基于BES-PP模型的区域洪水灾害恢复力研究

Research on Regional Flood Disaster Resilience Using an Improved Projection PursuitModel Based on Bald Eagle Search Optimization Algorithm

针对区域洪水灾害恢复力评价方法较为薄弱及其驱动机制不明的问题,构建自然、经济、社会和技术4个维度的洪水灾害恢复力评价指标体系,建立秃鹰搜索算法改进投影寻踪模型(Projection Pursuit Model Based on Bald Eagle Search Optimization Algorithm,BES-PP)。基于此,利用BES-PP模型对佳木斯市2003-2020年的洪水灾害恢复力进行评估。结果显示:佳木斯市的恢复力水平可分为3个阶段,第一阶段(2003-2006年)恢复力平稳上升但是水平较低,第二阶段(2007-2013年)恢复力水平出现明显波动,第三阶段(2014-2020年)恢复力快速上升并最终达到较高水平。为分析其驱动机制,利用BES-PP模型对各个指标的权重进行分析,结果发现经济维和自然维权重分别达到1.21168和0.93242,其平均权重分别达到0.30292和0.31081,远高于社会维和技术维。表明自然维和经济维的指标对洪水灾害恢复力具有较高程度的影响,应当重视自然及经济因素在规避洪水灾害中的重要作用。为验证BES-PP模型性能,引入了黏菌优化算法改进投影寻踪模型(Projection Pursuit Model Based on Slime Mould Algorithm,SMA-PP)和鲸鱼优化算法改进投影寻踪模型(Projection Pursuit Model Based on Whale Optimization Algorithm,WOA-PP)进行对比分析。结果显示:BES-PP模型在性能上具有较为明显的优势。此外,采用序号总和理论分析BES-PP、SMA-PP和WOA-PP的评价结果发现,BES-PP模型的评价结果更具合理性。研究成果为佳木斯市防灾减灾能力提升提供了科学依据,同时也为灾害恢复力评估提供了一些有价值的信息。

Aiming at the problems of weak evaluation methods and unclear driving mechanism of regional flood disaster resilience,an evalua⁃tion index system of flood disaster resilience from natural,economic,social and technical dimensions was constructed,and Projection Pur⁃suit Model Based on Bald Eagle Search Optimization Algorithm(BES-PP)was established.Based on this,the BES-PP model was used to evaluate the flood disaster resilience of Jiamusi City from 2003 to 2020.The results show that the resilience level of Jiamusi city can be divid⁃ed into three stages:the first stage(2003-2006)resilience rose steadily but at a low level;the second stage(2007-2013)resilience fluctu⁃ated obviously;the third stage(2014-2020)resilience rose rapidly and finally reached a high level.In order to analyze the driving mecha⁃nism,the BES-PP model was used to analyze the weights of each index.The results showed that the natural rights-protecting weights of eco⁃nomic peacekeeping reached 1.21168 and 0.93242,respectively,and their average weights reached 0.30292 and 0.31081,which were much higher than the technical dimensions of social peacekeeping.It shows that the index of natural and economic dimensions has a high de⁃gree of influence on the resilience of flood disaster and the important role of natural and economic factors in avoiding flood disaster should be paid attention to.In order to verify the performance of the BES-PP model,Projection Pursuit Model Based on Slime Mould Algorithm(SMAPP)and Projection Pursuit Model Based on Whale Optimization Algorithm(WOA-PP)are introduced for comparative analysis.The results show that the BES-PP model has obvious advantages in performance.In addition,the evaluation results of BES-PP,SMA-PP and WOA-PP were analyzed by using the serial number sum theory,and it was found that the evaluation results of the BES-PP model were more reason⁃able.The research results provide a scientific basis for the improvement of disaster prevention and reduction capacity of Jiamusi city,and also provide some valuable information for the assessment of disaster resilience.