文章基本信息

标题：Estimating sub-pixel to regional winter crop areas using neural nets
本地全文：下载
作者：Clement Atzberger ; Felix Rembold
期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：2010
卷号：XXXVIII - Part 7A
页码：13-18
出版社：Copernicus Publications
摘要：The work aimed at testing a methodology which can be applied to low spatial resolution satellite data to assess inter-annual crop areavariations onsub-pixel toregional scales. The methodology is based on the assumption that within mixed pixelsland covervariations arereflectedby changes in the related hyper-temporalprofiles of theNormalised Difference Vegetation Index (NDVI).We evaluated ifchanges in thefractional winter crop coverage are reflected in changingshapesof annual NDVI profilesand can be detected by usingneuralnetworks. The neural nets weretrainedon reference data obtained fromhigh resolutionLandsat TM/ETMimages. The proposedmethodology was applied in a study region in central Italy to estimate winter cropareasbetween 1988 and 2002from1 km resolutionNOAA-AVHRRprofilesand additional ancillary data readily available (CORINE land cover). The accuracy oftheestimates wasassessed by comparison to official agricultural statistics using a bootstrap approach. The method showed promise for estimating crop areavariation onsub-pixellevel(cross-validated R2between 0.7 and 0.8)toregional scales(normalized RMSE: 10%). The network basedapproachproved to have a significantly higher forecast capability than other methods used previously for the same study area
关键词：Neural; Pixel; Estimation; Method; Test