Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

The KnowWhereGraph: A Large-Scale Geo-Knowledge Graph for Interdisciplinary Knowledge Discovery and Geo-Enrichment

Rui Zhu, Cogan Shimizu, Shirly Stephen, Colby K. Fisher, Thomas Thelen, Kitty Currier, Krzysztof Janowicz, Pascal Hitzler, Mark Schildhauer, Wenwen Li, Dean Rehberger, Adrita Barua, Antrea Christou, Ling Cai, Abhilekha Dalal, Anthony D'Onofrio, Andrew Eells, Mitchell Faulk, Zilong Liu, Gengchen Mai, Mohammad Saeid Mahdavinejad, Bryce Mecum, Sanaz Saki Norouzi, Meilin Shi, Yuanyuan Tian, Sizhe Wang, Zhangyu Wang, Joseph Zalewski

TL;DR

KnowWhereGraph presents a large-scale, RDF-based geospatial knowledge graph that unifies diverse human–environment datasets through a modular schema centered on space, place, and time. It integrates over 30 open data sources into a cross-domain knowledge warehouse, uses a Discrete Global Grid (DGG) with S2 cells for multi-scale geography, and employs SOSA/SSN and GeoSPARQL ontologies alongside DEO/HIP hazard vocabularies. The authors deliver a suite of tools (Knowledge Explorer, Geo-Enrichment, and domain-specific apps) that enable rapid, geo-enriched queries, visualization, and decision support for disaster response, supply-chain risk, and land valuation. This framework aims to empower decision-makers with AI-ready, semantically rich data and to facilitate global, cross-domain knowledge discovery through scalable, standards-based interoperability.

Abstract

Global challenges such as food supply chain disruptions, public health crises, and natural hazard responses require access to and integration of diverse datasets, many of which are geospatial. Over the past few years, a growing number of (geo)portals have been developed to address this need. However, most existing (geo)portals are stacked by separated or sparsely connected data "silos" impeding effective data consolidation. A new way of sharing and reusing geospatial data is therefore urgently needed. In this work, we introduce KnowWhereGraph, a knowledge graph-based data integration, enrichment, and synthesis framework that not only includes schemas and data related to human and environmental systems but also provides a suite of supporting tools for accessing this information. The KnowWhereGraph aims to address the challenge of data integration by building a large-scale, cross-domain, pre-integrated, FAIR-principles-based, and AI-ready data warehouse rooted in knowledge graphs. We highlight the design principles of KnowWhereGraph, emphasizing the roles of space, place, and time in bridging various data "silos". Additionally, we demonstrate multiple use cases where the proposed geospatial knowledge graph and its associated tools empower decision-makers to uncover insights that are often hidden within complex and poorly interoperable datasets.

The KnowWhereGraph: A Large-Scale Geo-Knowledge Graph for Interdisciplinary Knowledge Discovery and Geo-Enrichment

TL;DR

KnowWhereGraph presents a large-scale, RDF-based geospatial knowledge graph that unifies diverse human–environment datasets through a modular schema centered on space, place, and time. It integrates over 30 open data sources into a cross-domain knowledge warehouse, uses a Discrete Global Grid (DGG) with S2 cells for multi-scale geography, and employs SOSA/SSN and GeoSPARQL ontologies alongside DEO/HIP hazard vocabularies. The authors deliver a suite of tools (Knowledge Explorer, Geo-Enrichment, and domain-specific apps) that enable rapid, geo-enriched queries, visualization, and decision support for disaster response, supply-chain risk, and land valuation. This framework aims to empower decision-makers with AI-ready, semantically rich data and to facilitate global, cross-domain knowledge discovery through scalable, standards-based interoperability.

Abstract

Global challenges such as food supply chain disruptions, public health crises, and natural hazard responses require access to and integration of diverse datasets, many of which are geospatial. Over the past few years, a growing number of (geo)portals have been developed to address this need. However, most existing (geo)portals are stacked by separated or sparsely connected data "silos" impeding effective data consolidation. A new way of sharing and reusing geospatial data is therefore urgently needed. In this work, we introduce KnowWhereGraph, a knowledge graph-based data integration, enrichment, and synthesis framework that not only includes schemas and data related to human and environmental systems but also provides a suite of supporting tools for accessing this information. The KnowWhereGraph aims to address the challenge of data integration by building a large-scale, cross-domain, pre-integrated, FAIR-principles-based, and AI-ready data warehouse rooted in knowledge graphs. We highlight the design principles of KnowWhereGraph, emphasizing the roles of space, place, and time in bridging various data "silos". Additionally, we demonstrate multiple use cases where the proposed geospatial knowledge graph and its associated tools empower decision-makers to uncover insights that are often hidden within complex and poorly interoperable datasets.

Paper Structure

This paper contains 28 sections, 1 equation, 14 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Spatial Data Infrastructures
  4. (Geo)portals
  5. Geospatial Knowledge Graphs
  6. Convention and Background
  7. Data Sources and Graph Overview
  8. Data Sources
  9. Graph Overview
  10. The KnowWhereGraph Schema
  11. Modeling Environmental Observations
  12. Modeling Time and Space
  13. Temporal Reference
  14. Geographic Regions
  15. Geo-referenced Cells
  16. ...and 13 more sections

Figures (14)

  • Figure 1: Overview structure of KnowWhereGraph.
  • Figure 2: This figure shows the highest level of abstraction that still depicts the meaningful structure of KnowWhereGraph. Pictured on top is the geospatial backbone, coupled with the bottom, how phenomena are conceptualized and subsequently integrated with the DGG.
  • Figure 3: This schema diagram shows the classes that are reused in KnowWhereGraph from the SOSA/SSN Ontology, OWL Time Ontology, QUDT (Quantities, Units, Dimensions, and Types Ontology), and Custom Data Types ontology.
  • Figure 4: Time Ontology used in KnowWhereGraph, adopted from Time-OWL.
  • Figure 5: Spatial Ontology used in KnowWhereGraph, adopted from GeoSPARQL Ontology. Blue boxes are classes from GeoSPARQL and yellow ones are newly designed for KnowWhereGraph. The class names of geographic regions are derived from the regional identifiers listed in Table \ref{['tab:regional-id']}. Particularly, NWZone corresponds to "National Weather Service Public Forecast Zones".
  • ...and 9 more figures