Subpixel Urban Mapping Over the Conterminous U.S. (CONUS) Using S-NPP VIIRS

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.

[1]  M. Rosegrant,et al.  Global Food Security: Challenges and Policies , 2003, Science.

[2]  Rui Zhang,et al.  Development of S-NPP VIIRS global surface type classification map using support vector machines , 2018, Int. J. Digit. Earth.

[3]  C. Vörösmarty,et al.  Global water resources: vulnerability from climate change and population growth. , 2000, Science.

[4]  N. Alexandratos.  Countries with Rapid Population Growth and Resource Constraints: Issues of Food, Agriculture, and Development , 2005 .

[5]  M. Friedl,et al.  Mapping sub-pixel urban expansion in China using MODIS and DMSP/OLS nighttime lights , 2016 .

[6]  Christopher O. Justice,et al.  Early evaluation of the VIIRS calibration, cloud mask and surface reflectance Earth data records , 2014 .

[7]  J. Townshend,et al.  Global land cover classi(cid:142) cation at 1 km spatial resolution using a classi(cid:142) cation tree approach , 2004 .

[8]  Alan H. Strahler,et al.  Global land cover mapping from MODIS: algorithms and early results , 2002 .

[9]  Suming Jin,et al.  Completion of the 2011 National Land Cover Database for the Conterminous United States – Representing a Decade of Land Cover Change Information , 2015 .

[10]  Xiaoxiong Xiong,et al.  Early On-Orbit Performance of the Visible Infrared Imaging Radiometer Suite Onboard the Suomi National Polar-Orbiting Partnership (S-NPP) Satellite , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[11]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[12]  Simon J. Hook,et al.  A Physics-Based Algorithm for the Simultaneous Retrieval of Land Surface Temperature and Emissivity From VIIRS Thermal Infrared Data , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[13]  James D. Wickham,et al.  Thematic accuracy assessment of the 2011 National Land Cover Database (NLCD). , 2017, Remote sensing of environment.

[14]  C. Elvidge,et al.  Why VIIRS data are superior to DMSP for mapping nighttime lights , 2013 .