GeoAI and Deep Learning Symposium: Intelligent Geospatial Analytics
The session recording will be archived on the site until June 25th, 2023
This session was streamed but not recorded
Date: 3/25/2023
Time: 8:30 AM - 9:50 AM
Room: Capitol Ballroom 3, Hyatt Regency, Fourth Floor
Type: Paper,
Theme:
Curated Track:
Sponsor Group(s):
Cyberinfrastructure Specialty Group, Geographic Information Science and Systems Specialty Group, Spatial Analysis and Modeling Specialty Group
Organizer(s):
Di Zhu University of Minnesota
Guofeng Cao University of Colorado, Boulder
Song Gao University of Wisconsin, Madison
Chair(s):
Di Zhu University of Minnesota
Description:
Geospatial artificial intelligence (GeoAI) has drawn great attention in the inter-discipline of computer science and GIScience. Recently there are many applications in the emerging field of GeoAI that utilize deep learning frameworks (e.g. CNN, GCN, LSTM, GAN, Transformer) for geospatial studies, but not so many works are here to investigate and discuss the intuitive link between critical concepts in traditional spatial analytics (e.g. spatial dependence, scale, distance decay, spatial heterogeneity) and deep learning/machine learning principles (e.g. convolution, embedding, attention). Therefore, it is still blurred to see why AI models could facilitate spatial analysis theoretically and empirically.
Traditional spatial analytics based on strict statistical principles, strong prior assumptions, or classic
computation workflows are facing great challenges and opportunities when embracing the explosive growth of geospatial data and recent technical innovations. This session aims to explore how spatial analytical methods can be enriched with more possibilities when combined with state-of-the-art machine learning/deep learning insights, thus boosting the advancement of intelligent geospatial applications and enlightening future research at the front of GeoAI.
Presentations (if applicable) and Session Agenda:
Guofeng Cao, University of Colorado - Boulder |
Deep learning-based geostatistics for geospatial uncertainty modeling |
Ziqi Li, Florida State University |
GeoShapley: an explainable AI method to measure geographic contribution in machine learning models |
Manzhu Yu, Pennsylvania State University |
Predicting hourly PM2.5 concentrations in wildfire-prone areas using a SpatioTemporal Transformer model |
Yuankun Jiao, University of Minnesota - Twin Cities |
Assessing Spatio-Temporal Street Name Evolution Using Natural Language Processing and Geospatial Analysis |
Feilin Lai |
Satellite Mapping of Urban Settlements in a Large City using Deep Learning |
Non-Presenting Participants
| Role | Participant |
|
| |
| |
| |
| |
| |
| |
| |
| |
| |
GeoAI and Deep Learning Symposium: Intelligent Geospatial Analytics
Description
Type: Paper,
Date: 3/25/2023
Time: 8:30 AM - 9:50 AM
Room: Capitol Ballroom 3, Hyatt Regency, Fourth Floor
Contact the Primary Organizer
Di Zhu University of Minnesota
dizhu@umn.edu
Session Sponsored By
