Comparison of Data Fusion Methods Using Crowdsourced Data in Creating a Hybrid Forest Cover Map

12313 29 44154 2 113703 document 44154 remotesensing-08-00261.pdf application/pdf 97b91096482cedb8a8f4ea4c06ead985 MD5 3020492 2016-03-22 11:58:34 https://pure.iiasa.ac.at/id/eprint/12313/1/remotesensing-08-00261.pdf 12313 1 1 application/pdf text en public cc_by

remotesensing-08-00261.pdf

published 44156 2 113713 document 44156 lightbox.jpg image/png ef26984cd4b24550b114d582fd53cf7e MD5 49895 2016-03-22 12:18:42 https://pure.iiasa.ac.at/id/eprint/12313/2/lightbox.jpg 12313 2 2 image/png other Thumbnails conversion from text to thumbnail_lightbox en public

lightbox.jpg

preview.jpg

medium.jpg

small.jpg

indexcodes.txt

http://eprints.org/relation/isVersionOf https://pure.iiasa.ac.at/id/document/44154 http://eprints.org/relation/isVolatileVersionOf https://pure.iiasa.ac.at/id/document/44154 http://eprints.org/relation/isIndexCodesVersionOf https://pure.iiasa.ac.at/id/document/44154 archive 2 disk0/00/01/23/13 2016-03-22 12:16:26 2024-01-04 13:53:20 2016-03-22 12:16:26 article show Lesiv M. 8477 0000-0001-9846-3342 Moltchanova E. Shchepashchenko D. 7435 0000-0002-7814-4990 See L. 8571 0000-0002-2665-7065 Shvidenko A. 1487 Comber A. Fritz S. 8130 0000-0003-0420-8549 Comparison of Data Fusion Methods Using Crowdsourced Data in Creating a Hybrid Forest Cover Map pub prog_esm data fusion methods; forest map; remote sensing; geographically-weighted regression; Geo-Wiki This article belongs to the Special Issue "Validation and Inter-Comparison of Land Cover and Land Use Data" available here: http://www.mdpi.com/journal/remotesensing/special_issues/lulc Data fusion represents a powerful way of integrating individual sources of information to produce a better output than could be achieved by any of the individual sources on their own. This paper focuses on the data fusion of different land cover products derived from remote sensing. In the past, many different methods have been applied, without regard to their relative merit. In this study, we compared some of the most commonly-used methods to develop a hybrid forest cover map by combining available land cover/forest products and crowdsourced data on forest cover obtained through the Geo-Wiki project. The methods include: nearest neighbour, naive Bayes, logistic regression and geographically-weighted logistic regression (GWR), as well as classification and regression trees (CART). We ran the comparison experiments using two data types: presence/absence of forest in a grid cell; percentage of forest cover in a grid cell. In general, there was little difference between the methods. However, GWR was found to perform better than the other tested methods in areas with high disagreement between the inputs. 2016 Molecular Diversity Preservation International (MDPI) 10.3390/rs8030261 181 279 276 281 98 public Remote Sensing 8 3 e261 TRUE 2072-4292 Harnessing the power of crowdsourcing to improve land cover and land-use information (CROWDLAND, FP7 617754) Geo-Wiki FALSE yes info:eu-repo/grantAgreement/EC/FP7/617754/EU/Harnessing the power of crowdsourcing to improve land cover and land-use information/CROWDLAND info:eu-repo/semantics/article info:eu-repo/semantics/openAccess