基于SSA-BP神经网络模型的风暴潮灾害损失评估  

The assessment of storm surge disaster loss based on SSA-BP neural network model

作　　者：贾丙宏 祝文硕 王瑞富[1] 高松[2] 胡莹[1] 王怀计 JIA Binghong;ZHU Wenshuo;WANG Ruifu;GAO Song;HU Ying;WANG Huaiji(College of Geodesy and Geomatics,Shandong University of Science and Technology,Qingdao 266590 China;North Sea Marine Forecast Center of State Oceanic Administration,Qingdao 266061 China)

机构地区：[1]山东科技大学测绘与空间信息学院,山东青岛266590 [2]国家海洋局北海预报中心,山东青岛266061

出　　处：《海洋预报》2022年第2期50-58,共9页Marine Forecasts

基　　金：国家重点研发计划课题(2017YFC1405005)。

摘　　要：选取浙江省1990—2020年29组记录完整的风暴潮历史灾情资料,建立了系统的风暴潮灾害损失评估指标体系,使用灰色关联分析法对指标进行筛选预处理,并提出基于麻雀搜索算法优化的BP神经网络模型,对风暴潮灾害直接经济损失进行评估。结果显示:传统BP神经网络对训练集的拟合得到的R2值为0.771,而经麻雀搜索算法(SSA-BP)优化后的R^(2)值达到0.916,且无论在稳定性还是精度方面均有所提高。This paper selects 29 sets of complete historical disaster data of storm surge recorded from 1990 to2020 in Zhejiang Province, and establishes a systematic disaster loss assessment indicators system for storm surge. Then, the indicators are screened and preprocessed using grey relational analysis method. Finally, this paper proposes a BP neural network model optimized by the sparrow search algorithm to evaluate the direct economic loss of storm surge disasters. The results show that the R^(2) value is 0.771 when the training set is fitted using the traditional BP neural network, while the R;value reaches 0.916 after optimized by the sparrow search algorithm(SSA-BP) with improved stability and accuracy.

关 键 词：风暴潮 灾害损失评估 麻雀搜索算法 BP神经网络 

分 类 号：P731.23[天文地球—海洋科学]