Big Earth Data

GeoAI and DGGS: Advancing Big Earth Data Analytics

The rapid growth of geospatial data from satellites, airborne platforms, in-situ sensors, simulations, and other emerging sources is creating unprecedented opportunities to observe Earth processes, understand environmental changes, and support data-driven decision-making across scales. Geospatial artificial intelligence (GeoAI) is increasingly becoming central to realizing this potential by enabling automated representation learning, pattern discovery, prediction, and reasoning from large and complex geospatial datasets. However, the effective integration and analysis of these data remain constrained by heterogeneous spatial resolutions, coordinate reference systems, data structures, and sampling schemes. Conventional spatial representations, including latitude-longitude grids and projected coordinate systems, can also introduce geometric distortions and inconsistencies that complicate global and multi-scale analysis. On the other hand, Discrete Global Grid Systems (DGGS) offer an alternative spatial framework based on hierarchical global tessellations and persistent cell-based indexing, providing new opportunities for organizing, integrating, and analyzing heterogeneous geospatial data across scales. Despite growing interest in both DGGS and GeoAI, important challenges remain in combining their capabilities, developing AI-ready geospatial data infrastructures, enabling scalable learning and reasoning across spatial hierarchies, and ensuring that resulting analyses are reproducible, interoperable, and trustworthy.

This special issue aims to examine recent advances at the intersection of DGGS and GeoAI and their applications to big geospatial/Earth data. It welcomes theoretical, methodological, and application-oriented research on global grid representations, geospatial data integration, spatial artificial intelligence, and scalable Earth data analytics. Particular interest is given to research that explores how DGGS can support AI-ready data organization, multi-source and multi-modal data integration, spatial learning and reasoning across scales, and emerging GeoAI approaches such as geospatial foundation models, large language models, and AI agents. By bringing together advances in spatial data infrastructures and artificial intelligence, this special issue seeks to identify new methods and research directions for building scalable, interoperable, and intelligent systems for Earth observation, environmental understanding, and geospatial decision support.

Potential topics include (but are not limited to) the following:

• DGGS-based geospatial data infrastructure and interoperability
• Spatial indexing, hierarchical data organization, and AI-ready geospatial data cubes
• Multi-source and multi-modal geospatial data integration using DGGS
• GeoAI and machine learning with DGGS for geospatial applications
• DGGS-based prediction, pattern discovery, and spatial reasoning
• Scalable cloud, distributed, and high-performance computing for DGGS and GeoAI
• Trustworthy and reproducible DGGS-GeoAI with uncertainty, provenance, and explainability
• Digital twins of the Earth and AI-driven scenario modeling of DGGS
• Geospatial foundation models, large language models, and AI agents for Earth data
• DGGS and GeoAI applications in Earth observation, climate and environmental monitoring, disaster management, urban systems, agriculture, natural resources, and sustainable development