Mapping informal settlements using WorldView-2 imagery and C4.5 decision tree classifier Recent developments in geotechnologies provide resources to propose innovative strategies for urban and environmental management, including remote sensing data and computational resources for processing them. With the main objective of identifying urban areas of illegal occupation, this work uses WorldView-2-sensor images and the InterIMAGE, an image interpretation software, based on knowledge, under development by PUC-RJ in cooperation with INPE. Confirmed the potential of Geographic Object-Based Image Analysis (GEOBIA) and, on the other hand, the complexity on building the classification models, this work performs and evaluates land cover classification using C4.5 decision tree algorithm, which enables to quickly select the most representative attributes for each class and generate simple classification rules. The results show that data mining technique presented high classification performance. Using the land cover classes, we proceeded with the land use classification to identify areas of irregular occupation. The thematic maps achieved high values of overall accuracy and Kappa index. Typical classifications have been resolved by discriminating nine land cover classes.