Group leaders
Summary
Scholarly publications play a crucial role in designing any hypothesis, projects, reports, thesis etc. and are helpful in making policies. Besides growing rapidly much of it remains locked in unstructured formats such as PDFs and lengthy reports, limiting reuse, synthesis, and policy relevance. The growth of large volumes of scholarly publications has also made it difficult to keep up the updated records. There is a limitation to the number of articles we can get from any repository. Some journals did not allow bulk downloading of the articles. The current open access model focuses on individual papers: find a paper on any query, download it, and read it manually.
semanticClimate approach moves beyond this by making the content semantically available, meaning it can be accessed not only by people (including those who use audio or alternative formats) but also by machines, enabling automated search, analysis, and the creation of semantically enriched corpora.
The semantic toolkits are open python-based toolset for automated large scale literature retrieval and corpus creation (pygetpapers), document processing (amilib), and semantic extraction of entities such as species, locations, chemical compounds, and other climate-relevant concepts (docanalysis/NER). The workflow addresses the community need for open, reproducible infrastructure that enables large-scale evidence synthesis, supports interdisciplinary research, and amplifies the reuse of knowledge beyond PDF and text formats.
The project not only contributes to open knowledge infrastructure but also supports capacity building, especially for early-career researchers and students.
Deliverables
- Extraction of a structured climate ontology as a knowledge graph.
- Interrogation of 15,000 pages of the IPCC AR6 reports (and hopefully emerging releases of AR7) , the current Open scientific literature.
- Enrichment with trusted knowledge (IPCC, publications, Wikipedia)
- Development of scholarly tech – semanticCorpus (2026) holds a searchable collection of articles and links with metadata management.
- Development of encyclopedia/knowledge_graph -a generally accessible technology which can give non-experts answers within an hour
