The 4th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery



Emerging advances from artificial intelligence, hardware accelerators and processing architectures continue to transform societal challenges impacted by geospatial applications. Recent breakthroughs in deep learning have brought forward an automated capability to learn hierarchical representational features from massive and complex data, including text, images, and videos. In tandem, rapid innovations in sensing technologies are collecting geospatial data in even higher resolution and throughput to enable mapping and analysis of the earth’s surface, events and various phenomena in unprecedented detail. Combined, these developments are offering potential for breakthroughs in geographic knowledge discovery to impact better decision making through precise humanitarian mapping, intelligent transport systems, urban expansion analysis, spatial diffusion methods to support epidemiology, climate change induced threats, natural disasters, and monitoring of the earth’s surface.

Following the success of the previous GeoAI workshops at SIGSPATIAL, GeoAI’21 aims to continue bringing together geoscientists, computer scientists, engineers, entrepreneurs, and decision makers from academia, industry, and government to discuss the latest trends, successes, grand challenges, and opportunities in the emerging field of geospatial artificial intelligence to provide actionable intelligence and power new geographic scientific discoveries.


Example topics include but are not limited to:

  • Data integrity, bias and privacy in Earth Sciences;
  • Emerging challenges and opportunities with deep fake geography;
  • GIScience with artificial intelligence for earth sciences and sustainability;
  • Geospatial artificial intelligence applications in public health and agricultural domains;
  • Spatial representation learning and deep neural networks for spatio-temporal data;
  • Domain knowledge guided methods for spatiotemporal learning and challenges;
  • Methods and tools for location intelligence applications;
  • Social network data analytics and geographic knowledge graphs;
  • Urban growth prediction and planning with machine learning methods;
  • Self-supervised and unsupervised deep learning methods spatial and spatio-temporal data;
  • Deep learning methods for disaster response and humanitarian applications;
  • Human in the loop methods for enhancing integrity in GeoAI applications;
  • Tools and methods for (explainable) XGeoAI;
  • Learning with multimodal fusion of geographic attributed datasets;
  • GeoAI methods for mobility and traffic data analytics;
  • GeoAI cyberinfrastructure for Earth sciences;

Workshop Chairs

Dalton Lunga

Dalton Lunga

Oak Ridge National Laboratory
Song Gao

Song Gao

University of Wisconsin Madison

Yingjie Hu

University at Buffalo

Bruno Martins

University of Lisbon
shawn newsam

Shawn Newsam

University of California, Merced
Lexie Yang

Lexie Yang

Oak Ridge National Laboratory
xueqing deng

Xueqing Deng

University of California, Merced

Submission Details

Paper submission: EXTENDED to September 7, 2021

Acceptance decision: UPDATED! October 6, 2021 

Camera ready version: TBD

Workshop date: November 2, 2021


This is a one-day workshop, which includes two keynotes (one for the morning and one for the afternoon respectively) and individual presentations. A paper competition will also be organized for the presented papers. Three submission types will be included in this workshop:

  • Full research paper: 8-10 pages
  • Short research paper or industry demo paper: 4 pages
  • Vision or statement paper: 2 pages

Full research papers should present mature research on a specific problem or topic in the context of AI for geospatial challenges. We also welcome short research articles or industry demonstrations of existing or developing methods, toolkits, and best practices for AI applications in the geospatial domain. A vision for future directions or an overview statement on gaps and challenges for the development of AI technology and their applications in the geospatial domain are also welcome.

Manuscripts should be submitted in PDF format and formatted using the ACM camera-ready templates available at All submitted papers will be peer reviewed to ensure the quality and the clarity of the presented research work. Submissions will be single-blind — i.e., the names affiliations of the authors should be listed in the submitted version.

Papers should be submitted at:

Program Committee

Pete Atkinson, Atkinson, Lancaster University, UK

Orhun Aydin, Esri Inc., USA

Booma Sowkarthiga Balasubramani, Microsoft, USA

Dengfeng Chai, Zhejiang University, China

Yao-Yi Chiang, University of Southern California, USA

Xiao Huang, University of Arkansas

Zhe Jiang, University of Alabama

Kuldeep Kurte, Oak Ridge National Laboratory, USA

Wenwen Li, Arizona State University, USA

Xiaojiang Li, Temple University, USA

Yanhua Li, Worcester Polytechnic Institute, USA

Gengchen Mai, Stanford University, USA

Claudio Persello, University of Twente, Netherlands

Devis Tuia, EPFL, Switzerland

Martin Werner, Technical University of Munich, Germany

Yiqun Xie, University of Maryland, College Park, USA

Fan Zhang, MIT Senseable City Lab, USA

Xun Zhou, University of Iowa, USA

Di Zhu, Peking University, China

Lei Zou, Texas A&M University, USA