Abstract
The topic of knowledge graphs (KGs) has recently attracted extensive attention in both industry and academia. Knowledge graphs are a new paradigm for representing, retrieving, integrating, and reasoning data from highly heterogeneous and multimodal sources. For example, international conferences, such as the Knowledge Graph Conference, have emerged in the past years, not to mention the increasing number of specialized workshops on KGs co-located with major computer science conferences, including Knowledge Graph Workshop at KDD 2021, Workshop for Deep Learning in Knowledge Graphs at ISWC 2021, Workshop on Knowledge Graph Construction at ESWC 2021, to name but a few. Also, the number of KGs-related papers accepted at these major conferences, including SIGSPATIAL, is rapidly increasing. Meanwhile, we also witness the increasing popularity of knowledge graph technologies in geography, geoinformatics, and GIScience domains. There are growing numbers of knowledge graph-related manuscripts accepted to the top geospatial-related venues, such as the International Journal of Geographical Information Science, Transactions in GIS, the International Journal of Applied Earth Observation and Geoinformation, and so on. Transactions in GIS also held two special issues about knowledge graphs: 1) Symbolic and Subsymbolic GeoAI: Geospatial Knowledge Graphs and Spatially Explicit Machine Learning [4], and 2) Knowledge-based GIS (K-GIS): Theories, Techniques and Applications. In addition, government agencies, industries, and non-governmental organizations (NGOs) are also lifting resources on topics of exploring KGs to build up interdisciplinary science and applications. One example is NSF's Accelerate Convergence Program, which promotes the idea of building an Open Knowledge Network to harness the data revolution. Funded by this program, the KnowWhereGraph is presently among the largest geo-enabled knowledge graphs, which integrates 28 different data layers at the intersection between humans and their environment [2].