基于SSA-BP神经网络模型的风暴潮灾害损失评估-海洋预报

基于SSA-BP神经网络模型的风暴潮灾害损失评估

单位：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

分类号：P731.23

出版年·卷·期（页码）：2022·39·第二期（50-58）

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R²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 to 2020 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 R² value is 0.771 when the training set is fitted using the traditional BP neural network, while the R² value reaches 0.916 after optimized by the sparrow search algorithm (SSA-BP) with improved stability and accuracy.

参考文献：

[1] 郭腾蛟, 李国胜. 风暴潮灾害经济损失灾前预评估研究进展[J]. 灾害学, 2018, 33(4): 164-168. Guo T J, Li G S. Research progress on pre-assessment of economic losses before storm surge disasters[J]. Journal of Catastrophology, 2018, 33(4): 164-168.
[2] 中华人民共和国自然资源部. 2020年中国海洋灾害公报[EB/ OL]. [2021-05-21]. http://www.mnr.gov.cn/sj/sjfw/hy/gbgg/zghyzhgb/. Ministry of Natural Resources of the People's Republic of China. 2020 Bulletin of China marine disaster[EB/OL].[2021-05-21]. http://www.mnr.gov.cn/sj/sjfw/hy/gbgg/zghyzhgb/.
[3] Huang Z G, Rosowsky D V, Sparks P R. Long-term hurricane risk assessment and expected damage to residential structures[J]. Reliability Engineering & System Safety, 2001, 74(3): 239-249.
[4] 赵昕, 王保颂, 郑慧. 基于RS-SVM模型的风暴潮灾害损失测度[J]. 海洋环境科学, 2015, 34(4): 596-600. Zhao X, Wang B S, Zheng H. The assessment of storm surge disaster loss based on RS-SVM model[J]. Marine Environmental Science, 2015, 34(4): 596-600.
[5] Rao A D, Chittibabu P, Murty T S, et al. Vulnerability from storm surges and cyclone wind fields on the coast of Andhra Pradesh, India[J]. Natural Hazards, 2007, 41(3): 515-529.
[6] 袁晓玉. 浙江省气候变化特征及自然灾害时空分布的统计分析[D]. 南京: 南京气象学院, 2002. Yuan X Y. Statistical analysis of climatic variation features and spatial and temporal distribution of the flood and drought in Zhejiang province[D]. Nanjing: Nanjing Institute of Meteorology, 2002.
[7] 中华人民共和国自然资源部. 1990～2020年中国海洋灾害公报[EB/OL]. [2021-05-21]. http://www.mnr.gov.cn/sj/sjfw/hy/gbgg/zghyzhgb/. Ministry of Natural Resources of the People's Republic of China. 1990-2020 Bulletin of China marine disaster[EB / OL]. [2021-05- 21]. http://www.mnr.gov.cn/sj/sjfw/hy/gbgg/zghyzhgb/.
[8] 于福江, 董剑希, 叶琳. 中国风暴潮灾害史料集: 1949-2009[M]. 北京: 海洋出版社, 2015. Yu F J, Dong J X, Ye L. Collection of storm surge disasters historical data in China 1949-2009[M]. Beijing: China Ocean Press, 2015.
[9] 浙江省统计局. 浙江统计年鉴[EB/OL]. [2021-05-21]. http://tjj.zj.gov.cn/col/col1525563/index.html. Zhejiang Provincial Bureau of Statistics. Statistical yearbook of Zhejiang province[EB/OL]. [2021-05-21]. http://tjj.zj.gov.cn/col/col1525563/index.html.
[10] 肖茹水, 郭佩芳, 解晓茹. 风暴潮灾害损失评估研究综述[J]. 海洋湖沼通报, 2021, 43(2): 67-73. Xiao R S, Guo P F, Xie X R. Theoretical research of storm surge loss assessment[J]. Transactions of Oceanology and Limnology, 2021, 43(2): 67-73.
[11] 徐晓晓. 海岸带地区风暴潮灾害风险研究[D]. 青岛: 中国海洋大学, 2015. Xu X X. Risk research of Storm surge disaster in coastal zone[D]. Qingdao: Ocean University of China, 2015.
[12] 张颖, 高倩倩, 高茂庭. 基于支持向量回归机算法的海水富营养化过程中藻类繁殖状态软测量研究[J]. 海洋预报, 2014, 31(5): 87-92. Zhang Y, Gao Q Q, Gao M T. Study on soft sensing for status of algae reproduction in the process of seawater eutrophication based on Support Vector Regression algorithm[J]. Marine Forecasts, 2014, 31(5): 87-92.
[13] 邓聚龙. 灰色系统理论教程[M]. 武汉: 华中理工大学出版社, 1990. Deng J L. Grey system theory tutorial[M]. Wuhan: Huazhong University of Technology Press, 1990.
[14] Ruan B B. Prediction of stock market by BP neural network model [J]. Journal of Physics: Conference Series, 2021, 1744: 042232.
[15] 卢君峰, 李少伟, 袁方超. 基于BP神经网络的厦门沿海风暴潮预报应用[J]. 海洋预报, 2016, 33(4): 9-16. Lu J F, Li S W, Yuan F C. Application of storm surge forecasting by BP artificial neural network off coast of Xiamen[J]. Marine Forecasts, 2016, 33(4): 9-16.
[16] Xue J K, Shen B. A novel swarm intelligence optimization approach: sparrow search algorithm[J]. Systems Science & Control Engineering, 2020, 8(1): 22-34.

服务与反馈：

【文章下载】【发表评论】【查看评论】【加入收藏】