GeoAI and Deep Learning Symposium: Spatially Explicit Machine Learning and Artificial Intelligence III
The session recording will be archived on the site until June 25th, 2023
This session was streamed but not recorded
Date: 3/24/2023
Time: 4:30 PM - 5:50 PM
Room: Capitol Ballroom 5, Hyatt Regency, Fourth Floor
Type: Paper, Hybrid session with both in-person and virtual presenters
Theme:
Curated Track:
Sponsor Group(s):
Geographic Information Science and Systems Specialty Group, Remote Sensing Specialty Group, Spatial Analysis and Modeling Specialty Group
Organizer(s):
Gengchen Mai University of Georgia
Angela Yao University of Georgia
Yao-Yi Chiang University of Minnesota
Zhangyu Wang University of California Santa Barbara
Chair(s):
Gengchen Mai University of Georgia
Description:
AAG 2023 GeoAI and Deep Learning Symposium: Spatially Explicit Machine Learning and Artificial Intelligence III
Description:
As Michael Goodchild puts it, “A model is said to be spatially explicit when it differentiates behaviors and predictions according to spatial locations”. In the context of machine learning (ML) and artificial intelligence (AI), we see the need for spatially explicit ML and AI models focusing on better ways to design ML/AI model architectures for consuming spatial information by incorporating spatial knowledge and spatial inductive bias such as spatial heterogeneity, spatial autocorrelation, map projection, and so on. The recent decade has witnessed many advancements of spatially explicit ML and AI technology for various GeoAI problems such as geographic question answering, geographic knowledge graph summarization, POI distribution modeling, trajectory prediction, traffic forecasting, geo-aware fine-grained species recognition, building pattern recognition, map generalization, remote sensing image classification, terrain feature recognition, and so on. However, adding spatial inductive bias to make spatially explicit models will yield more complex ML/AI model architectures. Investigating the trade-off between designing a spatially explicit ML/AI architecture versus a more general setup that would have to learn to value space implicitly is an important research question for the spatial data science and GeoAI community.
In this session, we welcome submissions broadly contributing to the research on GeoAI and spatially explicit AI/ML. AI/ML algorithm design and developments on geospatial data are particularly welcome.
Topics include (but are not limited to):
Spatially Explicit AI for Geospatial Semantics
-Geo-text Mining
-Geographic Knowledge Graph and Ontology Engineering
-Geographic Question Answering
-Geographic Entity Coreference Resolution and Gazetteer Matching
-Geographic Ontology Alignment
-Toponym Recognition and Resolution
-Geographic Knowledge Graph Summarization
-Geographic Entity Similarity Measurement
-Geographic Relation Reasoning
-Spatially Explicit AI for Remote Sensing
-Remote Sensing Image Classification
-Geospatial Object Recognition and Localization
-Unsupervised/Self-Supervised Learning on Remote Sensing Data
-Deep Generative Models on Remote Sensing Images (e.g., Superresolution, Style Transfer)
-Land Use and Land Cover Classification
-Spatially Explicit AI for Urban Computing
-Traffic Forecasting
-Trajectory Prediction and Generation
-Urban Functional Zone Detection
-POI Distribution Prediction and Spatially Explicit Location Recommendation Systems
-Spatially Explicit AI for Earth System Science
-Weather Forecasting and Extreme Weather Prediction
-Precipitation Prediction
-Spatially Explicit AI for Computational Sustainability
-Economic Development Prediction and Mapping
-Water Quality Mapping
-Spatially Explicit AI for Health
-AI for Medical Equipment Inequality
-Environmental-Related Health Issue Prediction
Organizers:
Gengchen Mai (gengchen.mai25@uga.edu), Assistant Professor, Department of Geography, University of Georgia
X. Angela Yao (xyao@uga.edu), Professor, Department of Geography, University of Georgia
Yao-Yi Chiang (yaoyi@umn.edu), Associate Professor, Department of Computer Science & Engineering, University of Minnesota-Twin Cities
Zhangyu Wang (zhangyuwang@ucsb.edu), Ph.D. Student, Department of Geography, University of California, Santa Barbara
If you are interested in participating in this session, please email an abstract and PIN to Gengchen Mai (gengchen.mai25@uga.edu) and Zhangyu Wang (zhangyuwang@ucsb.edu) by Nov. 15th, 2022.
Presentations (if applicable) and Session Agenda:
Marina Vicens Miquel |
Physics-based deep learning architectures for water level predictions |
Hugh Rice |
An Inclusive Economy classification for local authorities in Great Britain |
Gengchen Mai, University of Texas at Austin |
Towards General-Purpose Representation Learning of Polygonal Geometries |
Behzad Vahedi |
Partial Label Learning for Sea Ice Type Classification in the Arctic |
Non-Presenting Participants
| Role | Participant |
|
| |
| |
| |
| |
| |
| |
| |
| |
| |
GeoAI and Deep Learning Symposium: Spatially Explicit Machine Learning and Artificial Intelligence III
Description
Type: Paper, Hybrid session with both in-person and virtual presenters
Date: 3/24/2023
Time: 4:30 PM - 5:50 PM
Room: Capitol Ballroom 5, Hyatt Regency, Fourth Floor
Contact the Primary Organizer
Gengchen Mai University of Georgia
gengchen.mai25@uga.edu
Session Sponsored By
