Poster Presentation C Thursday, 5:00 6:00 pm C Edmund Fitzgerald Exhibit Hall

Present and Predicted Landscape Change in the Twin Cities Metropolitan Area

Fei Yuan, Kali Sawaya, Marvin Bauer
University of Minnesota
Department of Forest Resources
Remote Sensing and Geospatial Analysis Laboratory
115 Green Hall
1530 Cleveland Avenue North
St. Paul, MN  55108
yuan0024@tc.umn.edu

Bryan Pijanowski, Brad Shellito
Michigan State University
Basic Science and Remote Sensing Initiative
Natural Sciences Building
East Lansing, MI  48824

Satellite remote sensing can provide timely, accurate and up to date information that can be used to monitor and model urban growth. Classification of 1991 and 1998 Landsat Thematic Mapper imagery of the Twin Cities Metro Area (TCMA) has yielded promising results with overall accuracies of 90% and 92% for five, level I classes (agriculture, forest, water, wetland, urban). Land use change statistics and maps have been derived from the 1991 and 1998 classifications, quantifying and showing the spread of urban growth for this period. Those areas that transitioned from agriculture, forest or wetland to urban are represented. This same span of years has been used as input into a land transformation model. The land transformation model operates using artificial neural networks and geospatial data coupled with U.S. Census predictions to anticipate where future urban growth may occur. Preliminary results of this work are displayed, predicting the volume and location of urban expansion in the Twin Cities Metropolitan Area for 2010 and 2020. The overall accuracy of this model to predict urban transitions for the TCMA was 37%. These results are also accessible via the Internet at http://resac.gis.umn.edu/landchange.htm.