What is Special About GEO-AI & Spatial Data Science?
Guest Speaker: Dr. Shashi Shekhar
How to join virutally:
Please follow Webex Link: https://umbc.webex.com/umbc/j.php?MTID=m2f8ec1fca7d036e84a7ec5fd9868b8bb
Join by phone
- +1-202-860-2110 United States Toll (Washington D.C.)+1-646-992-2010 United States Toll (New York City)+1-415-655-0001 US Toll
- Attendee access code 355 548 40
Abstract: Rise of spatial big data (e.g., trajectories, remote-sensing)is fueling growth of Geo-AI(e.g., geo-imagery analysis automation)for making previously unimaginable maps,answering trail-blazing geo-content based queries, and understanding spatiotemporal patterns of our lives, etc. Applications span fromapps for navigation, ride-sharing, and delivery to monitoring global crops, climate change, diseases, andsmart citiesto understanding cellular or urban patterns of life.
However, one-size-fit-all machine learning performs poorly (e.g., salt-n-pepper noise, inaccuracy) due to spatial autocorrelation and variability, which violate the common i.i.d. assumption (i.e. data samples are generated independently andfrom identical distribution). Furthermore, high cost of spurious patterns requires guardrails such as noise tolerance, and modeling of spatial concepts (e.g., polygons) and implicit relationships (e.g., distance, inside). In addition, methods discretizing continuous space face themodifiable areal unit problem (e.g., gerrrymandering).
Thus, the talk suggestsspatial data science approaches and describes methods for spatial classification and prediction (e.g., spatial auto-regression, spatial decision trees, spatial variability aware neural networks) along with techniques for discovering patterns such as noise-robust hotspots (e.g., SaTScan, linear, arbitrary shapes), interactions (e.g., co-locations,tele-connections), spatial outliers, and their spatio-temporal counterparts (e.g.,cascade ,mixed-drove co-occurrence). It concludes by calling for inclusion of spatial perspectives in data science courses and curricula.
Bio: Shashi Shekhar is a leading scholar of spatial data science, spatial computing and Geographic Information Science (GIS).Currently, he is a Mcknight Distinguished University Professor and a University Distinguished Teaching Professorat the University of Minnesota (UMN). Recognitions include IEEE-CS Technical Achievement Award, UCGIS Education Award, IEEE Fellow, AAAS Fellow. He was also named a key difference-maker for the field of GIS by the most popular GIS textbook.
He is serving on the Computing Research Association (CRA) board (2016-22), a co-chair for the CRA Snowbird conference (2022),a co-Editor-in-Chief of Geo-Informatica (Springer),and a program co-chair for ACM SIGSpatial Intl. Conference (2022).Earlier, he served as the President of the University Consortium for GIS (UCGIS), and on many National Academies' committees including Geo-targeted Disaster Alerts and Warning (2013), Future Workforce for GEOINT (2011),Mapping Sciences (2004-2009) and Priorities for GEOINT Research (2004-2005).
In 1990s, Shashi's research developed roadmap storage and routing methods, which have revolutionized outdoor navigation. His evacuation route planning algorithms were used for homeland security and received many recognitions including the UMN CTS Award for significant impact on transportation. His recent research is analyzing spatial big data to recommend eco-routes to reduce emissions and energy use.He also pioneered spatial data mining research areavia pattern families (e.g. colocation), keynotes, surveys and workshops.
Shashi's 350+ publications include a popular textbook on Spatial Databases (Prentice Hall, 2003), an authoritative Encyclopedia of GIS (Springer, 2017) and a spatial computing book for broad audience. Many of Shashi's 100 advisees are serving in leadership positions and have received prestigious recognitions such as thePresidential Early Career Awards for Scientists and Engineers and NSF CAREER.
Shashi received a Ph.D. degree in Computer Science from the University of California (Berkeley, CA). More details are available from http://www.cs.umn.edu/~shekhar.