摘要
针对无资料区域山洪灾害临界雨量计算的难题,以山东省五莲县45个山丘区小流域沿河村落为研究对象,开展基于机器学习的山洪灾害临界雨量计算模型研究;基于水文水力学法结合现场调研确定各村落成灾水位及临界流量,通过水文模型计算产汇流得到洪水过程,采用试算法计算临界雨量;选取水文、下垫面、沿河村落等相关特征参数及临界雨量计算结果作为训练参数,构建基于极端梯度提升算法的不同预警时段临界雨量预估模型,并采用平均绝对误差和决定系数进行模型精度评估。结果表明:该模型计算的各预警时段临界雨量的平均绝对误差分别为4.56、 6.68、 7.11,决定系数分别为0.955、 0.967、 0.973,预测精度较高,能够满足无资料地区山洪预警工作的应用需求。
Addressing the challenge of calculating critical rainfall for flash floods in areas without data,a study was con-ducted on 45 small watersheds in mountainous and hilly regions along rivers in Wulian County,Shandong Province,to develop a machine learning-based model for calculating critical rainfall for flash floods.The disaster-causing water levels and critical discharges for each village were determined through a combination of hydrological and hydraulic methods along with on-site investigations.Flood processes were then derived through runoff production and concentration calculations using a hydrological model.The critical rainfall was calculated using a trial and error method.Relevant characteristic para-meters such as hydrological data,underlying surface conditions,and villages along the rivers,along with the calculated critical rainfall results,were selected as training parameters.Based on the extreme gradient boosting algorithm,different prediction models for critical rainfall during different warning periods were constructed.The accuracy of these models was evaluated using the mean absolute error and determination coefficient.The results show that the average absolute errors of the critical rainfall calculated by this model for each warning period are 4.56,6.68,and 7.11,respectively,while the determination coefficients are 0.955,0.967,and 0.973,respectively.The model exhibits high prediction accuracy,meeting the application requirements for flash flood warning in areas without data.
作者
李福晨
桑国庆
孙元森
LI Fuchen;SANG Guoqing;SUN Yuansen(School of Water Conservancy and Environment,University of Jinan,Jinan 250022,Shandong,China;Donggang District River Lake Management and Protection Center of Rizhao City,Rizhao 276800,Shandong,China)
出处
《济南大学学报（自然科学版）》
CAS
北大核心
2024年第4期391-398,共8页
Journal of University of Jinan(Science and Technology)
基金
山东省自然科学基金项目(ZR2020ME249)。
关键词
山洪灾害
临界雨量
极端梯度提升算法
预警指标
五莲县
mountain flood disaster
critical rainfall
extreme gradient boosting algrithm
warning index
Wulian County
