A deep learning-based probabilistic approach to flash flood warnings in mountainous catchments

被引：0
作者：
Zhao, Yuting [1 ]
Wu, Xuemei [1 ]
Zhang, Wenjiang [1 ]
Lan, Ping [1 ]
Qin, Guanghua [1 ]
Li, Xiaodong [1 ]
Li, Hongxia [1 ]
机构：
[1] Sichuan Univ, Coll Water Resource & Hydropower, State Key Lab Hydraul & Mt River Engn, Chengdu 610065, Peoples R China
来源：
JOURNAL OF HYDROLOGY | 2025年 / 652卷
关键词：
Flash flood warning; Probabilistic threshold optimization; Probabilistic method; Hybrid deep learning model; RAINFALL THRESHOLDS; PREDICTION; RUNOFF; MODEL; FORECASTS; SUPPORT; INDEX; BASIN; RISK;
D O I：
10.1016/j.jhydrol.2025.132677
中图分类号：
TU [建筑科学];
学科分类号：
0813 ;
摘要：
Advanced warning of flash flooding plays a vital role in mitigating risk. Established warning models focus on deterministic indicators and do not consider the probability of flash flood occurrences. This study proposed a probabilistic framework based on CNN-LSTM-MultiHead-Attention (CLMA) by considering the threshold optimization for the flash flooding warnings, and compared it with a deterministic method based on hydrological modeling. In addition to the pivotal factor of rainfall, the proposed model also incorporated antecedent precipitation index (API) and rainfall pattern (RP) as input factors to explore the hidden patterns of flash flood occurrences. The results show that the proposed method gave more informative results than the deterministic method by additionally generating hourly probability values. This greatly reduced false and missing alarms and enabled warnings to be issued average 1-3 h in advance. Meanwhile, incorporating API and RP data into the CLMA model enhanced its ability to forecast flash flooding, with API having a greater effect than RP. Moreover, probabilistic threshold optimization using the Best_DIFF criterion improved the CLMA model, decreasing the Euclidean Distance (ED) from 0.12 to 0.05 and increasing the Critical Successful Index (CSI) from 0.54 to 0.83. This study demonstrates that deep learning has the potential to be applied within a probabilistic framework for the flash flood forecasting, which can effectively assess risk information and support early decision-making to issue warnings and flood control actions.
引用
收藏
页数：14
相关论文
共 87 条
[1]  
Abbaszadeh Shahri A., Shan C., Larsson S., A Novel Approach to Uncertainty Quantification in Groundwater Table Modeling by Automated Predictive Deep Learning, Nat. Resour. Res., 31, 3, pp. 1351-1373, (2022)
[2]  
Abdar M., Et al., A review of uncertainty quantification in deep learning: Techniques, applications and challenges, Inf. Fusion, 76, pp. 243-297, (2021)
[3]  
Anctil F., Michel C., Perrin C., Andreassian V., A soil moisture index as an auxiliary ANN input for stream flow forecasting, J. Hydrol., 286, 1-4, pp. 155-167, (2004)
[4]  
Arnal L., Et al., Willingness-to-pay for a probabilistic flood forecast: a risk-based decision-making game, Hydrol. Earth Syst. Sci., 20, 8, pp. 3109-3128, (2016)
[5]  
Bai T., Tahmasebi P., Graph neural network for groundwater level forecasting, J. Hydrol., 616, (2023)
[6]  
Buizza R., The value of probabilistic prediction, Atmos. Sci. Lett., 9, 2, pp. 36-42, (2008)
[7]  
Carpenter T.M., Sperfslage J.A., Georgakakos K.P., Sweeney T., Fread D.L., National threshold runoff estimation utilizing GIS in support of operational flash flood warning systems, J. Hydrol., 224, 1-2, pp. 21-24, (1999)
[8]  
Choubin B., Et al., An ensemble prediction of flood susceptibility using multivariate discriminant analysis, classification and regression trees, and support vector machines, Sci. Total Environ., 651, pp. 2087-2096, (2019)
[9]  
Chowdhury M.E., Et al., An efficient flash flood forecasting system for the un-gaged Meghna basin using open source platform Delft-FEWS, Environ. Model. Softw., 161, (2023)
[10]  
Cui Y., Jia M., Lin T.Y., Song Y., Belongie S., Class-Balanced Loss Based on Effective Number of Samples, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9260-9269, (2019)
123456789