This National Science Foundation project grant of $372,621 awarded on August 1, 2022 will fund research to develop optimized spatial data conflation algorithms with topological conditions under the Social, Behavioral, and Economic Sciences program (CFDA 47.075). The University of Kansas Center for Research will lead the effort to advance computational methods for reliably matching and merging map objects in geographic information systems. Researchers aim to minimize the manual effort and costs required for conflating two geospatial datasets representing the same geographical region. The project incorporates two strategies for improving automatic conflation accuracy: error minimization through similarity-based matching of individual spatial objects, and leveraging spatial context to resolve more complex cases. Michigan State University will participate under a $50,000 subaward to help model, analyze, and accelerate the resulting optimization problem from the proposed optimized conflation approach. Widespread use of the new algorithms and models could make conflation a more accessible tool for students, planners, researchers and general GIS users.
Generated 1/6/24, 6:26 PM