Document Type
Presentation
Publication Date
3-3-2006
Abstract
Maximum Likelihood (ML) and Artificial Neural Network (ANN) supervised classification methods were used to demarcate land cover types within IKONOS and Landsat ETM+ imagery. Three additional data sources were integrated into the classification process: Canopy Height Model (CHM), Digital Terrain Model (DTM) and Thermal data. Both the CHM and DTM were derived from multiple return small footprint LIDAR. Forty maps were created and assessed for overall map accuracy, user's accuracy, producer's accuracy, kappa statistic and Z statistic using classification schemes from U.S.G.S. 1976 levels 1 and 2 and T.G.l.C. 1999 levels 2 and 4. Results for overall accuracy of land cover maps derived from multiple sources ranged from 13.67 to 57.56 percent for U.S.G.S. level 2 and T.G.l.C. level 4 across ML and ANN classifications. Results for overall map accuracy ranged from 26.00 to 72.33 percent for U.S.G.S. level 1 and T.G.I.C. level 2 across ML and ANN classifications. Land cover maps, derived using ML classification methodology, were consistently more accurate than land cover maps derived using an ANN classification algorithm.
Repository Citation
Unger, Daniel; Tribby, Hillary; Williams, Hans Michael; and Hung, I-Kuai, "Accuracy Assessment of Land Cover Maps Derived from Multiple Data Sources" (2006). Faculty Publications. 11.
https://scholarworks.sfasu.edu/spatialsci/11
Included in
Forest Sciences Commons, Geographic Information Sciences Commons, Remote Sensing Commons
Tell us how this article helped you.
Comments
Presented at the Eleventh Biennial USDA Forest Service Remote Sensing Applications Conference, April 24-28, 2006, Salt Lake City, Utah