结合随机森林与K-means聚类评价湿地火烧严重程度
|
摘要
针对湿地植被存在典型的季节及年际变化特征,常用的遥感识别手段无法对湿地火烧严重程度实现准确评价的问题,提出了一种适用于湿地火烧严重程度的评价方法。基于2001年9月扎龙湿地的火灾事件,应用K-means聚类分析,从季节与年际2个方面的NBR阈值中获取不同火烧严重程度的训练样本,并利用随机森林机器学习算法建立基于光谱指数的分类模型,从而实现了湿地火烧严重程度的准确制图与评价。结果表明,交叉验证的分类总体精度为89.9%,各个火烧严重程度之间未出现严重的混分情况,且该模型具有一定的可移植性,能够成功地用于湿地火灾研究,从而为湿地火灾管理提供相应的参考依据。
In view of the special seasonal and annual variation of wetland vegetation,the common remote sensing method is insufficient to assess wetland fire severity as accurate as possible.Therefore,an approach that is suitable for the assessment of wetland fire severity should be developed.This study presented a remote sensing approach to evaluate fire severity using the fire event information of Zhalong wetland in September 2001.The training samples of different fire severities were collected by K-means clustering analysis.The performance of nine spectral indices was assessed before implementation of the random forest machine learning algorithm.The 10-fold cross-validation result showed that the overall accuracy was 89.9%.There was no serious confusion among different fire severity levels,and the classification model can also be applied to another date with fire occurrences across the study area.Therefore,the remote sensing method that we presented can be successfully applied in wetland fire research,which could provide some valuable suggestions for wetland fire management.
In view of the special seasonal and annual variation of wetland vegetation,the common remote sensing method is insufficient to assess wetland fire severity as accurate as possible.Therefore,an approach that is suitable for the assessment of wetland fire severity should be developed.This study presented a remote sensing approach to evaluate fire severity using the fire event information of Zhalong wetland in September 2001.The training samples of different fire severities were collected by K-means clustering analysis.The performance of nine spectral indices was assessed before implementation of the random forest machine learning algorithm.The 10-fold cross-validation result showed that the overall accuracy was 89.9%.There was no serious confusion among different fire severity levels,and the classification model can also be applied to another date with fire occurrences across the study area.Therefore,the remote sensing method that we presented can be successfully applied in wetland fire research,which could provide some valuable suggestions for wetland fire management.
引文
[1]CHRISTINE W.Estimating emissions from fires in North America for air quality modeling[J].Atmospheric Environment,2006,40(19):3419-3432.
[2]吕爱锋,田汉勤,刘永强.火干扰与生态系统的碳循环[J].生态学报,2005,25(10):2734-2743.
[3]VIGILANTE T.Effects of fire history on the structure and floristic composition of woody vegetation around Kalumburu,North Kimberley,Australia:a landscape-scale natural experiment[J].Australian Journal of Botany,2004,52(52),381-404.
[4]陈利顶,傅伯杰.干扰的类型、特征及其生态学意义[J].生态学报,2000,20(4):581-586.
[5]邓欧,李亦秋,冯仲科,等.基于空间Logistic的黑龙江省林火风险模型与火险区划[J].农业工程学报,2012,28(8):200~205.
[6]李建平,张柏,张泠,等.湿地遥感监测研究现状与展望[J].地理科学进展,2007,26(1):33-43.
[7]MICHAEL C W,MATTHEW J R.Assessment of fire severity and species diversity in the southern Appalachians using Landsat TM and ETM+imagery[J].Remote Sensing of Environment,2007,108(2):189-197.
[8]PARKER B M,LEWIS T,SRIVASTAVA S K et al.Estimation and evaluation of multi-decadal fire severity patterns using Landsat sensors[J].Remote Sensing of Environment,2015,170(1):340-349.
[9]左仲武.国内外湿地生态系统研究进展[J].生态科学,2009,28(5):477-480.
[10]王伟,宋卫国,刘士兴,等.Kmeans聚类与多光谱阈值相结合的MODIS云检测算法[J].光谱学与光谱分析,2011,31(4):1061-1064.
[11]GISLASON P O,BENEDIKTSSON J A,SVEINSSON J R,et al.Random forests for land cover classification[J].Pattern Recognition Letters,2006,27(4):294-300.
[12]何报寅,丁超,杨小琴,等.Landsat7ETM+SLC-OFF数据的修复及其在武汉东湖水质反演中的应用[J].长江流域资源与环境,2011,20(1):90-95.
[13]CARL H K,NATHAN C B.Landscape assessment(LA)sampling and analysis methods[M].USDA Forest Service Gen Tech.Rep RMRS-GTR-164-CD.2006.
[14]CHUVIECO E,COCERO D,RIANO D et al.Combining NDVI and surface temperature for the estimation of live fuel moisture content in forest fire danger rating[J].Remote sensing of environment,2004,92(3):322-331.
[15]LOZANO F J,SUSANA SUAREZ-SEOANE,LUIS E D.Assessment of several spectral indices derived from multitemporal Landsat data for fire occurrence probability modelling[J].Remote Sensing of Environment,2007,107(4):533-544.
[16]GOODWIN N R,COLLETT L J.Development of an automated method for mapping fire history captured in Landsat TM and ETM+time series across Queensland,Australia[J].Remote Sensing of Environment,2014,148(5):206-221.
[17]雷震.随机森林及其在遥感影像处理中应用研究[D].上海:上海交通大学,2012.
[2]吕爱锋,田汉勤,刘永强.火干扰与生态系统的碳循环[J].生态学报,2005,25(10):2734-2743.
[3]VIGILANTE T.Effects of fire history on the structure and floristic composition of woody vegetation around Kalumburu,North Kimberley,Australia:a landscape-scale natural experiment[J].Australian Journal of Botany,2004,52(52),381-404.
[4]陈利顶,傅伯杰.干扰的类型、特征及其生态学意义[J].生态学报,2000,20(4):581-586.
[5]邓欧,李亦秋,冯仲科,等.基于空间Logistic的黑龙江省林火风险模型与火险区划[J].农业工程学报,2012,28(8):200~205.
[6]李建平,张柏,张泠,等.湿地遥感监测研究现状与展望[J].地理科学进展,2007,26(1):33-43.
[7]MICHAEL C W,MATTHEW J R.Assessment of fire severity and species diversity in the southern Appalachians using Landsat TM and ETM+imagery[J].Remote Sensing of Environment,2007,108(2):189-197.
[8]PARKER B M,LEWIS T,SRIVASTAVA S K et al.Estimation and evaluation of multi-decadal fire severity patterns using Landsat sensors[J].Remote Sensing of Environment,2015,170(1):340-349.
[9]左仲武.国内外湿地生态系统研究进展[J].生态科学,2009,28(5):477-480.
[10]王伟,宋卫国,刘士兴,等.Kmeans聚类与多光谱阈值相结合的MODIS云检测算法[J].光谱学与光谱分析,2011,31(4):1061-1064.
[11]GISLASON P O,BENEDIKTSSON J A,SVEINSSON J R,et al.Random forests for land cover classification[J].Pattern Recognition Letters,2006,27(4):294-300.
[12]何报寅,丁超,杨小琴,等.Landsat7ETM+SLC-OFF数据的修复及其在武汉东湖水质反演中的应用[J].长江流域资源与环境,2011,20(1):90-95.
[13]CARL H K,NATHAN C B.Landscape assessment(LA)sampling and analysis methods[M].USDA Forest Service Gen Tech.Rep RMRS-GTR-164-CD.2006.
[14]CHUVIECO E,COCERO D,RIANO D et al.Combining NDVI and surface temperature for the estimation of live fuel moisture content in forest fire danger rating[J].Remote sensing of environment,2004,92(3):322-331.
[15]LOZANO F J,SUSANA SUAREZ-SEOANE,LUIS E D.Assessment of several spectral indices derived from multitemporal Landsat data for fire occurrence probability modelling[J].Remote Sensing of Environment,2007,107(4):533-544.
[16]GOODWIN N R,COLLETT L J.Development of an automated method for mapping fire history captured in Landsat TM and ETM+time series across Queensland,Australia[J].Remote Sensing of Environment,2014,148(5):206-221.
[17]雷震.随机森林及其在遥感影像处理中应用研究[D].上海:上海交通大学,2012.
© 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 |