Abstract:To address the high demand for timely flood forecasting, this paper introduces AI technology in conjunction with physics-based hydrodynamic models. By training on typical heavy rainfall and flood processes, a rapid AI-based method for flood prediction is developed. Initially, a hydrodynamic numerical model for studying the flood processes in the research area is established. Subsequently, this model is used to simulate and compute flood processes under different rainfall scenarios, forming a database of outcomes. Different AI learning methods are then employed to the machine learning for the correlation between key rainfall features and flood processes, validating the reliability of this learning method. This leads to the creation of a rapid simulation and forecasting machine learning model specific to the studied area's flood processes. Finally, inputting forecasted rainfall values allows the application of the machine learning model for fast flood prediction. This paper delineates methodologies and showcases applications for two flood types as urban inundation and watershed flooding.Results demonstrate that the developed AI model can achieve over 300 ~ 400 times acceleration compared to physics-based models with a similar level of accuracy.
[1] 张建云,宋晓猛,王国庆,等.变化环境下城市水文学的发展与挑战——I.城市水文效应[J].水科学进展,2014,25(4):594-605. [2] 张小稳,刘国庆,陈光育,等.城市极端暴雨洪涝灾害风险评估与对策研究[J].中国防汛抗旱,2023,33(8):13-18. [3] 《中国水旱灾害防御公报》编写组.《中国水旱灾害防御公报2022》概要[J].中国防汛抗旱,2023,33(10):78-82. [4] 张建云,舒章康,王鸿杰,等.郑州"7·20"暴雨洪涝几个水文问题的讨论[J].地理学报,2023,78(7):1618-1626. [5] 喻海军,陈小兰,刘昌军,等.郑州中心城区2021年"7·20"特大暴雨洪涝复盘模拟分析[J].中国防汛抗旱,2022,32(5):11-15. [6] 马建明.关于城市洪涝风险防控体系构建的建议——郑州市"7·20"特大暴雨灾害思考[J].中国防汛抗旱,2022,32(4):45-47,71. [7] 张建云,王银堂,贺瑞敏,等.中国城市洪涝问题及成因分析[J].水科学进展,2016,27(4):485-491. [8] 李东来,侯精明,申若竹,等.基于地块概化和路网精细模拟理念的城市雨洪过程分区自适应模型[J].水科学进展,2023,34(2):197-208. [9] 王昕泽,侯精明,王峰,等.城市雨洪内涝三维实景动态模拟表达方法研究[J].中国防汛抗旱,2023,33(10):52-57. [10] 曾照洋,赖成光,王兆礼,等.基于WCA2D与SWMM模型的城市暴雨洪涝快速模拟[J].水科学进展,2020,31(1):29-38. [11] 梅超.城市水文水动力耦合模型及其应用研究[D].北京:中国水利水电科学研究院,2019. [12] 黄国如,陈志威,曾博威.城市洪涝模型及CPU-GPU异构并行计算技术研究进展[J].水利学报,2023,54(6):654-665. [13] 侯精明,张兆安,马利平,等.基于GPU加速技术的非结构流域雨洪数值模型[J].水科学进展,2021,32(4):567-576. [14] 崔震,郭生练,王俊,等.基于混合深度学习模型的洪水过程概率预报研究[J].水利学报,2023,54(8):889-897,909. [15] 刘媛媛,刘业森,郑敬伟,等.BP神经网络和数值模型相结合的城市内涝预测方法研究[J].水利学报,2022,53(3):284-295. [16] LIAO Y X,WANG Z L,CHEN X H,et al.Fast simulation and prediction of urban pluvial floods using a deep convolutional neural network model[J].Journal of Hydrology,2023,624:129945. [17] 侯精明,李桂伊,李国栋,等.高效高精度水动力模型在洪水演进中的应用研究[J].水力发电学报,2018,37(2):96-107. [18] 侯精明,李东来,王小军,等.建筑小区尺度下LID措施前期条件对径流调控效果影响模拟[J].水科学进展,2019,30(1):45-55. [19] 侯精明,王润,李国栋,等.基于动力波法的高效高分辨率城市雨洪过程数值模型[J].水力发电学报,2018,37(3):40-49. [20] HOU J M,Simons F,Mahgoub M,et al.A robust well-balanced model on unstructured grids for shallow water flows with wetting and drying over complex topography[J].Computer Methods in Applied Mechanics and Engineering,2013,257(15):126-149. [21] HOU J M,LIANG Q H,ZHANG H B,et al. An efficient unstructured MUSCL scheme for solving the 2D shallow water equations[J].Environmental Modelling and Software,2015,66:131-152.