Agent-based interpretation of geospatial evidential data

Abstract

We report on work developing a n d testing agent-based algorithms /or marshaling available evidence, making in/erences. and testing hypotheses using geospatially referenced data. I n addition to developing algorithms. we also identified and obtained land cover and transportation data from public sources, selected COTS sofiware for map preprocessing, studied the scaling behavior of the agent-based algorithms as afinction o/the number of map cells, and investigated the impact of interagent small-world communication networks and agent activation rules on processing speed and scaling. Our results demonstrate the viabiIi9 of an agent-based "bottomup" approach to solving problems that involve synthesizing data from multiple sources in a geaspatial setting. One particularly interesting finding is the discovev a/ a synergistic combination of small-world nehvorks and agent activation rules leading to emergent basins of attractionfor information flow.