| 425 | 0 | 29 |
| 下载次数 | 被引频次 | 阅读次数 |
【目的】山洪灾害给人类社会带来严重的经济损失和人员伤亡，因此科学识别、评估山洪灾害风险是亟待解决的科学问题。旨在通过耦合特征选择和随机森林算法提高山洪灾害风险预测的准确性，为灾害预警提供科学依据。【方法】选取17个与山洪灾害发生相关的特征因子，提出了耦合分类递归特征消除法(Classified Recursive Feature Elimination, RFE-class)和随机森林优化算法的特征选择技术，识别山洪灾害风险模拟最优特征组合。【结果】研究结果表明，采用分类递归特征法获得的最佳特征组合可以显著提高随机森林模型的预测性能，ROC(Receiver Operating Characteristic)曲线值达到了94.7%,相比单独使用随机森林算法精度提升了约5%。【结论】福建省山洪灾害高风险区域主要分布在武夷山脉、戴云山和玳瑁山区，涉及面积4.9万km2,影响人口2 700万人口。
Abstract：[Objective]Flash flood disasters cause severe economic losses and casualties to human society, making the scientific identification and assessment of flash flood disaster risk an urgent issue to be addressed. The aim of the study is to improve the accuracy of flash flood risk prediction by coupling feature selection with the Random Forest algorithm, thereby providing a scientific basis for disaster early warning.[Methods]Seventeen feature factors associated with the occurrence of flash flood disasters were selected. A feature selection approach that integrated Classified Recursive Feature Elimination(RFE-class) with a Random Forest optimization algorithm was proposed to identify the optimal feature combination for flash flood risk simulation.[Results]The result showed that the optimal feature combination obtained using the RFE-class method significantly improved the predictive performance of the Random Forest model, achieving a Receiver Operating Characteristic(ROC) curve value of 94.7%, representing an approximately 5% improvement in accuracy compared to using the Random Forest algorithm alone.[Conclusion]In Fujian Province, the high-risk areas for flash flood disasters are primarily distributed in the Wuyi Mountains, Daiyun Mountains, and Daimao Mountain regions, covering an area of approximately 49 000 km2 and affecting 27 million people.
[1] 付潇然，王中根，祁书文，等.应急视域下山洪灾害复盘与应对过程分析：以2022年6场典型事件为例[J].水利水电技术(中英文),2024,55(11):15-25.FU X R,WANG Z G,QI S W,et al.A summary and reflection on the six events of flash flood disasters in 2022 from an emergency management perspective[J].Water Resources and Hydropower Engineering,2024,55(11):15-25.
[2] 王浩，胡春宏，王中根，等.变化环境下我国洪水灾害防御的挑战与对策[J].水利学报，2022,53(6):1-14.WANG H,HU C H,WANG Z G,et al.Challenges and countermeasures of flood disaster prevention in China under changing environment[J].Journal of Hydraulic Engineering,2022,53(6):1-14.
[3] 李国英.为以中国式现代化全面推进强国建设、民族复兴伟业提供有力的水安全保障：在2024年全国水利工作会议上的讲话[J].水利发展研究，2024,24(1):1-10.LI G Y.Improved water security for China’s efforts to build itself into a stronger country and rejuvenate the Chinese nation on all fronts by pursuing Chinese modernization:Speech at the 2024 National Water Conservancy Work Conference[J].Water Resources Development Research,2024,24(1):1-10.
[4] 李国英.深入贯彻落实党的二十大精神扎实推动新阶段水利高质量发展：在2023年全国水利工作会议上的讲话[J].水利发展研究，2023,23(1):1-11.LI G Y.Thoroughly implement the spirit of the 20th National Congress of the Communist Party of China and solidly promote the high-quality development of water conservancy in the new stage:Speech at the National Water Conservancy Work Conference in 2023[J].Water Resources Development Research,2023,23(1):1-11.
[5] 杨露露，方秀琴，袁玲，等.江西省小流域山洪因子敏感性分析与灾害风险评估[J].科学技术与工程，2023,23(10):4448-4456.YANG L L,FANG X Q,YUAN L,et al.Flash flood factors sensitivity analysis and disaster risk assessment in Jiangxi Province[J].Science Technology and Engineering,2023,23(10):4448-4456.
[6] RAILLANI H,HAMMADI L,EL BALLOUTI A,et al.Uncertainty quantification for disaster modelling:Flooding as a case study[J].Stochastic Environmental Research and Risk Assessment,2023,37(7):2803-2814.
[7] WU X,LOU P,LI W,et al.Landscape ecological risk assessment and analysis of influencing factors in Selenga River Basin[J].Remote Sensing,2023,15(17):4262.
[8] 陈刚，李文静，林凯荣.基于GIS的清远市山洪灾害风险评价[J].人民珠江，2017,38(10):55-59.CHEN G,LI W J,LIN K R.Flash flood risk assessment in Qingyuan City based on GIS method[J].Pearl River,2017,38(10):55-59.
[9] ZHANG Q Z,ZHOU H M,LU Y,et al.Research on Chongqing Mountain flood disaster risk assessment system based on AHP-GIS[J].IOP Conference Series:Earth and Environmental Science,2019,330(3):032028.
[10] 章嘉俊，董林，张娜，等.基于GIS的新疆维吾尔自治区山洪灾害风险评价[J].人民长江，2024,55(11):81-88.ZHANG J J,DONG L,ZHANG N,et al.Risk assessment of flash flood disasters based on GIS in Xinjiang Uygur Autonomous Region[J].Yangtze River,2024,55(11):81-88.
[11] WIBOWO R C,SARKOWI M,SETIAWAN A F,et al.Flash flood hazard areas assessment in Bandar Negeri Suoh (BNS) region using an index based approaches and analytical hierarchy process[J].Journal of Physics:Conference Series,2020,1434(1):012006.
[12] ZHANG W T,ZHANG X N,LIU Y Z,et al.Assessment of flood inundation by coupled 1D/2D hydrodynamic modeling:A case study in mountainous watersheds along the coast of southeast China[J].Water,2020,12(3):822.
[13] HU X Z,SONG L X.Hydrodynamic modeling of flash flood in mountain watersheds based on high-performance GPU computing[J].Natural Hazards,2018,91(2):567-586.
[14] EL-SAOUD W A,OTHMAN A.An integrated hydrological and hydraulic modelling approach for flash flood hazard assessment in Eastern Makkah City,Saudi Arabia[J].Journal of King Saud University-Science,2022,34(4):102045.
[15] SALIH A,HASSABLLA A.Flash flood risk assessment in the Asir Region,southwestern Saudi Arabia,using a physically-based distributed hydrological model and GPM IMERG satellite rainfall data[J].Atmosphere,2024,15(6):624.
[16] LI W J,LIN K R,ZHAO T,et al.Risk assessment and sensitivity analysis of flash floods in ungauged basins using coupled hydrologic and hydrodynamic models[J].Journal of Hydrology,2019,572:108-120.
[17] AL KUISI M,AL AZZAM N,HYARAT T,et al.Flood hazard and risk assessment of flash floods for Petra Catchment area using hydrological and analytical hierarchy (AHP) modeling[J].Water,2024,16(16):2283.
[18] 付潇然，王中根，祁书文，等.应急视域下山洪灾害复盘与应对过程分析：以2022年6场典型事件为例[J].水利水电技术(中英文),2024,55(11):15-25.FU X R,WANG Z G,QI S W,et al.A summary and reflection on the six events of flash flood disasters in 2022 from an emergency management perspective[J].Water Resources and Hydropower Engineering,2024,55(11):15-25.
[19] 范桂英，汤军，高贤君，等.基于LightGBM的南阳市西部地区山洪灾害风险评价[J].中国农村水利水电，2023(8):135-141.FAN G Y,TANG J,GAO X J,et al.Flash flood disaster risk assessment in the western area of Nanyang City based on LightGBM[J].China Rural Water and Hydropower,2023(8):135-141.
[20] CHU Y,SONG W F,CHEN D B.Risk identification of mountain torrent hazard using machine learning and Bayesian model averaging techniques[J].Water,2024,16(11):1556.
[21] MA M H,LIU C J,ZHAO G,et al.Flash flood risk analysis based on machine learning techniques in the Yunnan Province,China[J].Remote Sensing,2019,11(2):170.
[22] 敬双怡，莘明亮，于玲红，等.基于模糊综合评价法的大同市山洪灾害风险评价[J].水利水电技术，2018,49(5):84-89.JING S Y,SHEN M L,YU L H,et al.Fuzzy comprehensive evaluation method-based risk assessment on mountain torrent disaster in Datong City[J].Water Resources and Hydropower Engineering,2018,49(5):84-89.
[23] RUIDAS D,SAHA A,ISLAM A R M T,et al.Development of geo-environmental factors controlled flash flood hazard map for emergency relief operation in complex hydro-geomorphic environment of tropical river,India[J].Environmental Science and Pollution Research,2023,30(49):106951-106966.
[24] JU W,XING Z,WU J.Comprehensive risk assessment of natural disasters based on machine learning in Changzhou City,China[J].Environment,Development and Sustainability,2024:1-33.
[25] ALIPOUR A,AHMADALIPOUR A,ABBASZADEH P,et al.Leveraging machine learning for predicting flash flood damage in the Southeast US[J].Environmental Research Letters,2020,15(2):024011.
[26] COSTACHE R,TRUNG TIN T,ARABAMERI A,et al.Flash-flood hazard using deep learning based on H2O R package and fuzzy-multicriteria decision-making analysis[J].Journal of Hydrology,2022,609:127747.
[27] BU C,ZHANG Z P.Research on overfitting problem and correction in machine learning[J].Journal of Physics:Conference Series,2020,1693(1):012100.
[28] ALI L,BUKHARI S A C.An approach based on mutually informed neural networks to optimize the generalization capabilities of decision support systems developed for heart failure prediction[J].IRBM,2021,42(5):345-352.
[29] XIONG J N,PANG Q,FAN C K,et al.Spatiotemporal characteristics and driving force analysis of flash floods in Fujian Province[J].ISPRS International Journal of Geo-Information,2020,9(2):133.
[30] 郝思佳，王文川，马强，等.基于水文水动力模型的山洪灾害复盘策略：以河南王宗店村“7·20”山洪为例[J].水利水电技术(中英文),2023(6):1-11.HAO S J,WANG W C,MA Q,et al.A numerical rehearsal strategy of flash flood disaster with hydrological and hydrodynamic modelling:Case study of “7·20” flash flood disaster in Wangzongdian Village,Henan Province[J].Water Resources and Hydropower Engineering,2023(6):1-11.
[31] HAN Y Y,HUANG L,ZHOU F F.A dynamic recursive feature elimination framework (dRFE) to further refine a set of OMIC biomarkers[J].Bioinformatics,2021,37(15):2183-2189.
[32] JEON H,OH S.Hybrid-recursive feature elimination for efficient feature selection[J].Applied Sciences,2020,10(9):3211.
[33] BIAU Gerard,SCORNET Erwan.A Random Forest Guided Tour[J].TEST,2016,25(2):197-227.
[34] CAI S Y,FAN J M,YANG W.Flooding risk assessment and analysis based on GIS and the TFN-AHP method:A case study of Chongqing,China[J].Atmosphere,2021,12(5):623.
[35] KHAJEHEI S,AHMADALIPOUR A,SHAO W Y,et al.A place-based assessment of flash flood hazard and vulnerability in the contiguous United States[J].Scientific Reports,2020,10:448.
基本信息:
DOI：10.13928/j.cnki.wrahe.2025.11.006
中图分类号:TP18;TV87;X43
引用信息:
[1]张晓蕾,秦瑞华,姚秋玲,等.基于分类递归特征消除法-随机森林优化算法的山洪灾害风险模拟技术[J].水利水电技术(中英文),2025,56(11):71-82.DOI:10.13928/j.cnki.wrahe.2025.11.006.
基金信息:
国家自然科学基金项目(42201093,52239006)