1. Introduction

More than 150 Earth observation satellites are currently in orbit measuring the state of the Earth system (Tatem et al. 2008). These satellites, together with countless air-, land-, and water-based monitoring systems, are generating large volumes of geospatial data. For example, the National Aeronautics and Space Administration (NASA)’s Earth Observing System (EOS) alone collect 1000 terabytes annually (Clery and Voss 2005). This unprecedented data-collecting capability brings considerable challenges to geospatial research and applications, one of which is how to derive high-level information and knowledge from the oceans of data in an effective and timely way. The traditional methods of analyzing data by expert analysts fall far short of today’s increased demands for geospatial knowledge. As a result, much data may never been analyzed even once after collection. Geospatial users are experiencing a data-rich yet analysis-poor period. Therefore, technologies for semi-automated or automated geospatial knowledge discovery and dissemination are urgently needed for geospatial applications.