A Novel Flood Classification Method Based on Machine Learning to Improve the Accuracy of Flood Simulation: A Case Study of Xunhe Watershed

被引:0
作者
Cai, Xi [1 ,2 ,3 ]
Zhang, Xiaoxiang [1 ,2 ,3 ]
Liu, Changjun [4 ]
Yang, Yongcheng [1 ,2 ,3 ]
Wang, Zihao [1 ,2 ,3 ]
机构
[1] Hohai Univ, Coll Geog & Remote Sensing, Nanjing 211100, Peoples R China
[2] Jiangsu Prov Engn Res Ctr Watershed Geospatial Int, Nanjing 211100, Peoples R China
[3] Hohai Univ, Ctr Geospatial Intelligence & Watershed Sci CGIWaS, Nanjing 211100, Peoples R China
[4] China Inst Water Resources & Hydropower Res, Res Ctr Flood & Drought Disaster Reduct, Beijing 100038, Peoples R China
基金
国家重点研发计划;
关键词
flood classification; flood simulation; machine learning; spatio-temporal variable source mixed model; Xunhe watershed; MODEL;
D O I
10.3390/w17040489
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Flood disasters pose one of the greatest threats to humanity. Effectively addressing this challenge requires improving the accuracy of flood simulation. Taking Xunhe watershed in Shandong Province as the study area, the Random Forest model was utilized to classify historical flood events within the watershed based on rainfall conditions, such as varying rainfall durations, intensities, and total precipitations. Multiple sets of hydrological model parameters were established to conduct flood classification simulation, reducing the error caused by using a single parameter set for the entire watershed. The results indicate that the Random Forest model can be applied to flood classification simulation in Xunhe watershed. Compared to unclassified simulations, the method proposed in this study leads to an improvement in the Nash coefficient by 0.06 to 0.14, a reduction in the relative error of peak discharge by 3% to 11.24% and a reduction in the relative error of flood volume by 1.46% to 9.44%. The flood classification simulation method proposed in this study has certain applicability in reducing flood simulation errors under different rainfall scenarios and improving accuracy in the watershed, providing new insights for flood control and disaster reduction efforts.
引用
收藏
页数:18
相关论文
共 31 条
  • [1] A new approach for simulating and forecasting the rainfall-runoff process within the next two months
    Alizadeh, Mohamad Javad
    Kavianpour, Mohamad Reza
    Kisi, Ozgur
    Nourani, Vahid
    [J]. JOURNAL OF HYDROLOGY, 2017, 548 : 588 - 597
  • [2] Assimilation of Sentinel 1 and SMAP - based satellite soil moisture retrievals into SWAT hydrological model: the impact of satellite revisit time and product spatial resolution on flood simulations in small basins
    Azimi, Shima
    Dariane, Alireza B.
    Modanesi, Sara
    Bauer-Marschallinger, Bernhard
    Bindlish, Rajat
    Wagner, Wolfgang
    Massari, Christian
    [J]. JOURNAL OF HYDROLOGY, 2020, 581
  • [3] A simple raster-based model for flood inundation simulation
    Bates, PD
    De Roo, APJ
    [J]. JOURNAL OF HYDROLOGY, 2000, 236 (1-2) : 54 - 77
  • [4] Random forests
    Breiman, L
    [J]. MACHINE LEARNING, 2001, 45 (01) : 5 - 32
  • [5] Towards better flood risk management: Assessing flood risk and investigating the potential mechanism based on machine learning models
    Chen, Jialei
    Huang, Guoru
    Chen, Wenjie
    [J]. JOURNAL OF ENVIRONMENTAL MANAGEMENT, 2021, 293
  • [6] Does high risk mean high loss: Evidence from flood disaster in southern China
    Chen, Yangyang
    Li, Jimei
    Chen, An
    [J]. SCIENCE OF THE TOTAL ENVIRONMENT, 2021, 785
  • [7] METHODS AND MERITS OF REGIONAL FLOOD FREQUENCY-ANALYSIS
    CUNNANE, C
    [J]. JOURNAL OF HYDROLOGY, 1988, 100 (1-3) : 269 - 290
  • [8] OPTIMAL USE OF THE SCE-UA GLOBAL OPTIMIZATION METHOD FOR CALIBRATING WATERSHED MODELS
    DUAN, QY
    SOROOSHIAN, S
    GUPTA, VK
    [J]. JOURNAL OF HYDROLOGY, 1994, 158 (3-4) : 265 - 284
  • [9] El Baida M, 2025, WATER RESOUR MANAG, V39, P1149, DOI 10.1007/s11269-024-04015-3
  • [10] Impact of catchment and climate attributes on flood generating processes and their effect on flood statistics
    Fischer, Svenja
    Pahlow, Markus
    Singh, Shailesh Kumar
    [J]. JOURNAL OF HYDROLOGY, 2025, 646