CLASSIFICATION OF CROPLANDS THROUGH INTEGRATION OF REMOTE-SENSING, GIS, AND HISTORICAL DATABASE

This work presents a methodology to classify croplands using a multite mporal/historical dataset of images and ground ancillary data referrin g to three consecutive years. An image processing/geographic informati on system as well as a database management system (DBMS) were used to make the integration of these multisource data. In order to evaluate t he usefulness of a database for crop classification, the area under st udy was digitally classified by two groups of interpreters, using two methodologies: (a) the proposed methodology using maximum likelihood c lassification assisted by an historical/multisource database, and (b) a conventional maximum likelihood classification only. Both results we re compared using the Kappa statistics. The indices to both the propos ed and the conventional digital classification methodologies were 0.66 9 (very good) and 0.472 (good), respectively. The use of the database rendered an improvement over the conventional digital classification. Furthermore, along with this study some problems related to multisourc e data integration are discussed.