Know, Know Where, Knowwheregraph: A Densely Connected, Cross-Domain Knowledge Graph and Geo-Enrichment Service Stack for Applications in Environmental Intelligence

Abstract

Knowledge graphs (KGs) are a novel paradigm for the representation, retrieval, and integration of data from highly heterogeneous sources. Within just a few years, KGs and their supporting technologies have become a core component of modern search engines, intelligent personal assistants, business intelligence, and so on. Interestingly, despite large-scale data availability, they have yet to be as successful in the realm of environmental data and environmental intelligence. In this paper, we will explain why spatial data require special treatment, and how and when to semantically lift environmental data to a KG. We will present our KnowWhereGraph that contains a wide range of integrated datasets at the human–environment interface, introduce our application areas, and discuss geospatial enrichment services on top of our graph. Jointly, the graph and services will provide answers to questions such as “what is here,” “what happened here before,” and “how does this region compare to …” for any region on earth within seconds.

Knowledge graphs: Introduction, history, and perspectives

“…More advanced forms of such inference are illustrated in the Environmental Intelligence OKN (Janowicz et al. 2022) and the flood impact evaluation OKN (Johnson et al. 2022) reported in this issue.…”

“…Wikidata solves the problem of identifying inverse relationships through the relation definitions created by curators and by using inference made possible through a KG inference engine. More advanced forms of such inference are illustrated in the Environmental Intelligence OKN (Janowicz et al 2022) and the flood impact evaluation OKN (Johnson et al 2022) reported in this issue. To the degree that the Wikidata KG is fully integrated into Wikipedia, the discrepancy of missing links in the example provided here would not be present.…”

Measuring Network Resilience via Geospatial Knowledge Graph: a Case Study of the US Multi-Commodity Flow Network

“…Each commodity flow in the network belongs to the class cfs:CFObject, which has several essential properties: cfs:CFValue, the total value ($ millions) of the commodity flow; cfs:AvgMileage, the average transport mileage (miles) of the commodity flow; time:year from the Time Ontology in OWL 2 , the year of the commodity flow; cfs:CFCode, the commodity code such as Standard Classification of Transported Goods (SCTG, described by cfs:SCTG) 3 or North American Industry Classification System (NAICS, described by cfs:NAICS) 4 . Note that the hierarchical structure in commodity types, if exists, can be preserved by adding corresponding data properties to cfs:CFCode; and kwg-ont:Region 5 from the KnowWhereGraph ontology [12], describing hierarchical geographical entities involved in CFS data such as the geographical or administrative origin and destination (e.g., state, region, division, and CFS area) of a commodity flow. Note that the concepts of regions and divisions we employ in the paper are from the Geographic Levels defined by the US Census Bureau 6 .…”

“…However, it is still hard to comprehensively assess the food system resilience with complex multidimensional information (e.g., multiple commodity types, suppliers and customers, geographic proximity, and at different scales). With the recent advances in geospatial knowledge graphs (GeoKG) [12,17], the importance of spatial concepts (e.g., the scale of geographic entities and spatial dependence) has been addressed in knowledge discovery, semantic reasoning, etc. Such concepts can be integrated with food systems [9] to help decision makers understand and improve the structure and resilience of food supply chain networks, thereby safeguarding local, regional, and global food security.…”

Corrigendum

“…In the article by Krzysztof Janowicz et al. (2022), the biography of co‐author Dawn Wright has been updated as follows:…”