基于BP神经网络的宁波市台风灾情预估模型研究
|
摘要
选取1949—2015年间对宁波市影响较大、灾情记录完整的58个台风样本,基于灾损数据,采用灰色关联分析法建立台风灾情关联度,选取台风灾害致灾因子、台风灾情综合关联度,利用BP神经网络建立台风灾情预估模型。结果表明,利用台风灾情关联度评估台风灾情大小合理可用,台风灾害致灾因子与灾情评价指标及台风灾情综合关联度间均存在一定的相关性,利用BP神经网络预估模型对台风灾情预估效果较好,其中训练样本、测试样本的模拟值与实际值相关系数分别达到0. 94、0. 865,均通过了0. 01信度的显著性检验,训练集、测试集灾情级别预报一致率为85. 3%、77. 8%,相关研究成果可为政府决策部门的抗台减灾工作提供科学依据。
Expending 58 typhoon cases that had the considerable effect on Ningbo and had finish catastrophe records from 1949 to 2015.In viewof the information of the calamity,the comprehensive correlation degree of typhoon disaster(Roj)was set up by utilizing the grey relational investigation technique.Choosing the disaster-causing factors of typhoon andpoint build disaster pre-assessment technique of typhoon disaster by utilizing BP neural network(BP).The outcomes demonstrated that,the severity of typhoon which evaluated byreasonable and available.There is a significant correlation between typhoon disaster risk factors and disaster assessment indicators as well aspre-evaluation model of BP is useful for predicting typhoon disaster;the correlation coefficient linking the simulated value and the actual value of the training set and the test set respectively reached0.94 and 0.896 and both achieved the confidence interval of 0.01.The consensus rate of the disaster level forecast of the training set and the test set is 85.3%and 77.8%respectively.This investigate outcomes could provide scientific premise to counter the typhoon work of government decision-making divisions.
Expending 58 typhoon cases that had the considerable effect on Ningbo and had finish catastrophe records from 1949 to 2015.In viewof the information of the calamity,the comprehensive correlation degree of typhoon disaster(Roj)was set up by utilizing the grey relational investigation technique.Choosing the disaster-causing factors of typhoon andpoint build disaster pre-assessment technique of typhoon disaster by utilizing BP neural network(BP).The outcomes demonstrated that,the severity of typhoon which evaluated byreasonable and available.There is a significant correlation between typhoon disaster risk factors and disaster assessment indicators as well aspre-evaluation model of BP is useful for predicting typhoon disaster;the correlation coefficient linking the simulated value and the actual value of the training set and the test set respectively reached0.94 and 0.896 and both achieved the confidence interval of 0.01.The consensus rate of the disaster level forecast of the training set and the test set is 85.3%and 77.8%respectively.This investigate outcomes could provide scientific premise to counter the typhoon work of government decision-making divisions.
引文
Blaikie P,Cannon T,Davis I,et al.,1994.At risk:natural hazards,people's vulnerability and disasters[M].London:Routledge:30-35.
陈仕鸿,隋广军,阳爱民,2013.广东台风灾情预测系统研究[J].自然灾害学报,3:50-55.Chen S H,Sui G J,Yang A M,2013.Research on typhoon disaster condition forecasting system of Guangdong Province[J].Journal of Natural Disasters,3:50-55.(in Chinese).
陈有利,钱燕珍,胡波,等,2017.宁波市主要气象灾害风险评估与区划[M].北京:气象出版社:103-105.Chen Y L,Qian Y Z,Hu B,et al.,2017.Risk assessment and zoning of major meteorological disasters in Ningbo City[M].Beijing:China Meteorological Press:103-105.(in Chinese).
邓聚龙,1987.灰色系统基本方法[M].武汉:华中理工大学出版社:11-13.Deng J L,1987.The basic methodology gray system[M].Wuhan:Huazhong University of Science and Technology Press:11-13.(in Chinese).
Dorland C,Tol R S J,Olsthoorn A A,et al.,1998.Impacts of windstorms in the Netherlands:present risk and prospects for climate change[M].London:Routledge:45-47.
端义宏,陈联寿,许映龙,等,2012.我国台风监测预报预警体系的现状及建议[J].中国工程科学,14(9):4-9.Duan Y H,Chen L S,Xu Y L,et al.,2012.The status and suggestions of the improvement in the typhoon observation forecasting and warning systems in China[J].Engineering Sciences,14(9):4-9.(in Chinese).
冯利华,1993.灾害损失的定量计算[J].灾害学(2):17-19.Feng L H,1993.Quantitative calculation of disasters loss[J].Journal of Catastrophology(2):17-19.(in Chinese).
官莉,刘旸,张雪慧,2010.人工神经网络算法在红外高光谱资料反演大气温度廓线中的应用[J].大气科学学报,33(3):341-346.Guan L,Liu Y,Zhang X H,2010.Application of artificial neural network algorithm in retrieving atmospheric temperature profiles from hyperspectral infrared data[J].Trans Atmos Sci,33(3):341-346.(in Chinese).
Hastie T,Tibshiran R,Friedman J.2004.统计学习基础:数据挖掘、推理与预测[M].北京:电子工业出版社:135-155.Hastie T,Tibshiran R,Friedman J,2004.The Elements of Statistical Learning:Data Mining,Inference and Prediction[M].Beijing:Publishing House of Electronics Industry,2004:135-155.(in Chinese).
Huang Z,Rosowsky D V,Sparks P R,2001.Long-term hurricane risk assessment and expected damage to residential structures[J].Reliability Engineering&System Safety,74(3):239-249.
Howard R A,Matheson J E,Nroth D W,1972.The decision to seed hurricans[J].Science,176(4040):1191-1202.
雷小途,陈佩燕,杨玉华,等,2009.中国台风灾情特征及其灾害客观评估方法[J].气象学报,67(5):875-883.Lei X T,Chen P Y,Yang Y H,etal.,2009.Characters and objective assessment of disasters caused by typhoons in China[J].Acta Meteorologica Sinica,67(5):875-883.(in Chinese).
李秀红,2007.基于灰色关联度的多目标决策模型与应用[J].山东大学学报(理学版),42(12):33-36.LI X H,2007.A model based on the grey relation grade for multi-objective decision-making and its application[J].Journal of Shandong University(Natural Science),42(12):33-36.(in Chinese).
刘少军,张京红,何政伟,等,2012.改进的物元可拓模型在台风灾害预评估中的应用[J].自然灾害学报,2:135-141.Liu S J,Zhang J H,He ZW,et al.,2012.Application of improved matter-element extension model to typhoon disaster pre-assessment[J].Journal of Natural Disasters,2:135-141.(in Chinese).
柳岳清,胡淳焓,周国华,2012.影响丽水的台风路径及灾害风险特征[J].科技通报,28(1):39-43.Liu Y Q,Hu C H,Zhou G H,2012.Track and disaster characteristics induced by Typhoon of Lishui[J].Bulletin of Science&Technology,28(1):39-43.(in Chinese).
牛海燕,刘敏,陆敏,等,2011.中国沿海地区台风致灾因子危险性评估[J].华东师范大学学报(自然科学版)(6):20-25.Niu H Y,Liu M,Lu M,et al.,2011.Risk assessment of typhoon hazard factors in China coastal areas[J].Journal of East China Normal University(Natural Science)(6):20-25.(in Chinese).
祁秀香,智协飞,2009.0601号登陆台风及暴雨减弱消亡过程中的动能收支分析[J].大气科学学报,32(6):824-831.Qi X X,Zhi X F,2009.Kinetic Energy Budget Analysis during Decaying of 0601 Landfall Typhoon and Storm Rainfall[J].Trans Atmos Sci,32(6):824-831.(in Chinese).
钱燕珍,郑梅迪,张程明,等,2018.宁波台风预报与服务[M].北京:气象出版社:25-31.Qian Y Z,Zheng MD,Zhang C M,et al.,2018.Typhoon forecast and service in Ningbo[M].Beijing:China Meteorological Press:25-31.(in Chinese).
Rumelhart D E,Hinton G E,Williams R J,1986.Learning representations by back-propagating errors[J].323(6088):399-421.
孙照渤,谭桂容,赵振国,等,2013.中国东部夏季雨型的人工神经网络集合预测[J].大气科学学报,36(1):1-6.Sun Z B,Tan G R,Zhao Z G,et al.,2013.Ensemble prediction of summer rainfall patterns over eastern China based on artificial neural networks[J].Trans Atmos Sci,36(1):1-6.(in Chinese).
Thom H,Marshall R,1971.Wind and surge damage due to Hurricane Camille[J].Journal of the Waterways Harbors&Coastal Engineering Division,97:355-363.
Vickery P J,Skerlj P F,Twisdale L A,2000.Simulation of hurricane risk in the U.S.using empirical track model[J].Journal of Structural Engineering,126(10):1222-1237.
王秀荣,王维国,马清云,2010.台风灾害综合等级评估模型及应用[J].气象,36(1):66-71.Wang X R,Wang W G,Ma Q Y,2010.Model for general grade division of typhoon disasters and application[J].Meteor Mont,36(1):66-71.(in Chinese).
Warner B,Misra M,1996.Understanding neural networks as statistical tools[J].The American Statistician,50(4):284-293.
温姗姗,翟建青,Thomas F,等,2017.1984-2014年影响中国热带气旋的经济损失标准化及其变化特征[J].热带气象学报,33(4):478-487.Wen S S,Zhai J Q,Thomas F,et al.,2017.Variation of normalized economic losses from influential tropical cyclones in China for 1984-2014[J].J Trop Meteor,33(4):478-487.
徐良炎,1994.我国台风灾害的初步分析[J].气象,20(10):50-55.Xu L Y,1994.An Analysis of typhoon Disasters in China[J].Meteor Mon,20(10):50-55.(in Chinese).
杨仕升,1997.自然灾害等级划分及灾情比较模型探讨[J].自然灾害学报(1):8-13.Yang S S,1997.Study on the model of grade division of natural disaster and comparison of disastrous conditions[J].Journal of Natural Disasters(1):8-13.(in Chinese).
殷洁,戴尔阜,吴绍洪,等,2013.中国台风强度等级与可能灾害损失标准研究[J].地理研究,32(2):266-274.Yin J,Dai E F,Wu S H,et al.,2013.A study on the relationship between typhoon intensity grade and disaster loss in China[J].Geographical Research,32(2):266-274.(in Chinese).
张颖超,张美娟,张中秋,等,2013.浙江省登陆热带气旋灾害影响评估[J].大气科学学报,36(2):229-234.Zhang Y C,Zhang MJ,Zhang Z Q,et al.,2013.Evaluation 0n disaster influence of tropical cyclone landing over Zhejiang Province[J].Trans Atmos Sci,36(2):229-234.(in Chinese).
智协飞,季晓东,张璟,等,2013.基于TIGGE资料的地面气温和降水的多模式集成预报[J].大气科学学报,36(3):257-266.Zhi X F,Ji X D,Zhang J,et al.,2013.Multi model ensemble forecasts of surface air temperature and precipitation using TIGGE datasets[J].Trans Atmos Sci,36(3):257-266.(in Chinese).
陈仕鸿,隋广军,阳爱民,2013.广东台风灾情预测系统研究[J].自然灾害学报,3:50-55.Chen S H,Sui G J,Yang A M,2013.Research on typhoon disaster condition forecasting system of Guangdong Province[J].Journal of Natural Disasters,3:50-55.(in Chinese).
陈有利,钱燕珍,胡波,等,2017.宁波市主要气象灾害风险评估与区划[M].北京:气象出版社:103-105.Chen Y L,Qian Y Z,Hu B,et al.,2017.Risk assessment and zoning of major meteorological disasters in Ningbo City[M].Beijing:China Meteorological Press:103-105.(in Chinese).
邓聚龙,1987.灰色系统基本方法[M].武汉:华中理工大学出版社:11-13.Deng J L,1987.The basic methodology gray system[M].Wuhan:Huazhong University of Science and Technology Press:11-13.(in Chinese).
Dorland C,Tol R S J,Olsthoorn A A,et al.,1998.Impacts of windstorms in the Netherlands:present risk and prospects for climate change[M].London:Routledge:45-47.
端义宏,陈联寿,许映龙,等,2012.我国台风监测预报预警体系的现状及建议[J].中国工程科学,14(9):4-9.Duan Y H,Chen L S,Xu Y L,et al.,2012.The status and suggestions of the improvement in the typhoon observation forecasting and warning systems in China[J].Engineering Sciences,14(9):4-9.(in Chinese).
冯利华,1993.灾害损失的定量计算[J].灾害学(2):17-19.Feng L H,1993.Quantitative calculation of disasters loss[J].Journal of Catastrophology(2):17-19.(in Chinese).
官莉,刘旸,张雪慧,2010.人工神经网络算法在红外高光谱资料反演大气温度廓线中的应用[J].大气科学学报,33(3):341-346.Guan L,Liu Y,Zhang X H,2010.Application of artificial neural network algorithm in retrieving atmospheric temperature profiles from hyperspectral infrared data[J].Trans Atmos Sci,33(3):341-346.(in Chinese).
Hastie T,Tibshiran R,Friedman J.2004.统计学习基础:数据挖掘、推理与预测[M].北京:电子工业出版社:135-155.Hastie T,Tibshiran R,Friedman J,2004.The Elements of Statistical Learning:Data Mining,Inference and Prediction[M].Beijing:Publishing House of Electronics Industry,2004:135-155.(in Chinese).
Huang Z,Rosowsky D V,Sparks P R,2001.Long-term hurricane risk assessment and expected damage to residential structures[J].Reliability Engineering&System Safety,74(3):239-249.
Howard R A,Matheson J E,Nroth D W,1972.The decision to seed hurricans[J].Science,176(4040):1191-1202.
雷小途,陈佩燕,杨玉华,等,2009.中国台风灾情特征及其灾害客观评估方法[J].气象学报,67(5):875-883.Lei X T,Chen P Y,Yang Y H,etal.,2009.Characters and objective assessment of disasters caused by typhoons in China[J].Acta Meteorologica Sinica,67(5):875-883.(in Chinese).
李秀红,2007.基于灰色关联度的多目标决策模型与应用[J].山东大学学报(理学版),42(12):33-36.LI X H,2007.A model based on the grey relation grade for multi-objective decision-making and its application[J].Journal of Shandong University(Natural Science),42(12):33-36.(in Chinese).
刘少军,张京红,何政伟,等,2012.改进的物元可拓模型在台风灾害预评估中的应用[J].自然灾害学报,2:135-141.Liu S J,Zhang J H,He ZW,et al.,2012.Application of improved matter-element extension model to typhoon disaster pre-assessment[J].Journal of Natural Disasters,2:135-141.(in Chinese).
柳岳清,胡淳焓,周国华,2012.影响丽水的台风路径及灾害风险特征[J].科技通报,28(1):39-43.Liu Y Q,Hu C H,Zhou G H,2012.Track and disaster characteristics induced by Typhoon of Lishui[J].Bulletin of Science&Technology,28(1):39-43.(in Chinese).
牛海燕,刘敏,陆敏,等,2011.中国沿海地区台风致灾因子危险性评估[J].华东师范大学学报(自然科学版)(6):20-25.Niu H Y,Liu M,Lu M,et al.,2011.Risk assessment of typhoon hazard factors in China coastal areas[J].Journal of East China Normal University(Natural Science)(6):20-25.(in Chinese).
祁秀香,智协飞,2009.0601号登陆台风及暴雨减弱消亡过程中的动能收支分析[J].大气科学学报,32(6):824-831.Qi X X,Zhi X F,2009.Kinetic Energy Budget Analysis during Decaying of 0601 Landfall Typhoon and Storm Rainfall[J].Trans Atmos Sci,32(6):824-831.(in Chinese).
钱燕珍,郑梅迪,张程明,等,2018.宁波台风预报与服务[M].北京:气象出版社:25-31.Qian Y Z,Zheng MD,Zhang C M,et al.,2018.Typhoon forecast and service in Ningbo[M].Beijing:China Meteorological Press:25-31.(in Chinese).
Rumelhart D E,Hinton G E,Williams R J,1986.Learning representations by back-propagating errors[J].323(6088):399-421.
孙照渤,谭桂容,赵振国,等,2013.中国东部夏季雨型的人工神经网络集合预测[J].大气科学学报,36(1):1-6.Sun Z B,Tan G R,Zhao Z G,et al.,2013.Ensemble prediction of summer rainfall patterns over eastern China based on artificial neural networks[J].Trans Atmos Sci,36(1):1-6.(in Chinese).
Thom H,Marshall R,1971.Wind and surge damage due to Hurricane Camille[J].Journal of the Waterways Harbors&Coastal Engineering Division,97:355-363.
Vickery P J,Skerlj P F,Twisdale L A,2000.Simulation of hurricane risk in the U.S.using empirical track model[J].Journal of Structural Engineering,126(10):1222-1237.
王秀荣,王维国,马清云,2010.台风灾害综合等级评估模型及应用[J].气象,36(1):66-71.Wang X R,Wang W G,Ma Q Y,2010.Model for general grade division of typhoon disasters and application[J].Meteor Mont,36(1):66-71.(in Chinese).
Warner B,Misra M,1996.Understanding neural networks as statistical tools[J].The American Statistician,50(4):284-293.
温姗姗,翟建青,Thomas F,等,2017.1984-2014年影响中国热带气旋的经济损失标准化及其变化特征[J].热带气象学报,33(4):478-487.Wen S S,Zhai J Q,Thomas F,et al.,2017.Variation of normalized economic losses from influential tropical cyclones in China for 1984-2014[J].J Trop Meteor,33(4):478-487.
徐良炎,1994.我国台风灾害的初步分析[J].气象,20(10):50-55.Xu L Y,1994.An Analysis of typhoon Disasters in China[J].Meteor Mon,20(10):50-55.(in Chinese).
杨仕升,1997.自然灾害等级划分及灾情比较模型探讨[J].自然灾害学报(1):8-13.Yang S S,1997.Study on the model of grade division of natural disaster and comparison of disastrous conditions[J].Journal of Natural Disasters(1):8-13.(in Chinese).
殷洁,戴尔阜,吴绍洪,等,2013.中国台风强度等级与可能灾害损失标准研究[J].地理研究,32(2):266-274.Yin J,Dai E F,Wu S H,et al.,2013.A study on the relationship between typhoon intensity grade and disaster loss in China[J].Geographical Research,32(2):266-274.(in Chinese).
张颖超,张美娟,张中秋,等,2013.浙江省登陆热带气旋灾害影响评估[J].大气科学学报,36(2):229-234.Zhang Y C,Zhang MJ,Zhang Z Q,et al.,2013.Evaluation 0n disaster influence of tropical cyclone landing over Zhejiang Province[J].Trans Atmos Sci,36(2):229-234.(in Chinese).
智协飞,季晓东,张璟,等,2013.基于TIGGE资料的地面气温和降水的多模式集成预报[J].大气科学学报,36(3):257-266.Zhi X F,Ji X D,Zhang J,et al.,2013.Multi model ensemble forecasts of surface air temperature and precipitation using TIGGE datasets[J].Trans Atmos Sci,36(3):257-266.(in Chinese).