Flexible metadata harvesting for ecology using large language models
This addresses a bottleneck for ecologists needing to combine datasets from multiple sources, though it is incremental as it applies existing LLM methods to a specific domain problem.
The paper tackles the challenge of finding and integrating ecological datasets from diverse platforms with varying metadata standards by developing an LLM-based metadata harvester that extracts and converts metadata into a unified format, achieving equal accuracy for structured and unstructured metadata and enabling dataset linking for tasks like ontology creation.
Large, open datasets can accelerate ecological research, particularly by enabling researchers to develop new insights by reusing datasets from multiple sources. However, to find the most suitable datasets to combine and integrate, researchers must navigate diverse ecological and environmental data provider platforms with varying metadata availability and standards. To overcome this obstacle, we have developed a large language model (LLM)-based metadata harvester that flexibly extracts metadata from any dataset's landing page, and converts these to a user-defined, unified format using existing metadata standards. We validate that our tool is able to extract both structured and unstructured metadata with equal accuracy, aided by our LLM post-processing protocol. Furthermore, we utilise LLMs to identify links between datasets, both by calculating embedding similarity and by unifying the formats of extracted metadata to enable rule-based processing. Our tool, which flexibly links the metadata of different datasets, can therefore be used for ontology creation or graph-based queries, for example, to find relevant ecological and environmental datasets in a virtual research environment.