With recent technological advances, the geospatial industry produces digital image data at an astonishing rate. Such large amounts of data need to be analyzed for visual content in a timely fashion. For in-depth analysis of the geospatial there is a need to find efficient methods to process the visual information into actionable knowledge. One of the most promising methods is to evaluate the relevance of geospatial images to domain-specific visual semantics. Most of existing methods for annotating semantic meaning to geospatial images are trained using binary feedback from users. Such approaches may lead to suboptimal models especially due to the fact that semantic relevance of images is rarely a binary problem. In this paper, we report an algorithm to link low-level image features with high-level visual semantics using graded relevance feedback from image analysts. This linkage is done using flexible possibility functions that mathematically model the existence of visual semantics in new images added to the database. Our experimental results show that our technique improves the knowledge discovery process as evidenced by increased mean average precision of semantic queries.