
为准确实现山区小流域在极端天气下的短时洪水预报,构建了一种基于物理的分布式水文模型和数据驱动的深度学习模型相结合的组合框架,并引入S2S策略进行模型优化。以7场历史台风降雨数据为初始变量条件,建立GRU、HEC-HMS-GRU和HEC-HMS-GRU-S2S模型进行提前1~3 h洪水预报性能对比分析。结果表明:从预测精度来看,HEC-HMS-GRU-S2S模型和HEC-HMS-GRU模型的预测能力较单一深度学习模型均有所提升,NSE指标分别最高提升57%、23%;从多步时长预测来看,HEC-HMS-GRU-S2S组合模型在保证预测的稳定性和准确性的同时提高了预测的提前期,在3 h提前期的NSE和RMSE指标分别为0.906、31.2;从可靠性评估来看,HEC-HMS-GRU-S2S组合模型能够减少在多步长预测中对峰值流量估计的偏差,改善预测过程中的洪峰高估和滞后现象,洪峰相对误差和峰现时差最低为2%和0 h。HEC-HMS-GRU-S2S组合模型为极端条件下的山区小流域的洪水预报提供了一种新的思路。
原文林,景博慧,唐彦杰,张帅虎,郭进军,胡少伟.基于降雨过程识别的山洪灾害动态预警模式[J].水电能源科学,2024(12).
原文林,赵小棚,杨逸凡,郭进军,胡少伟.山洪灾害危险性评估研究综述[J].水电能源科学,2024(11).
王啸,石朋,瞿思敏,司伟,戈晓斌.基于SWAT与新安江模型场次洪水模拟研究及评估[J].水力发电,2024(10).
胡迎春,陈耀登,高玉芳,彭涛.基于雷达估测降雨及WRF-Hydro模型的典型山洪模拟研究[J].高原气象,2024(01).
崔震,郭生练,王俊,张俊,周研来.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(08).
崔震,郭生练,王俊,王何予,尹家波,巴欢欢.基于GR4J-LSTM混合模型的洪水预报研究[J].人民长江,2022(07).
张振东,罗斌,覃晖,唐海华,周超,冯快乐.风光水互补系统时间序列变量概率预报框架[J].水利学报,2022(08).
殷仕明,徐炜,熊一橙,田远洋,赵思琪,陈思.基于迁移学习的长短时记忆神经网络水文模型[J].水力发电学报,2022(06).
蒋卫威,鱼京善,赤穗良辅,陈基培,姜淇,李卢祎.基于水文水动力耦合模型的山区小流域洪水预报[J].水文,2020(05).
G.R. Arathy Nair,S. Adarsh,Ahmed El Shafie,Ali Najah Ahmed.Enhancing hydrological data completeness: A performance evaluation of various machine learning techniques using probabilistic fusion imputer with neural networks for streamflow data reconstruction[J].Journal of Hydrology,2024.
Liu Binxiao,Tang Qiuhong,Zhao Gang,Gao Liang,Shen Chaopeng,Pan Baoxiang.Physics-Guided Long Short-Term Memory Network for Streamflow and Flood Simulations in the Lancang–Mekong River Basin[J].Water,2022(9).
Zhongrun Xiang,Jun Yan,Ibrahim Demir.A Rainfall‐Runoff Model With LSTM‐Based Sequence‐to‐Sequence Learning[J].Water Resources Research,2020.
Shuai Gao,Yuefei Huang,Shuo Zhang,Jingcheng Han,Guangqian Wang,Meixin Zhang,Qingsheng Lin.Short-term runoff prediction with GRU and LSTM networks without requiring time step optimization during sample generation[J].Journal of Hydrology,2020.
Frederik Kratzert,Daniel Klotz,Claire Brenner,Karsten Schulz,Mathew Herrnegger.Rainfall–runoff modelling using Long Short-Term Memory (LSTM) networks[J].Hydrology and Earth System Sciences,2018.
Jun Yan,Jiaming Jin,Furong Chen,Guo Yu,Hailong Yin,Wenjia Wang.Urban flash flood forecast using support vector machine and numerical simulation[J].Journal of Hydroinformatics,2018.
Chih-Chieh Young,Wen-Cheng Liu,Ming-Chang Wu.A physically based and machine learning hybrid approach for accurate rainfall-runoff modeling during extreme typhoon events[J].Applied Soft Computing,2017.
Fi-John Chang,Pin-An Chen,Ying-Ray Lu,Eric Huang,Kai-Yao Chang.Real-time multi-step-ahead water level forecasting by recurrent neural networks for urban flood control[J].Journal of Hydrology,2014.
Pin-An Chen,Li-Chiu Chang,Fi-John Chang.Reinforced recurrent neural networks for multi-step-ahead flood forecasts[J].Journal of Hydrology,2013.
A.G. Parlos,O.T. Rais,A.F. Atiya.Multi-step-ahead prediction using dynamic recurrent neural networks[J].Neural Networks,2000.
0
Views
186
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621