cheCkOVER: An open framework and AI-ready global crayfish database for next-generation biodiversity knowledge

Abstract

Background Species occurrence records represent the backbone of biodiversity science, yet their utility is often limited to spatial analyses, coarse distribution maps, or presence-absence models. Current biodiversity infrastructures rarely provide computational formats directly usable by modern artificial intelligence (AI) systems, such as large language models (LLMs), which increasingly mediate scientific communication and knowledge synthesis. Open frameworks that convert biodiversity occurrences into structured, machine-accessible knowledge are therefore essential, particularly when they enable rapid integration of new records and near real-time generation of spatial metrics and human-interpretable reports. Such capabilities substantially reduce the latency between data acquisition and decision support, enabling rapid production of updated range summaries and narrative outputs consumable by both domain experts and AI-assisted decision-making systems. Results We introduce cheCkOVER, an open framework that converts raw species occurrence datasets into standardized, API-ready, multi-layered outputs: biogeographic descriptors, dynamic distribution maps, summary metrics, and structured JSON biogeographic-narratives, ready for rapid integration into conservation evaluation workflows. Each product embeds provenance metadata to ensure transparency, traceability, and citation. We applied the pipeline to 115,434 global crayfish (Astacidea) occurrence records, generating an AI-ready knowledge base of 458 species packages. This demonstrates how the framework transforms minimal datapoints, validated species occurrences, into interoperable knowledge consumable by both humans and computational systems. The JSON outputs are optimized for retrieval-augmented generation, enabling AI systems to dynamically access and cite biodiversity knowledge beyond their pre-training corpora. Conclusions cheCkOVER is taxon-generalizable and establishes a reproducible pathway from biodiversity occurrences to narrative-ready, AI-interoperable knowledge. The framework's dual output, a generalizable pipeline and taxon-specific knowledge databases, enables flexible reuse across conservation research, policy reporting, and AI-driven applications. This minimalist-to-complex design extends the reach of biodiversity data beyond traditional analyses, positioning occurrence repositories as pivotal engines for next-generation biodiversity knowledge systems.

Links & Resources

Authors

Cite This Paper