Towards Intelligent Geospatial Data Discovery: a knowledge graph-driven multi-agent framework powered by large language models
arXiv:2603.20670v1 Announce Type: new Abstract: The rapid growth in the volume, variety, and velocity of geospatial data has created data ecosystems that are highly distributed, heterogeneous, and semantically inconsistent. Existing data catalogs, portals, and infrastructures still rely largely on keyword-based search with limited semantic support, which often fails to capture user intent and leads to weak retrieval performance. To address these challenges, this study proposes a knowledge graph-driven multi-agent framework for intelligent geospatial data discovery, powered by large language models. The framework introduces a unified geospatial metadata ontology as a semantic mediation layer to align heterogeneous metadata standards across platforms and constructs a geospatial metadata knowledge graph to explicitly model datasets and their multidimensional relationships. Building on the structured representation, the framework adopts a multi-agent collaborative architecture to perform
arXiv:2603.20670v1 Announce Type: new Abstract: The rapid growth in the volume, variety, and velocity of geospatial data has created data ecosystems that are highly distributed, heterogeneous, and semantically inconsistent. Existing data catalogs, portals, and infrastructures still rely largely on keyword-based search with limited semantic support, which often fails to capture user intent and leads to weak retrieval performance. To address these challenges, this study proposes a knowledge graph-driven multi-agent framework for intelligent geospatial data discovery, powered by large language models. The framework introduces a unified geospatial metadata ontology as a semantic mediation layer to align heterogeneous metadata standards across platforms and constructs a geospatial metadata knowledge graph to explicitly model datasets and their multidimensional relationships. Building on the structured representation, the framework adopts a multi-agent collaborative architecture to perform intent parsing, knowledge graph retrieval, and answer synthesis, forming an interpretable and closed-loop discovery process from user queries to results. Results from representative use cases and performance evaluation show that the framework substantially improves intent matching accuracy, ranking quality, recall, and discovery transparency compared with traditional systems. This study advances geospatial data discovery toward a more semantic, intent-aware, and intelligent paradigm, providing a practical foundation for next-generation intelligent and autonomous spatial data infrastructures and contributing to the broader vision of Autonomous GIS.
Executive Summary
This study proposes a knowledge graph-driven multi-agent framework for intelligent geospatial data discovery, leveraging large language models to address the limitations of existing data catalogs and portals. The framework introduces a unified geospatial metadata ontology, constructs a geospatial metadata knowledge graph, and adopts a multi-agent collaborative architecture to perform intent parsing, knowledge graph retrieval, and answer synthesis. Results from use cases demonstrate substantial improvements in intent matching accuracy, ranking quality, recall, and discovery transparency compared to traditional systems. This framework advances geospatial data discovery towards a more semantic, intent-aware, and intelligent paradigm, providing a practical foundation for next-generation intelligent and autonomous spatial data infrastructures.
Key Points
- ▸ Introduction of a unified geospatial metadata ontology as a semantic mediation layer
- ▸ Construction of a geospatial metadata knowledge graph to model datasets and their multidimensional relationships
- ▸ Adoption of a multi-agent collaborative architecture for intent parsing, knowledge graph retrieval, and answer synthesis
Merits
Strength in addressing semantic inconsistencies in geospatial data
The proposed framework effectively addresses the limitations of existing data catalogs and portals by introducing a unified geospatial metadata ontology and a geospatial metadata knowledge graph, enabling more accurate and transparent data discovery.
Demerits
Scalability and performance challenges
The framework's reliance on large language models and knowledge graphs may lead to scalability and performance issues, particularly when dealing with large volumes of geospatial data.
Expert Commentary
The proposed framework represents a significant advancement in geospatial data discovery, leveraging the power of large language models and knowledge graphs to address the limitations of existing systems. However, scalability and performance challenges must be carefully addressed to ensure the framework's practicality and usability. The framework's implications for policy and practice are substantial, with potential benefits for data-driven decision-making, transparency, and accountability. Further research is needed to fully explore the framework's potential and address the challenges associated with its implementation.
Recommendations
- ✓ Further research is needed to address scalability and performance challenges
- ✓ Exploration of the framework's potential applications in various sectors, including emergency response, urban planning, and environmental monitoring
Sources
Original: arXiv - cs.AI
