GEOG6163

Geospatial analytics increasingly relies on cutting-edge computational methods to tackle the diverse and rapidly growing range of available data, incl. spatial big data from location-based tech, sensor networks, and remote sensing products. In parallel, there is increasing availability of artificial intelligence based geospatial solutions (GeoAI) as well as access to the technology to run these (e.g. GPU computing). This class is designed to build from material introduced in GEOG 3160/5160 by giving students experience with these methods through a series of practically based examples using real world data. Topics include computer vision methods for remote sensed imagery, deep learning for sequence-based data (e.g. monitoring stations), spatial optimization and working with cloud services.

Prerequisites: "C-" or better in GEOG 3160 OR GEOG 5160.

Fall