This study developed an image integration and classification system in order to provide necessary spatial parameters for an integrated mesoscale environmental assessment system (IMEAS). The lack of complete and up-to-date coverage of landcover/landuse information has reduced the reliability of IMEAS modeling results, especially for the emission model. Therefore, the developed data providing system continuously collects, processes and analyzes images from multiple sources with different spatial and spectral resolutions. The classification results are used to update landuse maps of entire Taiwan. The system also aggregates the generated landcover/landuse information into gridformat data layers of different scales for direct input of modeling systems.