The Research Initiative for the Conservation of Biodiversity (FEdA) aims to sustainably deepen research on biodiversity and gain new insights into the state of biodiversity in Germany and the causes, dynamics, and consequences of biodiversity changes. This knowledge can then be used to develop effective system solutions. The research initiative's unique approach is to develop proposed solutions not only from a scientific and ecological perspective, but also to consider social and economic perspectives. A central task of FEdA is the development of innovative approaches to biodiversity conservation.
The Biodiversity Fact Check is a FEdA project for the comprehensive assessment and evaluation of biodiversity in Germany, including targeted action options to identify and develop concrete national and subnational policies. For this assessment, more than 150 scientists from 75 institutions and associations evaluated the findings from over 6,000 publications and compiled them in a specially developed database. To identify long-term developments, they created and analyzed an unprecedented dataset of approximately 15,000 trends from nearly 6,200 time series.
As part of the second project phase of the FEdA Central Coordination, the KIBA-D project "Continuous AI-based Biodiversity Assessments for Germany" is researching the foundations of an AI-based system in which experienced AI experts in the field of large language models, together with experts from the Fact Check on Biodiversity and the FEdA consortium, will use the fact check corpus and significantly expand it over the course of the project to train AI models to extract relevant data on biodiversity trends, causal relationships, and assessments of the effectiveness of instruments and measures from digitally available text information and – in an additional step – also analyze them jointly. To this end, a workflow for AI-supported extraction of biodiversity-relevant information from text sources, a crawling solution for finding and collecting additional sources, and LLM-based extraction models for the various subtasks will be developed.
The results of the KIBA-D project will be incorporated into the comprehensive literature database of the Biodiversity Fact Check and are intended to significantly expand this dataset. The establishment of a system for the continuous extraction of biodiversity data from digital texts, developed during the project, is intended to lay the foundation for continuous automated analysis of the generated data. The long-term goal is an accelerated, renewed comprehensive assessment by 2030.
Partners
- Deutsche Zentrum für integrative Biodiversitätsforschung Halle-Jena-Leipzig- iDiv e.V.
- Öko-Institut e.V.
- Unabhängiges Institut für Umweltfragen