基于证据理论的风暴潮灾害损失评估

doi:10.11978/2021037

热带海洋学报 ›› 2022, Vol. 41 ›› Issue (1): 75-81.doi: 10.11978/2021037CSTR: 32234.14.2021037

基于证据理论的风暴潮灾害损失评估

孙丰霖()

中国海洋大学海洋与大气学院, 山东青岛 266100

收稿日期:2021-03-29 修回日期:2021-05-13 出版日期:2022-01-10 发布日期:2021-05-24
通讯作者: 孙丰霖
作者简介:孙丰霖(1992—), 男, 山东淄博人, 博士研究生, 从事海洋灾害损失评估研究。email: sfl@stu.ouc.edu.cn

Disaster loss assessment of storm surge based on Dempster-Shafer theory of evidence

SUN Fenglin()

College of Oceanic and Atmospheric Sciences, Ocean University of China, Qingdao 266100, China

Received:2021-03-29 Revised:2021-05-13 Online:2022-01-10 Published:2021-05-24
Contact: SUN Fenglin

摘要/Abstract

摘要：

本文提出了一种基于Dempster-Shafer证据理论的风暴潮灾害损失评估方法。鉴于风暴潮致灾过程中的不确定性, 选择合适的具有代表性指标(包括最大风暴潮增水、最大有效波高和防灾减灾能力)产生灾害损失评估的证据, 并根据所选指标和风暴潮直接经济损失之间的相关性大小确定证据权重, 最后采用改进的Murphy证据融合算法进行证据融合, 从而判断灾害损失等级。通过实证分析发现, 本文所提出的方法在判断风暴潮灾害损失等级上的正确率达到93.1%, 优于朴素贝叶斯、支持向量机、神经网络和决策树等常用方法, 同时本文方法计算简便, 且随着训练集样本量的增加, 损失评估结果可进一步精细化。

关键词: 风暴潮灾害, 损失评估, 证据理论, 灾损等级, Murphy方法

Abstract:

A disaster loss assessment method based on the Dempster-Shafer theory of evidence for storm surge is proposed in this paper. Because of uncertainty of storm surge in the disaster process, we select representative indicators (maximum height of storm surge, significant wave height, disaster prevention and reduction ability) to produce several pieces of evidence. The weight of evidence is calculated by using correlation between indicator and direct economic loss of storm surge disaster. A modified Murphy method is used to fuse evidence from different sources to judge the disaster loss level. An example is used to show that the classification accuracy of the method used in this paper can reach 93.1%, which is better than some existing methods, such as the Naive Bayes, Support Vector Machine, Neural Network, and Decision Tree methods. In addition, the method is simple in computation, and the results of disaster loss assessment can be more detailed with increasing training samples.

Key words: storm surge disaster, loss assessment, evidence theory, disaster loss grade, Murphy method

中图分类号:

P954

孙丰霖. 基于证据理论的风暴潮灾害损失评估[J]. 热带海洋学报, 2022, 41(1): 75-81.

SUN Fenglin. Disaster loss assessment of storm surge based on Dempster-Shafer theory of evidence[J]. Journal of Tropical Oceanography, 2022, 41(1): 75-81.

图/表 4

图1

表1

表2

表3

参考文献 18

[1]	纪燕新, 熊艺媛, 麻荣永, 2007. 风暴潮灾害损失评估的模糊综合方法[J]. 广西水利水电, (2): 16-19, 28.
	JI YANXIN, XIONG YIYUAN, MA RONGYONG, 2007. Fuzzy synthetic method applied in assessment of storm tide disaster losses[J]. GX Water Resources & Hydropower Engineering, (2): 16-19, 28. (in Chinese with English abstract)
[2]	江斯琦, 刘强, 2020. 基于改进神经网络及地理信息系统空间分析的风暴潮经济损失评估[J]. 科学技术与工程, 20(22): 9243-9247.
	JIANG SIQI, LIU QIANG, 2020. The assessment of storm surge economic loss based on improved neural network and geographic information system spatial analysis[J]. Science Technology and Engineering, 20(22): 9243-9247. (in Chinese with English abstract)
[3]	康兵义, 李娅, 邓勇, 等, 2012. 基于区间数的基本概率指派生成方法及应用[J]. 电子学报, 40(6): 1092-1096. doi: 10.3969/j.issn.0372-2112.2012.06.004
	KANG BINGYI, LI YA, DENG YONG, et al, 2012. Determination of basic probability assignment based on interval numbers and its application[J]. Acta Electronica Sinica, 40(6): 1092-1096. (in Chinese with English abstract) doi: 10.3969/j.issn.0372-2112.2012.06.004
[4]	李超, 2006. 基于物元分析的我国洪灾损失综合评估[J]. 统计教育, (3): 44-46. (in Chinese)
[5]	罗金炎, 徐飞, 李燕, 等, 2020. 福建省台风灾害损失分布分析[J]. 沈阳师范大学学报(自然科学版), 38(5): 417-421.
	LUO JINYAN, XU FEI, LI YAN, et al, 2020. Analysis on the distribution of typhoon disaster losses in Fujian province[J]. Journal of Shenyang Normal University (Natural Science Edition), 38(5): 417-421. (in Chinese with English abstract)
[6]	石先武, 刘钦政, 王宇星, 2015. 风暴潮灾害等级划分标准及适用性分析[J]. 自然灾害学报, 24(3): 161-168.
	SHI XIANWU, LIU QINZHENG, WANG YUXING, 2015. Gradation criteria of storm surge disaster and their applicability analysis[J]. Journal of Natural Disasters, 24(3): 161-168. (in Chinese with English abstract)
[7]	隋意, 石洪源, 钟超, 等, 2020. 我国台风风暴潮灾害研究[J]. 海洋湖沼通报, (3): 39-44.
	SUI YI, SHI HONGYUAN, ZHONG CHAO, et al, 2020. Research on typhoon storm surge disaster in China[J]. Transactions of Oceanology and Limnology, (3): 39-44. (in Chinese with English abstract)
[8]	王志强, 陈思宇, 吕雪锋, 等, 2015. 风暴潮灾害受灾人口与直接经济损失评估方法研究进展[J]. 北京师范大学学报(自然科学版), 51(3): 274-279.
	WANG ZHIQIANG, CHEN SIYU, LÜ XUEFENG, et al, 2015. A review on evaluating hazard-affected population and direct economic losses by storm surge[J]. Journal of Beijing Normal University (Natural Science), 51(3): 274-279. (in Chinese with English abstract)
[9]	谢丽, 张振克, 2010. 近20年中国沿海风暴潮强度、时空分布与灾害损失[J]. 海洋通报, 29(6): 690-696.
	XIE LI, ZHANG ZHENKE,2010. Study on the relationship between intensity, spatial-temporal distribution of storm surges and disaster losses along the coast of China in past 20 years[J]. Marine Science Bulletin, 29(6): 690-696. (in Chinese with English abstract)
[10]	许启望, 谭树东, 1998. 风暴潮灾害经济损失评估方法研究[J]. 海洋通报, 17(1): 1-12.
	XU QIWANG, TAN SHUDONG, 1998. Research on the method of evaluating the economic loss caused by storm, surge disaster[J]. Marine Science Bulletin, 17(1): 1-12. (in Chinese with English abstract)
[11]	叶雯, 刘美南, 陈晓宏, 2004. 感知器算法在台风风暴潮灾情等级评估中的应用[J]. 中山大学学报(自然科学版), 43(2): 117-120.
	YE WEN, LIU MEINAN, CHEN XIAOHONG,2004. The application of the perception approach in the evaluation of typhoon storm surge disaster degree[J]. Acta Scientiarum Naturalium Universitatis Sunyatseni, 43(2): 117-120. (in Chinese with English abstract)
[12]	赵领娣, 边春鹏, 2012. 风暴潮灾害综合损失等级划分标准的研究[J]. 中国渔业经济, 30(3): 42-49.
	ZHAO LINGDI, BIAN CHUNPENG, 2012. The analysis of class division of storm surge comprehensive loss[J]. Chinese Fisheries Economics, 30(3): 42-49. (in Chinese with English abstract)
[13]	CHEN LEI, DIAO LING, SANG JUN, 2020. A new method to handle conflict when combining evidences using entropy function and evidence angle with an effective application in fault diagnosis[J]. Mathematical Problems in Engineering, 2020: 3564365.
[14]	DEMPSTER A P, 1967. Upper and lower probabilities induced by a multivalued mapping[J]. The Annals of Mathematical Statistics, 38(2): 325-339. doi: 10.1214/aoms/1177698950
[15]	MURPHY C K, 2000. Combining belief functions when evidence conflicts[J]. Decision Support Systems, 29(1): 1-9. doi: 10.1016/S0167-9236(99)00084-6
[16]	PAN LIPENG, DENG YONG, 2020. An association coefficient of a belief function and its application in a target recognition system[J]. International Journal of Intelligent Systems, 35(1): 85-104. doi: 10.1002/int.v35.1
[17]	SHAFER G, 1976. A mathematical theory of evidence[M]. Princeton: Princeton University Press: 1-287.
[18]	YAGER R R, 2018. Categorization in multi-criteria decision making[J]. Information Sciences, 460-461: 416-423. doi: 10.1016/j.ins.2017.08.011

风暴潮编号	防灾减灾能力	最大增水高度/m	最大有效波高/m	实际灾级	证据1	证据2	证据3	本文方法预测灾级
201909	1.00	0.63	0.81	1	1	2	1	1
201822	0.97	0.44	0.55	1	1	2	1	1
201911	1.00	0.89	0.80	1	1	2	1	1
201509	0.85	0.63	0.57	1	1	2	1	1
201205	0.72	1.69	0.62	1	1	3	1	1
201601	0.88	1.50	0.89	1	1	3	1	1
201407	0.80	1.89	1.06	1	1	3	2	1
201006	0.60	0.91	0.69	1	2	2	1	1
201011	0.60	1.84	0.94	1	2	3	1	1
201111	0.66	0.56	0.76	1	1	2	1	1
200108	0.37	1.96	1.00	1	3	3	2	3
201617	0.88	1.59	0.99	1	1	3	2	1
201308	0.77	0.58	0.63	1	1	2	1	1
201323	0.77	0.76	1.23	2	1	2	2	2
201312	0.77	1.64	1.41	2	1	3	2	2
199504	0.30	0.69	1.00	2	3	2	2	2
200808	0.52	1.34	1.05	2	2	2	2	2
200010	0.35	1.82	0.90	2	3	3	1	3
199417	0.29	0.42	1.05	2	3	2	2	2
200908	0.55	0.90	1.32	2	2	2	2	2
201013	0.60	1.33	1.02	2	2	2	2	2
200216	0.38	1.30	1.20	3	3	2	2	3
199012	0.26	2.92	0.18	3	3	3	1	3
200513	0.43	1.74	0.83	3	3	3	1	3
199914	0.34	1.40	0.97	3	3	2	2	3
200102	0.37	2.76	1.22	3	3	3	2	3
199607	0.31	1.49	0.89	3	3	3	1	3
200604	0.45	1.78	1.14	3	3	3	2	3
200608	0.45	2.36	1.26	3	3	3	2	3

灾级	本文方法				DS融合	Murphy方法
灾级	正确数	错误数	总数	正确率	DS融合	Murphy方法
一级	12	1	13	92.3%	77%	77%
二级	7	1	8	87.5%	88%	88%
三级	8	0	8	100.0%	88%	88%
总体	27	2	29	93.1%	83%	83%

灾级	本文方法	朴素贝叶斯	支持向量机	神经网络	决策树
一级	92.3%	92.3%	92.3%	84.6%	92.3%
二级	87.5%	87.5%	50.0%	62.5%	0.0%
三级	100.0%	62.5%	75.0%	62.5%	100.0%
总体	93.1%	82.8%	75.9%	72.4%	69.0%

基于证据理论的风暴潮灾害损失评估

Disaster loss assessment of storm surge based on Dempster-Shafer theory of evidence

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 4

参考文献 18

相关文章 0

Metrics

本文评价

推荐阅读 0