Mapping Urban Areas by Fusing Multiple Sources of Coarse Resolution Remotely Sensed Data

Widespread conversion of natural ecosystems and agricultural lands to urban land cover affects local and regional ecosystems, climate, biogeochemistry, as well as food production. This article reports on research undertaken to improve the understanding of the methodological and validation requirements for mapping urban land cover over large areas from coarse resolution remotely sensed data. The authors describe a technique called boosting which is used to improve supervised classification accuracy and provides a means to integrate MODIS (Moderate Resolution Imaging Spectroradiometer, from NASA) data with the DMSP nighttime lights data set and gridded population data. Results for North America indicate that fusion of these three data types improves urban classification results by resolving confusion between urban and other classes that occurs when any one of the data sets is used by itself. The authors apply traditional measures of accuracy assessment as well as new, maplet-based methods to demonstrate the effectiveness of their methodology for creating maps of cities at continental scales. Five color plates show the urban class at two cities: Baltimore-Washington, D.C. and the San Francisco Bay area.

  • Availability:
  • Authors:
    • Schneider, Annemarie
    • Friedl, Mark A
    • McIver, Douglas M
    • Woodcock, Curtis E
  • Publication Date: 2003-12


  • English

Media Info

  • Media Type: Print
  • Features: Figures; References; Tables;
  • Pagination: pp 1377-1386
  • Serial:

Subject/Index Terms

Filing Info

  • Accession Number: 01002039
  • Record Type: Publication
  • Files: TRIS
  • Created Date: Jul 14 2005 10:13AM