The goal of our study is providing a new validation concept into ENMs. This could be done by applying remote sensing (RS) techniques, which enables mapping of large areas and provide detailed information on land use. In order to validate the ENM models using the GEOBIA technique we used the species Bertholletia excelsa. The models were built on the ‘biomod2’ package. The images were obtained from orbital sensor Operational Land Imager (OLI) on board the Landsat-8 satellite. We calculated vegetation indices (EVI, SAVI, LAI and NDVI) and applied them to the GEOBIA technique. A total of 693 possible sites of B. excelsa were detected, using 25 sites accessible for validation, which added 45 new records of this species. GEOBIA has been shown to be a tool with a high potential to validate ENMs, as well as in the extraction of arboreal species from medium resolution spatial images.