TY - JOUR
T1 - Integrating global land cover products for improved forest cover characterization
T2 - An application in North America
AU - Song, Xiao Peng
AU - Huang, Chengquan
AU - Feng, Min
AU - Sexton, Joseph O.
AU - Channan, Saurabh
AU - Townshend, John R.
N1 - Funding Information:
This study is a contribution to the Global Forest Cover Change project funded by NASA’s Making Earth System Data Records for Use in Research Environments (MEaSUREs) Program [NNX08AP33A]. Additional support is provided by the NASA Earth and Space Science Fellowship (NESSF) Program [NNX12AN92H]; the Land-Cover/Land-Use Change Program [NNH07ZDA001N]; the Earth System Science from EOS Program [NNH06ZDA001N]; and the MODIS Science Team.
PY - 2014/10
Y1 - 2014/10
N2 - Six widely used coarse-resolution global land cover data-sets - Global Land Cover Characterization (GLCC), Global Land Cover 2000 (GLC2000), GlobCover land cover product (GlobCover), MODIS land cover product (MODIS LC), the University of Maryland land cover product (UMD LC), and the MODIS Vegetation Continuous Fields tree cover layer (MODIS VCF) disagree substantially in their estimates of forest cover. Employing a regression tree model trained on higher-resolution, Landsat-based data, these multisource multiresolution maps were integrated for an improved characterization of forest cover over North America. Evaluated using a withheld test sample, the integrated percent forest cover (IPFC) data-set has a root mean square error of 11.75% - substantially better than the 17.37% of GLCC, 17.61% of GLC2000, 17.96% of GlobCover, 15.23% of MODIS LC, 19.25% of MODIS VCF, and 15.15% of UMD LC, respectively. Although demonstrated for forest, this approach based on integration of multiple products has potential for improved characterization of other land cover types as well.
AB - Six widely used coarse-resolution global land cover data-sets - Global Land Cover Characterization (GLCC), Global Land Cover 2000 (GLC2000), GlobCover land cover product (GlobCover), MODIS land cover product (MODIS LC), the University of Maryland land cover product (UMD LC), and the MODIS Vegetation Continuous Fields tree cover layer (MODIS VCF) disagree substantially in their estimates of forest cover. Employing a regression tree model trained on higher-resolution, Landsat-based data, these multisource multiresolution maps were integrated for an improved characterization of forest cover over North America. Evaluated using a withheld test sample, the integrated percent forest cover (IPFC) data-set has a root mean square error of 11.75% - substantially better than the 17.37% of GLCC, 17.61% of GLC2000, 17.96% of GlobCover, 15.23% of MODIS LC, 19.25% of MODIS VCF, and 15.15% of UMD LC, respectively. Although demonstrated for forest, this approach based on integration of multiple products has potential for improved characterization of other land cover types as well.
KW - North America
KW - data fusion
KW - forest
KW - land cover
KW - regression tree
UR - http://www.scopus.com/inward/record.url?scp=84903173809&partnerID=8YFLogxK
U2 - 10.1080/17538947.2013.856959
DO - 10.1080/17538947.2013.856959
M3 - Article
AN - SCOPUS:84903173809
SN - 1753-8947
VL - 7
SP - 709
EP - 724
JO - International Journal of Digital Earth
JF - International Journal of Digital Earth
IS - 9
ER -