Work

LLM-Based Metadata and Context Extraction for Agricultural Long-Term Experiments

Year: 2025

Type: article

Abstract: Long-term agricultural field experiments (LTEs) provide essential data for crop modeling and understanding agricultural processes under global change. Their reuse is limited by poor FAIR data practices and limited focus on specific experimental factors. Initiatives like the LTE-Overview Map have made a leap in metadata collection. However, manual processes remain inefficient.Our approach uses Large Language Models (LLMs) to automatically extract standardized, interoperable metadata from scientific literature, enhancing data discovery and reusability.

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.17302671

Authors: Lachmuth, Susanne, Hoffmann, Carsten, Donmez, Cenk, Ryo, Masahiro, Lischeid, Gunnar

Institution: Leibniz Centre for Agricultural Landscape Research

Language: English

Topic: Research Data Management Practices

Subfield: Information Systems

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Deutsche Forschungsgemeinschaft

Award: FAIRe Dateninfrastruktur für die Agrosystemforschung