropical cyclones (TC) are commonly known for their strong winds, but the true dangers lie in associated rainfall and resulting floods. With a warming atmosphere due to global climate change, tropical cyclone precipitation is expected to rise. Accurate forecasts of where and how intense these TCs will produce precipitation become crucial. However, existing methods often struggle to meet this demand. Our new method, the Tropical Cyclone Precipitation Forecasting Model (TCPF), uses satellite image sequencing to forecast TC precipitation accurately within 0–120 min of a cyclone, even in extreme situations. By analyzing TCs by intensity and whether they make landfall, our predictability research enhances the understanding of TC precipitation, providing intelligent insights for improved forecasting models. Key Points We develop a tropical cyclone precipitation forecasting model (TCPF) using satellite image sequencing from Global Precipitation Measurement TCPF forecasts TC precipitation accurately within 0–120 min, including extreme and accumulated precipitation The research gives the predictability in different intensity categories and landfall versus non‐landfall TC precipitation