Forecasting Land Use

Tuesday, July 8, 2008 - 12:00pm

Dr. Joydeep Ghosh applies data mining techniques to remotely sensed and GIS data to develop a comprehensive framework for efficient and accurate mapping, monitoring, and modeling of land cover and changes in usage over large regions.

The ability to forecast changes in land use is particularly important in regions undergoing rapid ecological changes or urbanization. There is plenty of information from satellites and in Geographic Information Systems (GIS). The trouble is that remotely sensed data doesn't inter-operate well with traditional spatial data. Dr. Ghosh's research helps clarify the significance of all that information by applying data mining techniques and—ultimately— developing a comprehensive framework for efficient and accurate mapping, monitoring, and modeling of land cover and changes in usage over large regions.

This endeavor involves three complementary activities: (i) large scale classification of remote sensing imagery using advanced learning methods, including transfer learning, active learning and manifold based data descriptors