The rapid increase in high-quality data, advanced machine learning algorithms, and the availability of fast hardware has largely contributed to a renewed interest in Artificial Intelligence (AI). Despite many successful stories, there are many challenges that remain to be solved in AI. Interestingly, nowadays, one of the most prominent topics in AI is the combination of representation learning techniques (Connectionist Artificial Intelligence) with symbolic representation and reasoning associated with knowledge graphs (Symbolic Artificial Intelligence), in order to develop scalable and interpretable machine learning models.From a geospatial point-of-view, GeoAI, as an interdisciplinary field of GIScience and AI, advocates the idea of developing and utilizing AI techniques in geography and earth science. Geospatial knowledge graphs, as symbolic representations of geospatial knowledge, go to the core of GeoAI and facilitate many intelligent applications such as geospatial data integration and knowledge discovery. In fact, geospatial data plays an important role in the Linked Open Data cloud, since spatio-temporal scopes are essential for describing events, people, and objects. However, many relational machine learning models treat geographic entities as ordinary entities in which the spatial footprints of places are neglected and the distance decay effect is ignored. This results in suboptimal performance in many geospatial-related tasks. 

In addition, there exist many demands for further advancements in other research topics related to GeoAI, such as remote sensing and street view image analysis, transportation modeling, and geo-text analysis. There are, for instance, many challenges in the adaptation of deep learning techniques to these scenarios, including the limited availability of labeled data or the difficulty of the models to generalize between locations. Incorporating geospatial knowledge (i.e., prior knowledge about the structure of objects on the surface of the Earth, and about the fundamental rules of geography) directly into deep neural network models, in the form of specially designed components and/or regularization schemes, so-called spatially-explicit machine learning, is a promising approach to address the aforementioned challenges.

Based on the above observations, this combined workshop and tutorial emphasizes the importance of geospatial information and principles in designing, developing, and utilizing geospatial knowledge graphs and other GeoAI techniques. Accordingly, we call for new methods, models, and resources for advancing research related to Geospatial Knowledge Graphs and GeoAI.

List of Relevant Topics

• Deep Learning and Reinforcement Learning on Geospatial Knowledge Graphs
  • Geographic Knowledge Graph Embeddings
  • Geographic Question Answering and Semantic Parsing based on Knowledge Graphs
  • Geospatial Knowledge Graph Summarization
• Geo-Ontology Engineering and Geospatial Knowledge Graph Construction
  • Spatio-Temporal Scoping of Knowledge Graphs
  • Gazetteer Data Management
  • Coreference Resolution for Geographic Entities
  • Geographic Ontology Alignment
  • Geospatial Knowledge Graph Construction and Completion
  • Geographic Entity Similarity Measurement
• Querying and Visualization on Geospatial Knowledge Graphs
  • GeoSPARQL and Spatial Query Evaluation
  • Knowledge Graph Visualization
  • Geo-Ontology Visualization
• Geographic Information Retrieval and Geo-Text Analysis
  • Text Geoparsing, Toponym Recognition, and Toponym Resolution
  • Information Extraction from Location-Based Social Media
  • Searching and Indexing Texts based on Locations
  • Open Domain Geographic Question Answering
  • Human Experience Extraction from Place Descriptions
• Spatially Explicit Machine Learning Methods and Models for GeoAI
  • Bridging GIScience Methods with Deep Learning
  • Model Invariance/Equivariance for Geospatial Applications (e.g., equivariance to changes in input scale or rotation)
• GeoAI for Geospatial Image Analysis
  • Classification, Segmentation, and Object/Instance Recognition
  • Remote Sensing Images
  • Street View Images
  • Scanned Paper Maps and Historical Imagery
• GeoAI Resources and Infrastructures
  • Data Augmentation Strategies and Dataset Generation
  • Development of benchmark Datasets, Tools, and Platforms
  • Spatial Data Infrastructures Supporting GeoAI
• Other GeoAI Topics and Applications
  • Transportation Modeling and Trajectory Data Analysis
  • Spatial Optimization
  • Spatio-Temporal Data Fusion and Assimilation
  • Spatial Simulation (i.e. Learning Agents in Agent-based Simulations)

Submission Guidelines

This workshop will have a half-day for tutorial sessions and a half-day for research presentations. We welcome short research articles and industry demonstration papers regarding relevant topics. The page limit is 4 pages and the recommended template is the 2019 template provided by LIPIcs (http://drops.dagstuhl.de/styles/lipics-v2019/lipics-v2019-authors.tgz). The submission Web page for both tracks of GIScience 2021 is: https://easychair.org/conferences/?conf=geokg21.

All presented papers will be made available through CEUR-WS proceedings contingent upon the authors' agreement. We will also consider a special issue with a journal.

Committees

Program Committee

• Weiming Huang, GIS Centre, Lund University
• Fei Du, Apple Map
• Cogan Shimizu, Kansas State University
• Bo Yan, LinkedIn Corporation
• Ni Lao, SayMosaic
• Xi Liu, Google Inc.
• Yao-Yi Chiang, University of Southern California
• Rui Zhu, University of California, Santa Barbara
• Wenwen Li, Arizona State University
• Simon Scheider, University Utrecht, Department of Human Geography and Spatial Planning
• Carsten Keßler, Department of Planning, Aalborg University Copenhagen
• Dalia Varanka, U.S. Geological Survey
• Martin Raubal, ETH Zurich
• Blake Regalia, NASA JPL
• Morteza Karimzadeh, University of Colorado Boulder
• Fan Zhang, MIT
• Hongxu Ma, Google X

Organizing committee

• Gengchen Mai, Stanford AI Lab, Stanford University
• Yingjie Hu, Department of Geography, University at Buffalo
• Song Gao, Department of Geography, University of Wisconsin-Madison
• Ling Cai, Department of Geography, University of California, Santa Barbara
• Bruno Martins, Instituto Superior Técnico, University of Lisbon
• Johannes Scholz, Institute of Geodesy, Graz University of Technology
• Jing Gao, Department of Geography and Spatial Sciences, University of Delaware

Contact

All questions about submissions should be emailed to Gengchen Mai or Ling Cai.