Version 1
: Received: 19 August 2024 / Approved: 19 August 2024 / Online: 19 August 2024 (10:03:11 CEST)
How to cite:
Liu, N.; Jiang, J.; Mao, D.; Fang, M.; Li, Y.; Han, B.; Ren, S. Method of AI-Based Precipitation Estimation by Using FY-4B Satellite Data. Preprints2024, 2024081289. https://doi.org/10.20944/preprints202408.1289.v1
Liu, N.; Jiang, J.; Mao, D.; Fang, M.; Li, Y.; Han, B.; Ren, S. Method of AI-Based Precipitation Estimation by Using FY-4B Satellite Data. Preprints 2024, 2024081289. https://doi.org/10.20944/preprints202408.1289.v1
Liu, N.; Jiang, J.; Mao, D.; Fang, M.; Li, Y.; Han, B.; Ren, S. Method of AI-Based Precipitation Estimation by Using FY-4B Satellite Data. Preprints2024, 2024081289. https://doi.org/10.20944/preprints202408.1289.v1
APA Style
Liu, N., Jiang, J., Mao, D., Fang, M., Li, Y., Han, B., & Ren, S. (2024). Method of AI-Based Precipitation Estimation by Using FY-4B Satellite Data. Preprints. https://doi.org/10.20944/preprints202408.1289.v1
Chicago/Turabian Style
Liu, N., Bowei Han and Suling Ren. 2024 "Method of AI-Based Precipitation Estimation by Using FY-4B Satellite Data" Preprints. https://doi.org/10.20944/preprints202408.1289.v1
Abstract
A smart precipitation estimation method based on FY-4B meteorological satellite data (FY-4B_AI) is proposed in this paper. This method spatiotemporally matches 125 features derived from multi-temporal and multi-channels of FY-4B satellite data with the precipitation at stations. Then a precipitation model using the Light Gradient Boosting Machine algorithm is constructed. Comparative results between FY-4B_AI and GPM/IMERG-L products for over 450 million station cases throughout 2023 shows that: 1) FY-4B_AI is superior to GPM IMERG-L in the average absolute error, root mean square error, relative error, correlation coefficient, probability of detection and critical success index. While in the mean error and false alarm rate, FY-4B_AI is slightly inferior to GPM/IMERG-L. 2) Evaluation of strong weather event applications reveals that both FY-4B_AI and GPM/IMERG-L can accurately represent the spatial distribution characteristics of precipitation, no matter in the southeast humid region or the northwest dry region. Notably, FY-4B_AI, due to its higher spatiotemporal resolution, provides a more detailed distribution of precipitation.
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
