Monitoring urban land cover change: An expert system approach to land cover classification of semiarid to arid urban centers

The spatial and temporal distribution of land cover is a fundamental datase t for urban ecological research. An expert (or hypothesis testing) system h as been used with Landsat Thematic Mapper (TM) data to derive a land cover classification for the semiarid Phoenix metropolitan portion of the Central Arizona-Phoenix Long Term Ecological Research (CAP LTER) site. Expert syst ems allow for the integration of remotely sensed data with other sources of georeferenced information such as land use data, spatial texture, and digi tal elevation models (DEMs) to obtain greater classification accuracy. Logi cal decision rules are used with the various datasets to assign class value s to each pixel. TM reflectance data acquired in 1998 [visible to shortwave infrared (VSWIR) bands plus a vegetation index] were initially classified for land cover using a maximum likelihood decision rule. In addition, spati al texture of the TM data was calculated. An expert system was constructed to perform postclassification sorting of the initial land cover classificat ion using additional spatial datasets such as texture, land use, water righ ts, city boundaries, and Native American reservation boundaries. Pixels wer e reclassified using logical decision rules into 12 classes. The overall ac curacy of this technique was 85%. Individual class user's accuracy ranged f rom 73% to 99%, with the exception of the commercial/industrial materials c lass. This class performed poorly (user's accuracy of 49%) due to the simil arity of subpixel components with other classes. The results presented here indicate that the expert system approach will be useful both for ongoing C AP LTER research, as well as the planned global Urban Environmental Monitor ing (UEM) program of the Advanced Spaceborne Thermal Emission and Reflectio n Radiometer (ASTER) instrument. (C) 2001 Elsevier Science Inc. All rights reserved.