Artificial Intelligence Discrete Global Grid System (DGGS) for Disaster Management: Call for Participation (CFP)

For historical reasons, Geographic Information Systems (GIS) rely on a projected, scale-dependent representation of the Earth that was developed for navigation with paper maps, resulting in distortions. In contrast, Discrete Global Grid Systems (DGGS) provide a natively digital, cell-based approach that accurately represents the Earth as a spheroid. DGGS divide the planet into hierarchically tessellated cells across all scales, functioning as a “spreadsheet for Earth” that supports efficient analysis and integration of large datasets. With fixed-area cells, data related to a phenomenon at a specific location can be directly linked to its corresponding cell(s). This allows for quick integration with cell values from various datasets and efficient analysis to produce valid summaries for any selection of cells. DGGS simplify the ingestion of statistical and other gridded data into broader geospatial systems, thereby unlocking significant potential for enhanced contextual analysis and insights.  DGGS can be developed in various ways to fulfill different objectives. Ensuring interoperability among diverse DGGS is essential for users and software employing different DGGS methods to collaborate effectively. This DGGS-oreinted Pilot aims to explore and demonstrate this interoperability. 

DGGS represent locations as cells, moving beyond traditional geographic reference systems. DGGS are ideal for data integration, efficient querying, and serving as authoritative content stores for Artificial Intelligence (AI) powered natural language queries. The “AI-DGGS for Disaster Management Pilot” initiative explores how different DGGS grid designs can use OGC Standards for automatic data exchange, focusing on disaster management. It will also investigate enhancing DGGS with AI/Machine Learning (ML) tools, such as chatbots for natural language queries and AI-driven insights, using a Retrieval-Augmented Generation (RAG) approach for accurate, authoritative responses. RAG is a hybrid architecture that integrates a retriever model to fetch pertinent documents from an external knowledge base and a generator model to create answers based on the retrieved documents. Unlike traditional language models, RAG accesses external data during inference. It enhances factual accuracy and reduces hallucination by grounding responses in retrieved content, making it useful for knowledge-intensive tasks like open-domain question answering. DGGS serve as a localization identifier system for real-world objects, organizing space with nested cells. A list of cell IDs describes the geometries, with accuracy depending on cell size. DGGS can integrate data described at different zoom levels, making them suitable for various domains like finance, disaster management, and environmental analysis. They can replace postal addresses, eliminating the need for descriptive addresses or landmarks, accurately identifying areas without traditional infrastructure, and adapting to dynamic urban growth. 

The "AI-DGGS for Disaster Management Pilot" aims to prototype the potential of OGC standards to facilitate the interoperable use of DGGS combined with AI for disaster management applications. This project will include assessing the suitability of existing OGC standards for enabling AI-DGGS data integration, analysis, and visualization, while identifying further steps needed for OGC standards to fully support AI-DGGS interoperability requirements within disaster management systems. Key deliverables will include the clients, servers, and the visualization platform, which will demonstrate this interoperability. The results will be documented in the final report. Furthermore, all demonstrators will be maintained by the participants for an additional year after the pilot’s completion to showcase the AI-DGGS interoperability capabilities.

Consultation with emergency management professionals, industry professionals, and other government department officials indicates that current mapping software packages are limited in scope and lack AI integration, limiting their ability to support complex disaster management requirements. Disasters are global and so should be the mapping platforms that integrate data needed to inform planning and preparedness, response and recovery activities.

The Canadian Geospatial Data Infrastructure (CGDI), led by Natural Resources Canada’s (NRCan) GeoConnections Program, enables Canadians to find, access, and share location information to support decision-making, enhance analysis, and inform policy development across various sectors. As climate change intensifies disasters, geospatial data becomes increasingly crucial for disaster planning, response and recovery. NRCan aims to ensure that CGDI’s geospatial standards meet the needs of Canada’s emergency professionals.

The French Space Agency (CNES) and the European Space Agency (ESA) are actively engaged in advancing the application of Discrete Global Grid Systems (DGGS) to enhance geospatial data analysis and integration. These efforts align with their broader goals of improving Earth observation capabilities and supporting global environmental monitoring. The adoption of DGGS allows for scalable, uniform coverage of the Earth’s surface, enhancing the precision and interoperability of geospatial datasets. For example, ESA’s "Big Data from Space" (BiDS) initiative has been a key driver in the development of XDGGS, which integrates DGGS into Python’s Xarray library, facilitating the handling of multi-dimensional geospatial datasets.

The United States Geological Survey (USGS) maintains and distributes vast geospatial datasets—such as topographic maps, satellite imagery, and elevation models—and continues to explore and support various data-management standards to facilitate integration, analysis, and sharing of information. In alignment with its mandate to ‘describe and understand the Earth; minimize loss of life and property from natural disasters; manage water, biological, energy, and mineral resources; and enhance and protect our quality of life,’ the USGS also provides the reliable scientific information needed to advance research, inform policy, and protect the public. By refining data collection and analysis efforts, the USGS ensures its expanding repository of geospatial information can effectively guide decision-making on environmental issues, resource management, and hazard mitigation—ultimately strengthening the United States of America’s ability to understand and safeguard its natural landscapes and resources.

The global leader in geographic information standards, the Open Geospatial Consortium (OGC), is developing standards to enhance interoperability. As DGGS advances, standards will be key for ensuring diverse types of data can be easily incorporated, and that independently operated DGGS can communicate. NRCan is committed to advancing early DGGS interoperability to increase the benefits of this technology for all who live in Canada. The advancements in DGGS are also fostering considerable interest within the USGS.

Artificial Intelligence (AI) is evolving at a pace that is challenging traditional mapping products. Traditional mapping interfaces and software are cumbersome to operate and integrate new and real-time data, still requiring a level of mapping and technical expertise. Web mapping products lack intuitive AI based interfaces that use natural language to generate visuals and answer questions. DGGS, combined with AI, presents an opportunity to revolutionize how mapping is undertaken by making mapping analyses easier for existing and new users. Standards development will be critical for ensuring sufficient data and system interoperability is in place to maximize the broad use of DGGS and AI approaches.

This pilot will explore how disaster management can be improved by relying on OGC standards for AI and DGGS.

Please consider the following tips regarding the eligibility criteria for this pilot.

The following table details the major Initiative milestones and events for the AI DGGS Disaster Management Pilot. Dates are subject to change.

During the pilot, weekly or biweekly check-ins will be held for participants to discuss progress, highlight challenges, and share perspectives on key issues through video conferences.

Objectives will be delivered by tasks described in Technical Requirements The following general requirements apply to all tasks:

All aspects of the project will be based on the following hypothetical disaster scenario to focus activities. Over a period of several months, the Province of Manitoba has experienced severe weather which led to the following hazard events:

Emergency managers aim to better respond to these hazard events by understanding:

To support this understanding, emergency managers wish to integrate multiple sources of geographic and statistical information together to create a “common operating picture” – a single view of information available to support decision making. DGGS and AI will be used to provide this common operating picture. Emergency managers are also interested in understanding potential impacts of climate change on future floods. They wish to understand the potential of DGGS to assist with this, including:

Project activities completed in the context of this scenario must consider NRCan requirements for the Emergency Geomatics Service (EGS) and Manitoba’s emergency management approaches, which are both well-defined and fully operational. Project activities must include application over the Red River of Manitoba at minimum (i.e. portion of the Red River from the border to Lake Winnipeg). Work shall also consider portions of the contributing Red River watershed in the United States. Developed DGGS approaches must show how this technology can facilitate improved interoperability to complement EGS’ and the province’s existing emergency management framework for floods and EGS products as input.

All project activities shall consider the following persona. Deliverables shall be constructed so that they allow the requirements of the persona to be met within the context of the project scenario.

Emergency Response Coordinator

To this end, developed prototypes must possess the following key features:

This section identifies the technical objectives of the AI DGGS for Disaster Management Pilot initiative and the corresponding activities and deliverables. All deliverables are identified by the identifier Dxxx, with "xxx" being a three-digit number.

It is expected that proposals to achieve these technical objectives will build on and refer to the OGC standards baseline, i.e., the complete set of member-approved Abstract Specifications, Standards including Profiles and Extensions, and Community Standards, where relevant.

The following task descriptions outline the requirements to meet the project’s objectives.

Task 1: Demonstrate the interoperability of DGGS using the draft OGC API – DGGS standard

The participant shall demonstrate how independent DGGS can interoperate through the draft OGC API – DGGS standard. This shall include:

Task 2: Demonstrate the ability of different OGC standards to enable integration of forms of geospatial and statistical data using DGGS.

Within the context of the project’s scenario, the participant shall demonstrate how DGGS can support the integration of different forms of geospatial and statistical information using interoperable, OGC standards-based approaches. This shall include:

Task 3: Evaluate the ability of OGC standards to enable DGGS analysis for emergency management decisions

The participant shall demonstrate how DGGS, using OGC standards-based approaches, can support analysis of geospatial and statistical data to inform emergency management decision making. This shall include:

Task 4: AI in Depth. Explore the ability of OGC standards to enable use of AI approaches with DGGS

AI approaches are increasingly important as a mechanism for completing geospatial analysis and for obtaining insights from geographic and other forms of information. AI approaches will be applied in the context of DGGS; it is thus necessary that OGC standards used to enable DGGS interoperability be designed to support the application of AI to DGGS. In this context, this task shall include:

“Identify neighbourhoods that will likely be impacted by flooding.”

The participant shall demonstrate linkages between the use of LLM and the AI requirements for geospatial analysis and/or predictive modelling listed above (e.g. demonstrate how submission of a question through an AI chatbot can invoke geospatial analysis and/or predictive modelling approaches to return an answer in both text and visual formats).

Task 5: Prototype the use of OGC standards for enabling interoperable visualization within DGGS in a disaster management context

The participant shall demonstrate how DGGS approaches, through OGC API – DGGS as well as other OGC standards, can support visualization of geographic and statistical information. The visualization methods used must align with and support the project’s scenario. This shall include:

Task 6: Create and maintain availability of prototypes and demonstrations beyond the project end date

Execution of the project will result in the creation of a prototype accessible via the web and demonstrations of the use of OGC approaches for delivering interoperable AI-DGGS solutions in a disaster management context. There is a need for these materials to be made available beyond the end date of this contract. This shall include:

Figure 1 depicts the architecture and deliverables of the AI-DGGS Disaster Management Pilot.

The complete set of deliverables namely: D001, D100 and D102, cover all the requirements defined in the Technical Requirements and implement them according to the requirements described in Project Scenario and General Requirements.

This initiative is being conducted under the OGC Collaborative Solutions and Innovation (COSI) Program, which aims to solve the biggest challenges in location. Together with OGC members, the COSI Team is exploring the future of climate, disasters, autonomy and robots, outer space systems interoperability, defense and intelligence, and more.

The OGC COSI Program is a forum for OGC members to solve the latest and most complex geospatial challenges via a collaborative and agile process. OGC members (sponsors and technology implementers) come together to solve problems, produce prototypes, develop demonstrations, provide best practices, and advance the future of standards. Since 1999, more than 125 funded initiatives have been executed - from small interoperability experiments run by an OGC working group to multi-million dollar testbeds with more than three hundred OGC-member participants.

OGC COSI initiatives promote rapid prototyping, testing, and validation of technologies, such as location standards or architectures. Within an initiative, OGC Members test and validate draft specifications to address geospatial interoperability requirements in real-world scenarios, business cases, and applied research topics. This approach not only encourages rapid technology development but also determines the technology maturity of potential solutions and increases technology adoption in the marketplace.

The following table lists all abbreviations used in this CFP.

The following table identifies all corrections that have been applied to this CFP compared to the original release. Minor editorial changes (spelling, grammar, etc.) are not included.

The following table identifies all clarifications that have been provided in response to questions received from organizations interested in this CFP.