VEG: Intelligent workbench for studying earth's vegetation

Abstract The purpose of this paper is to describe VEG, an intelligent workbench for remote sensing scientists. VEG assists scientists in the analysis of optical reflectance data. VEG was designed to manage complexity, provide intelligent support, provide visualization tools, and contract the time required for a scientist studying the earth's vegetation to run exploratory studies, test alternative hypotheses, do what if thinking, and manage large data sets. VEG organizes and provides coherence to a diverse set of techniques and tools that are used by these scientists. It codifies in knowledge-based system components, heuristic knowledge used by these scientists when doing scientific work. The VEG system saves the scientist many hours of laborious calculation, and it empowers the scientist by allowing him or her to work quickly at a higher level of abstraction without the need to focus attention on a multitude of low-level tasks. The VEG system includes rule-based components, data management tools, technique design and management tools, browsers, graphics support, a highly visual interface, and a system for organizing and managing problem histories.