An artificial neural network approach was evaluated in multispectral image processing applications, including general land cover classification and land use feature identification. The performance of an artificial neural network was compared to that of a standard statistical classification technique available from a commercial image processing package (ERDAS). Landsat Thematic Mapper 30 meter multispectral data of St. Louis, Missouri were utilized for the classification. Seventeen distinct land cover types were identified in the St. Louis study area. Supervised classifications were performed with both the neural network and the standard statistical methods. The results show that the neural network is more responsive to cultural material with skewed spectral distributions and sub-pixel spatial resolution (e.g. asphalt roads). The neural network’s probabilistic output also enables discrepancy resolution capabilities for the higher level task of land use feature identification. A model was developed to identify roads from the multispectral classifications. The neural network based model performed much better than the model based on the standard statistical classification technique.