森林火灾发生后,为及时、准确地掌握森林受灾情况,利用高分一号卫星(GF-1)16m宽幅影像各波段反射率信息,结合计算的归一化植被指数(NDVI)、过火区识别指数(BAI)、阴影植被指数(SVI)、归一化差异水体指数(NDWI)和全球环境监测指数(GEMI)等5种光谱指数,构建森林火烧迹地识别决策树模型(CART);在选取的研究区对该模型方法进行验证,并与最大似然监督分类法和非监督分类(ISODATA)方法所得到的结果精度进行了对比分析,结果表明采用基于CART模型的决策树方法对火烧迹地识别结果精度较最大似然法总体分类精度提高了4.38%,Kappa系数提高了0.102 4,制图精度提高了14.96%,用户精度提高了8.50%;而采用ISODATA方法识别的火烧迹地的总体精度和Kappa系数都较低,制图精度和用户精度都没有达到1%。
This paper describes the technique to be needed for rapidly and accurately identifying the burned area by forest fires,following the catastrophic fires by the vegetation index CART decision tree methods using the wide coverage image of GF-1(GF-1 WFV).They were compared between the maximum likelihood classification of supervised and unsupervised classification(ISODATA),within burned area indexes,to improve the accuracy of the burned area,shaded vegetation index,global environment monitoring index,improved shadows and bare commission or omission burned phenomenon.The results showed that the decision tree classification method based on CART algorithms for burned area identification has significantly improved the overall accuracy by 4.38% compared with the maximum likelihood method;Kappa coefficient increased by 0.1024.GF-1 satellite imagery for unsupervised classification(ISODATA)identifies the burned area poorly,the overall accuracy and Kappa coefficient are low,the map making accuracy and user accuracy have not reached 1%.
[1]Gitas I Z,Mitri G H,Ventura G.Object-based image classification for burned area mapping of Creus Cape,Spain,using NOAA-AVHRR imagery[J].Remote Sensing of Environment,2004,92(3):409-413.
[2]Giglio L,Loboda T,Roy D P,et al.An active-fire based burned area mapping algorithm for the MODIS sensor[J].Remote Sensing of Environment,2009,113(2):408-420.
[3]覃先林,李增元,易浩若,等.基于ENVISAT-MERIS数据的火烧迹地制图方法研究[J].遥感技术与应用,2008,22(4):1-6.
[4]朱曦,覃先林,廖靖.基于模糊集理论的单时相跨区域森林火烧迹地遥感制图[J].国土资源遥感,2013,25(4):122-128.
[5]朱曦,覃先林.基于二阶段算法的HJ-CCD数据火烧迹地制图[J].遥感技术与应用,2013,28(1):72-77.
[6]刘健,许章华,余坤勇,等.山地丘陵区遥感影像阴影检测与去除方法[J].农业机械学报,2013,44(10):238-241.
[7]许章华,刘健,余坤勇,等.阴影植被指数 SVI 的构建及其在四种遥感影像中的应用效果[J].光谱学与光谱分析,2013,33(12):3359-3365.
[8]周庆,李峰,张海涛,等.监督分类技术在高分辨率卫星影像中的应用[J].北京林业大学学报,2003(S1):47-49.
[9]汪金花,张永彬,孔改红.谱间关系法在水体特征提取中的应用[J].矿山测量,2004(4):30-32.
[10]徐涵秋.基于谱间特征和归一化指数分析的城市建筑用地信息提取[J].地理研究,2005,24(2):311-320.
[11]徐涵秋.利用改进的归一化差异水体指数(NDWI)提取水体信息的研究[J].遥感学报,2005,9(5):589-595.
[12]Segah H,Tani H,Hirano T.Detection of fire impact and vegetation recovery over tropical peat swamp forest by satellite data and ground-based NDVI instrument[J].Int.J.Remote Sens.,2010,31:5297-5314.
[13]Parsons A.Burned Area Emergency Rehabilitation Soil Burn Severity Definitions and Mapping Guidelines Draft[M].USDA Forest Service,Rocky Mountain Research Station:Missoula,MT,USA,2003.
[14]Balzter H,Gonzalez M C,Gerard F,et al.Post-Fire Vegetation Phenology in Siberian Burn Scars[C]//In Proceedings of 2007 IEEE International Geoscience and Remote Sensing Symposium,Barcelona,Spain:4652-4655.
[15]Telesca L,Lasaponara R.Pre-and post-fire behavioral trends revealed in satellite NDVI time series[J].Geophys.Res.Lett.,2006,33.
