基于BP神经网络和VSM的台风灾害经济损失评估

详细信息    查看全文 | 推荐本文 |

英文篇名：Economic Loss Assessment of Typhoon Based on BP Neural Network and VSM 作者：林江豪 ; 阳爱民 英文作者：LIN Jianghao;YANG Aimin;Laboratory for Language Engineering and Computing,Guangdong University of Foreign Studies;School of Information Science and Technology,Guangdong University of Foreign Studies; 关键词：台风灾害 ; 经济损失 ; BP神经网络 ; VSM ; 损失评估 ; 广东 英文关键词：typhoon disaster;;economic loss;;BP neural network;;VSM;;loss assessment;;Guangdong 中文刊名：灾害学 英文刊名：Journal of Catastrophology 机构：广东外语外贸大学语言工程与计算实验室;广东外语外贸大学信息科学与技术学院; 出版日期：2019-01-10 出版单位：灾害学 年：2019 期：01 基金：广州市哲学社会科学“十三五”规划2018年度课题(2018GZQN27) 语种：中文; 页：24-28 页数：5 CN：61-1097/P ISSN：1000-811X 分类号：F127;P429

摘要

统计了对广东省造成直接经济损失的台风数据,包括致灾因子、孕灾环境和承灾体等评估因子,对数据进行无量纲化、归一化处理,作为验证模型的数据集。建立BP神经网络和空间向量模型(VSM)相结合的综合评估模型,利用BP神经网络进行初步预测,基于VSM对预测结果进行修正,从而构建台风灾害经济损失评估模型。将收集的历史台风经济损失数据分为训练和测试集,对模型进行训练和检验。经验证,采用BP神经网络和VSM相结合的台风灾害经济损失评估模型能够有效降低训练数据不足对评估结果的影响,平均误差率由30%降低到14%。
        We collecte the historical data of economic losses triggered by typhoon disasters into a typhoon data set,including disaster-causing factors,disaster-pregnant environment and hazard bearing body. The data set undertaken the process of dimensionless and normalization before being used to testify and verify the model. In order to evaluate the economic loss of typhoon,we establisha comprehensive evaluation model. It began with using BP neural network to evaluate economic losses of typhoon disaster. Then,the evaluation results are remedied via VSM model before the comprehensive evaluation model is built. The collected data is divided into two data sets,one for model training,and the other for testing. The experimental results showed that the comprehensive evaluation model is effective. More specifically,it could avoid the influence the shortage of training data brought on the evaluation results and the average error rate is reduced from 30% to 14%.

引文

[1]叶雯.广东省台风灾害特点及减灾对策[J].灾害学,2002,17(3):54-59.
    [2] Emanuel,K. and R. Sundararajan,et al. Hurricanes and global warming[J]. Bull. Am. Meteorol. Soc,2008,89:347-367.
    [3] WANG Xiaoling,WU Liguang,REN Fumin,et al. Influences of tropical cyclones on China during 1965-2004[J]. Advances in Atmospheric Sciences,2008,25(3):417-426.
    [4]孙绍骋.灾害评估研究内容与方法探讨[J].地理科学进展,2001,20(2):122-130.
    [5] ZHANG Xinchang,LOU Weiping. Estimation of the number of collapsed houses damaged by typhoon based on principal components analysis and support vector machine[J]. Meteorological and Environmental Research,2010,1(4):11-14.
    [6]娄伟平,陈海燕,郑峰,等.基于主成分神经网络的台风灾害经济损失评估[J].地理研究,2009,8(5):1243-1255.
    [7]刘少军,张京红,何政伟,等.基于GIS的台风灾害损失评估模型研究[J].灾害学,2010,25(2):64-67.
    [8] LU C L,CHEN S H. Multiple linear interdependent models(Mlim)applied to typhoon data from China[J]. Theoretical and applied climatology. 1998,61(3):143-149.
    [9] HSU C C,HONG Z Y. An intelligent typhoon damage prediction system from aerial photographs[M]. Springer,2010.
    [10]陈仕鸿,刘晓庆.基于离散型Hopfield神经网络的台风灾情评估模型[J].自然灾害学报,2011,20(5):47-52.
    [11]陈仕鸿,隋广军,阳爱民.广东台风灾情预测系统研究[J].自然灾害学报,2012,21(3):50-55.
    [12]吴亚玲,姜珊,吴先华,等.基于极值理论的广东省台风灾害损失分布及其金融对策研究[J].灾害学,2017,32(01):126-131+220.
    [13]魏章进,马华铃,唐丹玲.基于改进熵值法的台风灾害风险趋势评估[J].灾害学,2017,32(03):7-11.
    [14]朱凯,王正林.精通MATLAB神经网络[M].北京:电子工业出版社,2010:193-200.
    [15]李庆华,赵彦斌,赵峰等.基于向量空间模型的并行信息检索算法[J].小型微型计算机系统,2005,26(9):1560-1562.