基于高斯过程回归模型的洪涝灾害损失预测研究——以重庆市为例
|
摘要
快速准确的预测洪涝灾害各项损失是开展洪涝灾害应急管理工作的基础,而预测技术和方法则是洪涝灾害损失预测的核心与关键。从灾害风险构成因素和数据易获取性2方面构建了洪涝灾害损失评估指标体系,分别从致灾因子、孕灾环境、承灾体和应急能力4个方面选取了13项损失评估输入指标,提出基于高斯过程回归模型的洪涝灾害损失预测方法,并应用于重庆市洪灾受灾人数、农作物受灾面积和直接经济损失的预测。实例表明,高斯过程回归方法对上文提到的3种损失情况预测结果的残差平方和分别为0.99、0.1、12.67,拟合精度分别达到99.85%、99.97%、96.1%,相较于多层感知器神经网络和支持向量机等方法更具优越性。
Fast and accurate prediction of flood damage is the basis for emergency management of flood disasters, and forecasting techniques and methods are the core and key to flood disaster loss prediction. This paper constructs a flood disaster assessment index system from the aspects of disaster risk component and data accessibility, and selects 13 loss assessment input indicators from disaster-causing factors, affected environment, disaster-bearing object and emergency response capability. A prediction method of flood damage loss based on Gaussian process regression model is proposed, which is applied to the prediction of the flood damage loss in Chongqing of affected number of people, crop affected area and direct economic losses. The example shows that the residual square sum of the three loss cases mentioned above is 0.99, 0.1 and 12.67 respectively, and the fitting precision is 99.85%, 99.97% and 96.1% respectively. Compared with the multi-layer perceptron neural network and support vector machine, the Gauss process regression method is more superior.
Fast and accurate prediction of flood damage is the basis for emergency management of flood disasters, and forecasting techniques and methods are the core and key to flood disaster loss prediction. This paper constructs a flood disaster assessment index system from the aspects of disaster risk component and data accessibility, and selects 13 loss assessment input indicators from disaster-causing factors, affected environment, disaster-bearing object and emergency response capability. A prediction method of flood damage loss based on Gaussian process regression model is proposed, which is applied to the prediction of the flood damage loss in Chongqing of affected number of people, crop affected area and direct economic losses. The example shows that the residual square sum of the three loss cases mentioned above is 0.99, 0.1 and 12.67 respectively, and the fitting precision is 99.85%, 99.97% and 96.1% respectively. Compared with the multi-layer perceptron neural network and support vector machine, the Gauss process regression method is more superior.
引文
[1]Natural disasters trends[EB/OL].(2018-03-01)[2018-07-05]https://www.emdat.be/publications.
[2]周蕾,吴先华,吉中会.考虑恢复力的洪涝灾害损失评估研究进展[J].自然灾害学报,2017,26(2):11-21.ZHOU L,WU X H,JI Z H.Research advance in flood damage assessment considering resilience[J].Journal of Natural Disasters,2017,26(2):11-21.
[3]王平,黄河,吴玮.基于支持向量机的湖北省洪涝农业损失预测模型[J].湖北农业科学,2014,53(18):4437-4440.WANG P,HUANG H,WU W.Forecast model of flood disaster agricultural losses in Hubei Province based on support vector machine[J].Hubei Agricultural Sciences,2014,53(18):4437-4440.
[4]刘小生,胡啸,王婷丽.基于神经网络集成的洪灾损失快速评估[J].中国有色金属学报(英文版),2014(8):2636-2641.LIU X S,HU X,WANG T L.Rapid assessment of flood loss based on neural network ensemble[J].Transactions of Nonferrons Metals Society of China,2014(8):2636-2641.
[5]于小兵,姚天祥,骆翔,等.集成神经网络和灰色系统的我国农业受灾面积预测[J].干旱区资源与环境,2016,30(9):64-70.YU X B,YAO T X,LUO X,et al.Integrate NARX neural network and grey system to forecast China agricultural areas affected by natural disasters[J].Journal of Arid Land Resources and Environment,2016,30(9):64-70.
[6]冯倩,刘强.基于SVM-BP神经网络的风暴潮灾害损失预评估[J].海洋环境科学,2017,36(4):615-621.FENG Q,LIU Q.Pre-assessment for the loss caused by storm surge based on the SVM-BP neural network[J].Marine Environmental Science,2017,36(4):615-621.
[7]李祎琛,何亚伯,汪洋.基于粗糙集RBF神经网络村镇山洪灾害损失预测研究---以神农架林区为例[J].灾害学,2017,32(2):227-234.LI Y C,HE Y B,WANG Y.Mountain torrent disaster loss prediction research based on RSs and RBF neural network:A case study on Shennongjia[J].Journal of Catastrophology,2017,32(2):227-234.
[8]王甜甜,刘强.基于BAS-BP模型的风暴潮灾害损失预测[J].海洋环境科学,2018,37(3):457-463.WANG T T,LIU Q.The assessment of storm surge disaster loss based on BAS-BP model[J].Marine Environmental Science,2018,37(3):457-463.
[9]杨胜梅,黄艳芳,李申亭,等.基于空间信息技术的溃坝洪灾损失定量评估研究[J].长江科学院院报,2013,30(11):105-108.YANG S M,HUANG Y F,LI S T,et al.Quantitative assessment on dam break loss based on spatial information technology[J].Journal of Yangtze River Scientific Research Institute,2013,30(11):105-108.
[10]李谢辉,韩荟芬.河南省黄河中下游地区洪灾损失评估与预测[J].灾害学,2014,29(1):87-92.Li X H,Han H F.Loss assessment and prediction of flood disaster in the middle and lower reaches of Yellow River in Henan Province[J].Journal of Catastrophology,2014,29(1):87-92.
[11]张先起,张宏洋,李亚敏,等.黄河下游滩区洪水淹没损失评估研究[J].系统工程理论与实践,2015,35(6):1625-1632.ZHANG X Q,ZHANG H Y,LI Y M,et al.Research on floodplain flood loss assessment of the lower Yellow River[J].Systems Engineering-Theory&Practice,2015,35(6):1625-1632.
[12]李大鸣,范玉,赵明雨,等.基于洪水演进数值模拟的洪灾生命损失计算方法研究[J].水利水电技术,2015,46(10):17-21.LI D M,FAN Y,ZHAO M Y,et al.Flood routing numerical simulation-based study on method for calculation of life loss from flood disaster[J].Water Resources and Hydropower Engineering,2015,46(10):17-21.
[13]李大鸣,陈硕,顾利军,等.桃林口水库下游山区洪水演进模拟和洪灾损失评估[J].长江科学院院报,2018,35(6):36-41.LI D M,CHEN S,GU L J,et al.Flood routing simulation and flood loss assessment for mountainous area in the downstream of Taolinkou Reservoir[J].Journal of Yangtze River Scientific Research Institute,2018,35(6):36-41.
[14]KOURGIALAS N N,KARATZAS G P.A hydro-economic modelling framework for flood damage estimation and the role of riparian vegetation[J].Hydrological Processes,2013,27(4):515-531.
[15]AMIREBRAHIMI S,RAJABIFARD A,MENDIS P,et al.Aframework for a microscale flood damage assessment and visualization for a building using BIM-GIS integration[J].International Journal of Digital Earth,2016,9(4):363-386.
[16]CHEN A S,HAMMOND M J,DJORDJEVIC'S,et al.From hazard to impact:flood damage assessment tools for mega cities[J].Natural Hazards,2016,82(2):857-890.
[17]KEFI M,MISHRA B K,KUMAR P,et al.Assessment of tangible direct flood damage using a spatial analysis approach under the effects of climate change:Case study in an urban watershed in Hanoi,Vietnam[J].International Journal of Geo-Information,2018,7(1):1-18.
[18]RASMUSSEN C E,WILLIAMS C K I.Gaussian processes for machine learning[M].The MIT Press,2006.
[19]VOZINAKI A E,KOURGIALAS N,KARATZAS G P.Estimating flood inundation and the consequent economic losses in the Koiliaris river basin in Crete,Greece[J].Global Nest Journal,2012,14(3):284-293.
[20]韩赜,林孝松,左倩云,等.山区镇域山洪灾害孕灾环境分区研究[J].重庆工商大学学报(自然科学版),2014,31(6):82-89.HAN Z,LIN X S,ZUO Q Y,et al.Research on torrent disaster development environment partition in mountainous town-region[J].Journal of Chongqing Technology and Business University(Natural Science Edition),2014,31(6):82-89.
[21]张念强.基于GIS的鄱阳湖地区洪水灾害风险评价[D].南昌:南昌大学,2006.ZHANG N Q.Evaluation of flood risk in Poyang Lake region basing on GIS[D].Nanchang:Nanchang University,2006.
[22]National ocean service[DB/OL].(2018-01-02)ftp://ftp.cdc.noaa.gov/Datasets/cpc_global_precip/[2018-07-03].
[23]中国科学院计算机网络信息中心国际科学数据镜像网站[DB/OL].(2019-09-16)[2018-07-03]http://www.gscloud.cn.
[24]国家减灾中心[EB/OL].(2018-01-04)[2018-07-03]http://www.jianzai.gov.cn/zxzq/index.jhtml.
[25]李宁,张正涛,陈曦,等.论自然灾害经济损失评估研究的重要性[J].地理科学进展,2017,36(2):256-263.LI N,ZHANG Z T,CHEN X,et al.Importance of economic loss evaluation in natural hazard and disaster research[J].Progress in Geography,2017,36(2):256-263.
[2]周蕾,吴先华,吉中会.考虑恢复力的洪涝灾害损失评估研究进展[J].自然灾害学报,2017,26(2):11-21.ZHOU L,WU X H,JI Z H.Research advance in flood damage assessment considering resilience[J].Journal of Natural Disasters,2017,26(2):11-21.
[3]王平,黄河,吴玮.基于支持向量机的湖北省洪涝农业损失预测模型[J].湖北农业科学,2014,53(18):4437-4440.WANG P,HUANG H,WU W.Forecast model of flood disaster agricultural losses in Hubei Province based on support vector machine[J].Hubei Agricultural Sciences,2014,53(18):4437-4440.
[4]刘小生,胡啸,王婷丽.基于神经网络集成的洪灾损失快速评估[J].中国有色金属学报(英文版),2014(8):2636-2641.LIU X S,HU X,WANG T L.Rapid assessment of flood loss based on neural network ensemble[J].Transactions of Nonferrons Metals Society of China,2014(8):2636-2641.
[5]于小兵,姚天祥,骆翔,等.集成神经网络和灰色系统的我国农业受灾面积预测[J].干旱区资源与环境,2016,30(9):64-70.YU X B,YAO T X,LUO X,et al.Integrate NARX neural network and grey system to forecast China agricultural areas affected by natural disasters[J].Journal of Arid Land Resources and Environment,2016,30(9):64-70.
[6]冯倩,刘强.基于SVM-BP神经网络的风暴潮灾害损失预评估[J].海洋环境科学,2017,36(4):615-621.FENG Q,LIU Q.Pre-assessment for the loss caused by storm surge based on the SVM-BP neural network[J].Marine Environmental Science,2017,36(4):615-621.
[7]李祎琛,何亚伯,汪洋.基于粗糙集RBF神经网络村镇山洪灾害损失预测研究---以神农架林区为例[J].灾害学,2017,32(2):227-234.LI Y C,HE Y B,WANG Y.Mountain torrent disaster loss prediction research based on RSs and RBF neural network:A case study on Shennongjia[J].Journal of Catastrophology,2017,32(2):227-234.
[8]王甜甜,刘强.基于BAS-BP模型的风暴潮灾害损失预测[J].海洋环境科学,2018,37(3):457-463.WANG T T,LIU Q.The assessment of storm surge disaster loss based on BAS-BP model[J].Marine Environmental Science,2018,37(3):457-463.
[9]杨胜梅,黄艳芳,李申亭,等.基于空间信息技术的溃坝洪灾损失定量评估研究[J].长江科学院院报,2013,30(11):105-108.YANG S M,HUANG Y F,LI S T,et al.Quantitative assessment on dam break loss based on spatial information technology[J].Journal of Yangtze River Scientific Research Institute,2013,30(11):105-108.
[10]李谢辉,韩荟芬.河南省黄河中下游地区洪灾损失评估与预测[J].灾害学,2014,29(1):87-92.Li X H,Han H F.Loss assessment and prediction of flood disaster in the middle and lower reaches of Yellow River in Henan Province[J].Journal of Catastrophology,2014,29(1):87-92.
[11]张先起,张宏洋,李亚敏,等.黄河下游滩区洪水淹没损失评估研究[J].系统工程理论与实践,2015,35(6):1625-1632.ZHANG X Q,ZHANG H Y,LI Y M,et al.Research on floodplain flood loss assessment of the lower Yellow River[J].Systems Engineering-Theory&Practice,2015,35(6):1625-1632.
[12]李大鸣,范玉,赵明雨,等.基于洪水演进数值模拟的洪灾生命损失计算方法研究[J].水利水电技术,2015,46(10):17-21.LI D M,FAN Y,ZHAO M Y,et al.Flood routing numerical simulation-based study on method for calculation of life loss from flood disaster[J].Water Resources and Hydropower Engineering,2015,46(10):17-21.
[13]李大鸣,陈硕,顾利军,等.桃林口水库下游山区洪水演进模拟和洪灾损失评估[J].长江科学院院报,2018,35(6):36-41.LI D M,CHEN S,GU L J,et al.Flood routing simulation and flood loss assessment for mountainous area in the downstream of Taolinkou Reservoir[J].Journal of Yangtze River Scientific Research Institute,2018,35(6):36-41.
[14]KOURGIALAS N N,KARATZAS G P.A hydro-economic modelling framework for flood damage estimation and the role of riparian vegetation[J].Hydrological Processes,2013,27(4):515-531.
[15]AMIREBRAHIMI S,RAJABIFARD A,MENDIS P,et al.Aframework for a microscale flood damage assessment and visualization for a building using BIM-GIS integration[J].International Journal of Digital Earth,2016,9(4):363-386.
[16]CHEN A S,HAMMOND M J,DJORDJEVIC'S,et al.From hazard to impact:flood damage assessment tools for mega cities[J].Natural Hazards,2016,82(2):857-890.
[17]KEFI M,MISHRA B K,KUMAR P,et al.Assessment of tangible direct flood damage using a spatial analysis approach under the effects of climate change:Case study in an urban watershed in Hanoi,Vietnam[J].International Journal of Geo-Information,2018,7(1):1-18.
[18]RASMUSSEN C E,WILLIAMS C K I.Gaussian processes for machine learning[M].The MIT Press,2006.
[19]VOZINAKI A E,KOURGIALAS N,KARATZAS G P.Estimating flood inundation and the consequent economic losses in the Koiliaris river basin in Crete,Greece[J].Global Nest Journal,2012,14(3):284-293.
[20]韩赜,林孝松,左倩云,等.山区镇域山洪灾害孕灾环境分区研究[J].重庆工商大学学报(自然科学版),2014,31(6):82-89.HAN Z,LIN X S,ZUO Q Y,et al.Research on torrent disaster development environment partition in mountainous town-region[J].Journal of Chongqing Technology and Business University(Natural Science Edition),2014,31(6):82-89.
[21]张念强.基于GIS的鄱阳湖地区洪水灾害风险评价[D].南昌:南昌大学,2006.ZHANG N Q.Evaluation of flood risk in Poyang Lake region basing on GIS[D].Nanchang:Nanchang University,2006.
[22]National ocean service[DB/OL].(2018-01-02)ftp://ftp.cdc.noaa.gov/Datasets/cpc_global_precip/[2018-07-03].
[23]中国科学院计算机网络信息中心国际科学数据镜像网站[DB/OL].(2019-09-16)[2018-07-03]http://www.gscloud.cn.
[24]国家减灾中心[EB/OL].(2018-01-04)[2018-07-03]http://www.jianzai.gov.cn/zxzq/index.jhtml.
[25]李宁,张正涛,陈曦,等.论自然灾害经济损失评估研究的重要性[J].地理科学进展,2017,36(2):256-263.LI N,ZHANG Z T,CHEN X,et al.Importance of economic loss evaluation in natural hazard and disaster research[J].Progress in Geography,2017,36(2):256-263.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |