基于气象因子的随机森林算法在湘中丘陵区林火预测中的应用
|
摘要
基于湘中丘陵区1988-2014气象观测数据和森林火灾历史数据,应用二项逻辑斯蒂回归模型和随机森林算法,将样本数据随机分成训练样本(60%)和测试样本(40%),重复5次拟合,将每次拟合中筛选出的显著特征变量组成全样本数据进行拟合及交叉验证,建立湖南水口山地区林火发生预测模型。结果表明,林火的发生与林分内日最小相对湿度、细小可燃物湿度码和干旱码显著相关;随机森林算法的预测精度在所有样本组合的模拟中均比二项逻辑斯蒂回归模型的预测精度高7%~10%,即使在交叉验证中,前者的预测精度也要高10%左右,表明随机森林算法具有一定的预测优势和现实应用价值,可用于湘中丘陵地区林火预测和决策管理。
Based on the meteorological data and historical data of forest fire between 1988 and 2014 in the hilly areas in central Hunan Province,logistic regression(LR)model and random forest(RF)algorithm were used to identify the relationship between fire occurrence and meteorological factors.Dataset was randomly divided into training(60%)and validation(40%)samples,fittings were repeated for 5 times,significant predictors which were screened out by each fitting were used to constitute complete samples to conduct fitting operation and cross validation,two methods were applied to establish fire prediction model for Shuikou mountainous area.The results indicated that daily minimum relative humidity,fine fuel moisture code(FFMC)and drought code(DC)had significant correlation with forest fire.In the simulation of all the samples,the prediction accuracy of RF was higher 7%-10% than that of LR.Even in the cross validation test,the former's prediction accuracy was also about 10% higher.Those results revealed that the RF model could be used in the fire prediction and decision management in the hilly areas in central Hunan Province.
Based on the meteorological data and historical data of forest fire between 1988 and 2014 in the hilly areas in central Hunan Province,logistic regression(LR)model and random forest(RF)algorithm were used to identify the relationship between fire occurrence and meteorological factors.Dataset was randomly divided into training(60%)and validation(40%)samples,fittings were repeated for 5 times,significant predictors which were screened out by each fitting were used to constitute complete samples to conduct fitting operation and cross validation,two methods were applied to establish fire prediction model for Shuikou mountainous area.The results indicated that daily minimum relative humidity,fine fuel moisture code(FFMC)and drought code(DC)had significant correlation with forest fire.In the simulation of all the samples,the prediction accuracy of RF was higher 7%-10% than that of LR.Even in the cross validation test,the former's prediction accuracy was also about 10% higher.Those results revealed that the RF model could be used in the fire prediction and decision management in the hilly areas in central Hunan Province.
引文
[1]CHAS-AMIL M L,PRESTEMON J P,MCCLEAN C J,et al.Human-ignited wildfire patterns and responses to policy shifts[J].Applied Geography,2015,56:164-176.
[2]张乃平,夏东海.自然灾害应急管理[M].北京:中国经济出版社,2009:304.
[3]ZHONG M,FAN W,LIU T,et al.Statistical analysis on current status of China forest fire safety[J].Fire Safety Journal,2003,38(3):257-269.
[4]HERAWATI H,SANTOSO H.Tropical forest susceptibility to and risk of fire under changing climate:a review of fire nature,policy and institutions in Indonesia[J].Forest Policy&Economics,2011,13(4):227-233.
[5]RANDERSON J T,FLANNER M G,JIN Y,et al.Supporting material:the impact of boreal forest fire on climate warming[J].Science,2006.314(5802):1130-1132.
[6]WESTERLING A L,HIDALGO H G,CAYAN D R,et al.Warming and earlier spring increase western U.S.forest wildfire activity[J].Science,2006,313:940-943.
[7]MARLON J R,BARTLEIN P J,GAVIN D G,et al.Long-term perspective on wildfires in the western USA[J].Proceedings of the National Academy of Sciences of the United States of America,2012,109(9):3203-3204.
[8]苏立娟,何友均,陈绍志.1950—2010年中国森林火灾时空特征及风险分析[J].林业科学,2015,51(1):88-96.SU L J,HE Y J,CHEN S Z.Temporal and spatial characteristics and risk analysis of forest fires in China from 1950to 2010[J].Scientia Silvae Sinicae,2015,51(1):88-96.(in Chinese)
[9]王明玉,舒立福,王秋华,等.中国南方冰雪灾害对森林火灾火发生短期影响分析——以湖南为例[J].林业科学,2008,44(11):64-68.WANG M Y,SHU L F,WANG Q H,et al.Forest fire occurrence in short term under the impacts of snow damage in south of China,a case study in Hunan Province[J].Scientia Silvae Sinicae,2008,44(11):64-68.(in Chinese)
[10]储昌超,张贵,孙玉荣.基于克里金方法的湖南森林火灾趋势预测研究[J].中南林业科技大学学报,2014,34(6):66-70.CHU C C,ZHANG G,SUN Y R.Trend forecast of forest fire in Hunan Province based on Kriging interpolation model[J].Journal of Central South University of Forestry&Technology,2014,34(6):66-70.(in Chinese)
[11]郭海峰,禹伟.湖南省森林火险天气等级预测模型研究[J].中南林业科技大学学报,2016,36(12):44-47,67.GUO H F,YU W.Study weather grade prediction model of forest-fire risk in Hunan Province[J].Journal of Central South University of Forestry&Technology,2016,36(12):44-47,67.(in Chinese)
[12]OLIVEIRA S,OEHLER F,SAN-MIGUEL-AYANZ J,et al.Modeling spatial patterns of fire occurrence in Mediterranean Europe using multiple regression and random forest[J].Forest Ecology&Management,2012,275(4):117-129.
[13]李欣海.随机森林模型在分类与回归分析中的应用[J].应用昆虫学报,2013,50(4):1190-1197.LI X H.Using“random forest”for classification and regression[J].Entomological Knowledge,2013,50(4):1190-1197.(in Chinese)
[14]张雷,王琳琳,张旭东,等.随机森林算法基本思想及其在生态学中的应用——以云南松分布模拟为例[J].生态学报,2014,34(3):650-659.ZHANG L,WANG L L,ZHANG X D,et al.The basic principle of random forest and its applications in ecology:a case study of Pinus yunnanensis[J].Acta Ecologica Sinica,2014,34(3):650-659.(in Chinese)
[15]FABRICIUS K E.Classification and regression trees:apowerful yet simple technique for ecological data analysis[J].Ecology,2000,81(11):3178-3192.
[16]LOUISR I,ANANTHAM P,STEPHENN M,et al.Estimating potential habitat for 134eastern US tree species under six climate scenarios[J].Forest Ecology&Management,2008,254(3):390-406.
[17]BREIMAN L.Random forest[J].Machine Learning,2001,45:5-32.
[18]王璟睿,沈文娟,李卫正,等.基于RapidEye的人工林生物量遥感反演模型性能对比[J].西北林学院学报,2015,30(6):196-202.WANG J R,SHEN W J,LI W Z,et al.Performances comparison of multiple non-linear models for estimating plantationsbiomass based on RapidEye imagery[J].Journal of Northwest Forestry University,2015,30(6):196-202.(in Chinese)
[19]CUTLER D R,EDWARDS T C,BEARD K H,et al.Random forests for classification in ecology[J].Ecology,2007,88(11):2783-92.
[20]RODRIGUES M,RIVA J D L.An insight into machine-learning algorithms to model human-caused wildfire occurrence[J].Environmental Modeling&Software,2014,57:192-201.
[21]张馨月,苏晓慧.四川省林火次数与气象因子的相关性研究[J].西北林学院学报,2017,32(3):176-180.ZHANG X Y,SU X H.Correlation analysis on forest fire occurring frequency and meteorological factors in Sichuan[J].Journal of Northwest Forestry University,2017,32(3):176-180.(in Chinese)
[22]WOTTON B M.Interpreting and using outputs from the Canadian forest fire danger rating system in research applications[J].Environmental&Ecological Statistics,2009,16(2):107-131.
[23]郭福涛,苏漳文,马祥庆,等.大兴安岭塔河地区雷击火发生驱动因子综合分析[J].生态学报,2015,35(19):6439-6448.GUO F T,SU Z W,MA X Q,et al.Climatic and non-climatic factors driving lightning-induced fire in Tahe,Daxing'an mountain[J].Acta Ecologica Sinica,2015,35(19):6439-6448.(in Chinese)
[24]张恒,金森,邸雪颖.基于FWI湿度码的塔河林业局地表凋落物含水率预测[J].应用生态学报,2014,25(7):2049-2055.ZHANG H,JIN S,DI X Y.Prediction of litter moisture content in Tahe forestry bureau of northeast China based on FWI moisture codes[J].Chinese Journal of Applied Ecology,2014,25(7):2049-2055.(in Chinese)
[25]信晓颖,江洪,周国模,等.加拿大森林火险气候指数系统(FWI)的原理及应用[J].浙江农林大学学报,2011,28(2):314-318.XIN X Y,JIANG H,ZHOU G M,et al.Canadian forest fire weather index(FWI)system:a review[J].Journal of Zhejiang A&F University,2011,28(2):314-318.(in Chinese)
[26]梁慧玲,林玉蕊,杨光,等.基于气象因子的随机森林算法在塔河地区林火预测中的应用[J].林业科学,2016,52(1):89-98.LIANG H L,LIN Y R,YANG G,et al.Application of random forest algorithm on the forest fire prediction in Tahe area based on meteorological factors[J].Scientia Silvae Sinicae,2016,52(1):89-98.(in Chinese)
[27]郭福涛,苏漳文,王光玉,等.我国北方针叶林人为火发生的预测模型[J].应用生态学报,2015,26(7):2099-2106.GUO F T,SU Z W,WANG G Y,et al.Prediction model of human-caused fire occurrence in the boreal forest of northern China[J].Chinese Journal of Applied Ecology,2015,26(7):2099-2106.(in Chinese)
[28]CHANG Y,ZHU Z,BU R,et al.Predicting fire occurrence patterns with logistic regression in Heilongjiang Province,China[J].Landscape Ecology,2013,28(10):1989-2004.
[29]孙瑜,史明昌,彭欢,等.基于MAXENT模型的黑龙江大兴安岭森林雷击火火险预测[J].应用生态学报,2014,25(4):1100-1106.SUN Y,SHI M C,PENG H,et al.Forest lighting fire forecasting for Daxinganling mountains based on MAXENT model[J].Chinese Journal of Applied Ecology,2014,25(4):1100-1106.(in Chinese)
[30]尹华,胡玉平.基于随机森林的不平衡特征选择算法[J].中山大学学报:自然科学版,2014,53(5):59-65.YIN H,HU Y P.An imbalanced feature selection algorithm based on random forest[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2014,53(5):59-65.(in Chinese)
[31]巩亚楠,帕提麦·马秉成,朱登浩,等.随机森林与Logistic回归在预约挂号失约影响因素预测中的应用[J].现代预防医学,2014,41(5):769-772.GONG Y N,PA T M,ZHU D H,et al.Application of random forests and logistic regression in prediction of influencing factors of missed appointment registration[J].Modern Preventive Medicine,2014,41(5):769-772.(in Chinese)
[32]彭国兰.随机森林在企业信用评估中的应用[D].厦门:厦门大学,2007.
[33]LIAW A,WIENER M.Classification and regression by random forest[J].R.News,2002,23:23.
[34]吕杰,汪康宁,李崇贵,等.基于小波变换和随机森林的森林类型分类研究[J].西北林学院学报,2016,31(6):264-267.LYU J,WANG K N,LI C G,et al.Classification of forest types based on discrete wavelet transform and random forests from GF-1images[J].Journal of Northwest Forestry University,2016,31(6):264-267.(in Chinese)
[35]GENUER R,POGGI J M,TULEAU-MALOT C.Variable selection using random forests[M].New York:Elsevier Science Inc.,2010.
[36]武晓岩,闫晓光,李康.基因表达数据的随机森林逐步判别分析方法[J].中国卫生统计,2007,24(2):151-154.WU X Y,YAN X G,LI K.The stepwise discriminant analysis of random forests used in gene expression data[J].Chinese Journal of Health Statistics,2007,24(2):151-154.(in Chinese)
[37]LITTELL J S,MCKENZIE D,PETERSON D L,et al.Climate and wildfire area burned in western USA ecoprovinces,1916-2003[J].Ecological Applications,2009,19(4):1003-1021.
[38]WOTTON B M,MARTELL D L,LOGAN K A.Climate change and People-caused forest fire occurrence in Ontario[J].Climatic Change,2003,60(3):275-295.
[39]FLANNIGAN M D,STOCKS B J,WOTTON B M.Forest fires and climate change[J].Science of the Total Environment,262:221-230.
[40]郭福涛,苏漳文,马祥庆,等.大兴安岭塔河地区雷击火发生驱动因子综合分析[J].生态学报,2015,35(19):6439-6448.GUO F T,SU Z W,MA Q X,et al.Climatic and non-climatic factors driving lightning-induced fire in Tahe,Daxing′an mountain[J].Acta Ecologica Sinica,2015,35(19):6439-6448.(in Chinese)
[41]CHANG Y,ZHU Z,BU R,et al.Predicting fire occurrence patterns with logistic regression in Heilongjiang Province,China[J].Landscape Ecology,2013,28(10):1989-2004.
[42]田晓瑞,MCRAE D J,舒立福,等.大兴安岭地区森林火险变化及FWI适用性评估[J].林业科学,2010,46(5):127-132.TIAN X R,Douglas J M,SHU L F,et al.Changes of forest fire danger and the evaluation of the FWI system application in the Daxinganling region[J].Scientia Silvae Sinicae,2010,46(5):127-132.(in Chinese)
[43]PAUSAS J G.Changes in fire and climate in the eastern iberian peninsula(mediterranean basin)[J].Climatic Change,2004,63(3):337-350.
[44]GUO F,SU Z,WANG G,et al.Wildfire ignition in the forests of southeast China:identifying drivers and spatial distribution to predict wildfire likelihood[J].Applied Geography,2016,66:12-21.
[45]STOCKS B J.Forest fires and sustainability in the boreal forests of Canada[J].Ambio,1998,27(7):545-550.
[46]RODRIGUES M,RIVA J D L,FOTHERINGHAM S.Modeling the spatial variation of the explanatory factors of humancaused wildfires in Spain using geographically weighted logistic regression[J].Applied Geography,2014,48(48):52-63.
[47]SAEFUDDIN A,SETIABUDI N A,FITRIANTO A.On comparison between logistic regression and geographically weighted logistic regression:with application to indonesian poverty data[J].World Applied Sciences Journal,2012,19(2):205-210.
[48]赵玉,王红,张珍珍.基于遥感光谱和空间变量随机森林的黄河三角洲刺槐林健康等级分类[J].遥感技术与应用,2016,31(2):359-367.ZHAO Y,WANG H,ZHANG Z Z.Forest healthy classification of robinia pseudoacacia in the Yellow River Delta,China based on spectral and spatial remote sensing variables using random forest[J].Remote Sensing Technology and Application,2016,31(2):359-367.(in Chinese)
[49]赵铜铁钢,杨大文,蔡喜明,等.基于随机森林模型的长江上游枯水期径流预报研究[J].水力发电学报,2012,31(3):18-24,38.ZHAO T T G,YANG D W,CAI X M,et al.Predict seasonal low flows in the upper Yangtze River using random forests model[J].Journal of Hydroelectric Engineering,2012,31(3):18-24,38.(in Chinese)
[50]赖成光,陈晓宏,赵仕威,等.基于随机森林的洪灾风险评价模型及其应用[J].水利学报,2015,46(1):58-66.LAI C G,CHEN X H,ZHAO S W,et al.A flood risk assessment model based on random forest and its application[J].Journal of Hydraluic Engineering,2015,46(1):58-66.(in Chinese)
[2]张乃平,夏东海.自然灾害应急管理[M].北京:中国经济出版社,2009:304.
[3]ZHONG M,FAN W,LIU T,et al.Statistical analysis on current status of China forest fire safety[J].Fire Safety Journal,2003,38(3):257-269.
[4]HERAWATI H,SANTOSO H.Tropical forest susceptibility to and risk of fire under changing climate:a review of fire nature,policy and institutions in Indonesia[J].Forest Policy&Economics,2011,13(4):227-233.
[5]RANDERSON J T,FLANNER M G,JIN Y,et al.Supporting material:the impact of boreal forest fire on climate warming[J].Science,2006.314(5802):1130-1132.
[6]WESTERLING A L,HIDALGO H G,CAYAN D R,et al.Warming and earlier spring increase western U.S.forest wildfire activity[J].Science,2006,313:940-943.
[7]MARLON J R,BARTLEIN P J,GAVIN D G,et al.Long-term perspective on wildfires in the western USA[J].Proceedings of the National Academy of Sciences of the United States of America,2012,109(9):3203-3204.
[8]苏立娟,何友均,陈绍志.1950—2010年中国森林火灾时空特征及风险分析[J].林业科学,2015,51(1):88-96.SU L J,HE Y J,CHEN S Z.Temporal and spatial characteristics and risk analysis of forest fires in China from 1950to 2010[J].Scientia Silvae Sinicae,2015,51(1):88-96.(in Chinese)
[9]王明玉,舒立福,王秋华,等.中国南方冰雪灾害对森林火灾火发生短期影响分析——以湖南为例[J].林业科学,2008,44(11):64-68.WANG M Y,SHU L F,WANG Q H,et al.Forest fire occurrence in short term under the impacts of snow damage in south of China,a case study in Hunan Province[J].Scientia Silvae Sinicae,2008,44(11):64-68.(in Chinese)
[10]储昌超,张贵,孙玉荣.基于克里金方法的湖南森林火灾趋势预测研究[J].中南林业科技大学学报,2014,34(6):66-70.CHU C C,ZHANG G,SUN Y R.Trend forecast of forest fire in Hunan Province based on Kriging interpolation model[J].Journal of Central South University of Forestry&Technology,2014,34(6):66-70.(in Chinese)
[11]郭海峰,禹伟.湖南省森林火险天气等级预测模型研究[J].中南林业科技大学学报,2016,36(12):44-47,67.GUO H F,YU W.Study weather grade prediction model of forest-fire risk in Hunan Province[J].Journal of Central South University of Forestry&Technology,2016,36(12):44-47,67.(in Chinese)
[12]OLIVEIRA S,OEHLER F,SAN-MIGUEL-AYANZ J,et al.Modeling spatial patterns of fire occurrence in Mediterranean Europe using multiple regression and random forest[J].Forest Ecology&Management,2012,275(4):117-129.
[13]李欣海.随机森林模型在分类与回归分析中的应用[J].应用昆虫学报,2013,50(4):1190-1197.LI X H.Using“random forest”for classification and regression[J].Entomological Knowledge,2013,50(4):1190-1197.(in Chinese)
[14]张雷,王琳琳,张旭东,等.随机森林算法基本思想及其在生态学中的应用——以云南松分布模拟为例[J].生态学报,2014,34(3):650-659.ZHANG L,WANG L L,ZHANG X D,et al.The basic principle of random forest and its applications in ecology:a case study of Pinus yunnanensis[J].Acta Ecologica Sinica,2014,34(3):650-659.(in Chinese)
[15]FABRICIUS K E.Classification and regression trees:apowerful yet simple technique for ecological data analysis[J].Ecology,2000,81(11):3178-3192.
[16]LOUISR I,ANANTHAM P,STEPHENN M,et al.Estimating potential habitat for 134eastern US tree species under six climate scenarios[J].Forest Ecology&Management,2008,254(3):390-406.
[17]BREIMAN L.Random forest[J].Machine Learning,2001,45:5-32.
[18]王璟睿,沈文娟,李卫正,等.基于RapidEye的人工林生物量遥感反演模型性能对比[J].西北林学院学报,2015,30(6):196-202.WANG J R,SHEN W J,LI W Z,et al.Performances comparison of multiple non-linear models for estimating plantationsbiomass based on RapidEye imagery[J].Journal of Northwest Forestry University,2015,30(6):196-202.(in Chinese)
[19]CUTLER D R,EDWARDS T C,BEARD K H,et al.Random forests for classification in ecology[J].Ecology,2007,88(11):2783-92.
[20]RODRIGUES M,RIVA J D L.An insight into machine-learning algorithms to model human-caused wildfire occurrence[J].Environmental Modeling&Software,2014,57:192-201.
[21]张馨月,苏晓慧.四川省林火次数与气象因子的相关性研究[J].西北林学院学报,2017,32(3):176-180.ZHANG X Y,SU X H.Correlation analysis on forest fire occurring frequency and meteorological factors in Sichuan[J].Journal of Northwest Forestry University,2017,32(3):176-180.(in Chinese)
[22]WOTTON B M.Interpreting and using outputs from the Canadian forest fire danger rating system in research applications[J].Environmental&Ecological Statistics,2009,16(2):107-131.
[23]郭福涛,苏漳文,马祥庆,等.大兴安岭塔河地区雷击火发生驱动因子综合分析[J].生态学报,2015,35(19):6439-6448.GUO F T,SU Z W,MA X Q,et al.Climatic and non-climatic factors driving lightning-induced fire in Tahe,Daxing'an mountain[J].Acta Ecologica Sinica,2015,35(19):6439-6448.(in Chinese)
[24]张恒,金森,邸雪颖.基于FWI湿度码的塔河林业局地表凋落物含水率预测[J].应用生态学报,2014,25(7):2049-2055.ZHANG H,JIN S,DI X Y.Prediction of litter moisture content in Tahe forestry bureau of northeast China based on FWI moisture codes[J].Chinese Journal of Applied Ecology,2014,25(7):2049-2055.(in Chinese)
[25]信晓颖,江洪,周国模,等.加拿大森林火险气候指数系统(FWI)的原理及应用[J].浙江农林大学学报,2011,28(2):314-318.XIN X Y,JIANG H,ZHOU G M,et al.Canadian forest fire weather index(FWI)system:a review[J].Journal of Zhejiang A&F University,2011,28(2):314-318.(in Chinese)
[26]梁慧玲,林玉蕊,杨光,等.基于气象因子的随机森林算法在塔河地区林火预测中的应用[J].林业科学,2016,52(1):89-98.LIANG H L,LIN Y R,YANG G,et al.Application of random forest algorithm on the forest fire prediction in Tahe area based on meteorological factors[J].Scientia Silvae Sinicae,2016,52(1):89-98.(in Chinese)
[27]郭福涛,苏漳文,王光玉,等.我国北方针叶林人为火发生的预测模型[J].应用生态学报,2015,26(7):2099-2106.GUO F T,SU Z W,WANG G Y,et al.Prediction model of human-caused fire occurrence in the boreal forest of northern China[J].Chinese Journal of Applied Ecology,2015,26(7):2099-2106.(in Chinese)
[28]CHANG Y,ZHU Z,BU R,et al.Predicting fire occurrence patterns with logistic regression in Heilongjiang Province,China[J].Landscape Ecology,2013,28(10):1989-2004.
[29]孙瑜,史明昌,彭欢,等.基于MAXENT模型的黑龙江大兴安岭森林雷击火火险预测[J].应用生态学报,2014,25(4):1100-1106.SUN Y,SHI M C,PENG H,et al.Forest lighting fire forecasting for Daxinganling mountains based on MAXENT model[J].Chinese Journal of Applied Ecology,2014,25(4):1100-1106.(in Chinese)
[30]尹华,胡玉平.基于随机森林的不平衡特征选择算法[J].中山大学学报:自然科学版,2014,53(5):59-65.YIN H,HU Y P.An imbalanced feature selection algorithm based on random forest[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2014,53(5):59-65.(in Chinese)
[31]巩亚楠,帕提麦·马秉成,朱登浩,等.随机森林与Logistic回归在预约挂号失约影响因素预测中的应用[J].现代预防医学,2014,41(5):769-772.GONG Y N,PA T M,ZHU D H,et al.Application of random forests and logistic regression in prediction of influencing factors of missed appointment registration[J].Modern Preventive Medicine,2014,41(5):769-772.(in Chinese)
[32]彭国兰.随机森林在企业信用评估中的应用[D].厦门:厦门大学,2007.
[33]LIAW A,WIENER M.Classification and regression by random forest[J].R.News,2002,23:23.
[34]吕杰,汪康宁,李崇贵,等.基于小波变换和随机森林的森林类型分类研究[J].西北林学院学报,2016,31(6):264-267.LYU J,WANG K N,LI C G,et al.Classification of forest types based on discrete wavelet transform and random forests from GF-1images[J].Journal of Northwest Forestry University,2016,31(6):264-267.(in Chinese)
[35]GENUER R,POGGI J M,TULEAU-MALOT C.Variable selection using random forests[M].New York:Elsevier Science Inc.,2010.
[36]武晓岩,闫晓光,李康.基因表达数据的随机森林逐步判别分析方法[J].中国卫生统计,2007,24(2):151-154.WU X Y,YAN X G,LI K.The stepwise discriminant analysis of random forests used in gene expression data[J].Chinese Journal of Health Statistics,2007,24(2):151-154.(in Chinese)
[37]LITTELL J S,MCKENZIE D,PETERSON D L,et al.Climate and wildfire area burned in western USA ecoprovinces,1916-2003[J].Ecological Applications,2009,19(4):1003-1021.
[38]WOTTON B M,MARTELL D L,LOGAN K A.Climate change and People-caused forest fire occurrence in Ontario[J].Climatic Change,2003,60(3):275-295.
[39]FLANNIGAN M D,STOCKS B J,WOTTON B M.Forest fires and climate change[J].Science of the Total Environment,262:221-230.
[40]郭福涛,苏漳文,马祥庆,等.大兴安岭塔河地区雷击火发生驱动因子综合分析[J].生态学报,2015,35(19):6439-6448.GUO F T,SU Z W,MA Q X,et al.Climatic and non-climatic factors driving lightning-induced fire in Tahe,Daxing′an mountain[J].Acta Ecologica Sinica,2015,35(19):6439-6448.(in Chinese)
[41]CHANG Y,ZHU Z,BU R,et al.Predicting fire occurrence patterns with logistic regression in Heilongjiang Province,China[J].Landscape Ecology,2013,28(10):1989-2004.
[42]田晓瑞,MCRAE D J,舒立福,等.大兴安岭地区森林火险变化及FWI适用性评估[J].林业科学,2010,46(5):127-132.TIAN X R,Douglas J M,SHU L F,et al.Changes of forest fire danger and the evaluation of the FWI system application in the Daxinganling region[J].Scientia Silvae Sinicae,2010,46(5):127-132.(in Chinese)
[43]PAUSAS J G.Changes in fire and climate in the eastern iberian peninsula(mediterranean basin)[J].Climatic Change,2004,63(3):337-350.
[44]GUO F,SU Z,WANG G,et al.Wildfire ignition in the forests of southeast China:identifying drivers and spatial distribution to predict wildfire likelihood[J].Applied Geography,2016,66:12-21.
[45]STOCKS B J.Forest fires and sustainability in the boreal forests of Canada[J].Ambio,1998,27(7):545-550.
[46]RODRIGUES M,RIVA J D L,FOTHERINGHAM S.Modeling the spatial variation of the explanatory factors of humancaused wildfires in Spain using geographically weighted logistic regression[J].Applied Geography,2014,48(48):52-63.
[47]SAEFUDDIN A,SETIABUDI N A,FITRIANTO A.On comparison between logistic regression and geographically weighted logistic regression:with application to indonesian poverty data[J].World Applied Sciences Journal,2012,19(2):205-210.
[48]赵玉,王红,张珍珍.基于遥感光谱和空间变量随机森林的黄河三角洲刺槐林健康等级分类[J].遥感技术与应用,2016,31(2):359-367.ZHAO Y,WANG H,ZHANG Z Z.Forest healthy classification of robinia pseudoacacia in the Yellow River Delta,China based on spectral and spatial remote sensing variables using random forest[J].Remote Sensing Technology and Application,2016,31(2):359-367.(in Chinese)
[49]赵铜铁钢,杨大文,蔡喜明,等.基于随机森林模型的长江上游枯水期径流预报研究[J].水力发电学报,2012,31(3):18-24,38.ZHAO T T G,YANG D W,CAI X M,et al.Predict seasonal low flows in the upper Yangtze River using random forests model[J].Journal of Hydroelectric Engineering,2012,31(3):18-24,38.(in Chinese)
[50]赖成光,陈晓宏,赵仕威,等.基于随机森林的洪灾风险评价模型及其应用[J].水利学报,2015,46(1):58-66.LAI C G,CHEN X H,ZHAO S W,et al.A flood risk assessment model based on random forest and its application[J].Journal of Hydraluic Engineering,2015,46(1):58-66.(in Chinese)