Subpixel urban mapping over the conterminous U.S. (CONUS) using S-NPP VIIRS
Document Type
Conference Proceeding
Publication Date
1-1-2019
Abstract
A random forest regression model was developed to estimate subpixel urban percentage using the Visible Infrared Imaging Radiometer Suite (VIIRS) data and high quality calibration information derived from the National Land Cover Database (NLCD) 2011. Accuracy assessment resulted in a mean absolute error of 3.57% and a root mean square error of 8.50%. A wall-to-wall map of urban land use across the conterminous U. S. (CONUS) in 2012 was produced, demonstrating the utility of VIIRS observations for urban mapping at regional to larger scales.
Identifier
85113858645 (Scopus)
Publication Title
International Geoscience and Remote Sensing Symposium IGARSS
External Full Text Location
https://doi.org/10.1109/IGARSS.2019.8900580
First Page
1903
Last Page
1906
Volume
2019-January
Recommended Citation
Jin, Huiran, "Subpixel urban mapping over the conterminous U.S. (CONUS) using S-NPP VIIRS" (2019). Faculty Publications. 7949.
https://digitalcommons.njit.edu/fac_pubs/7949
