ISSN 1000-0526
CN 11-2282/P
CN 11-2282/P
Progress and Reflections on the Application of Machine Learning Techniques in Flood Forecasting
- Article
- Figures
- Metrics
- Preview PDF
- Reference
- Related
- Cited by
- Materials
Abstract:
Flood forecasting is an effective non engineering measure to reduce flood losses and enhance resilience.And accurate flood forecasting is one of the key technical challenges in the hydrological field. At present, flood forecasting models based on physical mechanisms still have shortcomings in simulation accuracy and efficiency, while forecasting models constructed using deep learning techniques have experienced rapid development.This study comprehensively reviews the principles and characteristics of deep learning models applied in the field of flood forecasting. It summarizes the progress and problems in the application of deep learning models for quantitative and probabilistic flood forecasting. The study also explores the relevance and application prospects of deep learning models in relation to flood physics models, particularly in the parameterization of physical processes, interpretability studies, and error correction of flood forecasting models. It is believed that deep coupling with physical models is the future development direction of deep learning models, which will be an important development paradigm for the time series prediction of flood, and an important research component for realizing the water resource intelligence in the future. Finally, a few thoughts are given on the difficulties of deep learning in flood forecasting, and corresponding solutions are proposed for the current challenges, in order to better explore the application of deep learning technology in the field of flood forecasting.
Keywords:
Project Supported:
Hubei Province Natural Science and Meteorology Innovation and Development Joint Fund Project（2022CFD129；2023AFD094）；Yangtze River Basin Meteorological Open Fund Project(CJLY2022Y06)；Hubei Provincial Meteorological Bureau（2022Y06）；Sponge City Construction Water System Science Hubei Provincial Key Laboratory Open Fund (Wuhan University)
Clc Number:
Mobile website
