A Case-based Reasoning Approach for Task-driven Remote Sensing Image Discovery under Spatial-Temporal Constrains

Remote sensing (RS) images are an important source of geospatial data. However, current approaches in task-driven RS images discovery establish links between tasks and RS image parameters directly, without spatial-temporal constraints, leading to hard maintenance and low query precision Moreover, the complex relationship between tasks and RS images under spatial-temporal constraints is difficult to model and represent by rules. Thus, this research proposes an location and time method that not only filters but also acts as spatial-temporal constraint in the discovery process, and exploits the relationships between tasks and RS data sources under spatial-temporal constraints through Case-based Reasoning (CBR). The RS application case representation model and similarity assessment model is proposed to support analogical reasoning in CBR. A prototype system was developed to validate this method. The results show that the method is a feasible approach that improves the service efficacy of remote sensing data.