Artificial intelligence is rapidly transforming the Earth and environmental sciences, yet the effectiveness and reliability of AI depend fundamentally on the quality, interoperability, semantics, provenance, and machine-actionability of the underlying data. While FAIR principles have substantially advanced scientific data stewardship, emerging GeoAI, foundation models, multimodal AI, and agentic systems require research data infrastructures that move beyond data accessibility toward AI readiness.
This session brings together the geoscience, data science, research infrastructure, and semantic-web communities to explore how FAIR and interoperable data ecosystems can support trustworthy AI-enabled scientific discovery. We particularly welcome work addressing semantic interoperability, FAIR Digital Objects, knowledge graphs, machine-actionable metadata, controlled vocabularies and ontologies, provenance, AI-ready data standards, and emerging frameworks such as CDIF, Croissant, Semantic Croissant, and GeoCroissant.
We invite methodological developments, infrastructures, standards, demonstrators, and applications involving Earth observation, climate and environmental data, geospatial information, urban digital twins, sensor networks, social and human-generated data, and other heterogeneous scientific resources.
The session aims to connect data stewardship and interoperability communities with researchers developing the next generation of AI-enabled Earth and environmental science, and to identify practical pathways toward open, interoperable, trustworthy, and AI-ready scientific ecosystems.