#ClimateKG will be used for the #IPCC #AR6 corpus of 7 main reports of 10,000 pages. For corpus browsing, republishing, community enrichment. The constructed knowledge graph in Wikibase/MediaWiki allows browsing using the familiar #MediaWiki interface with #Wikidata enhancements like infoboxes, and #scholia like interfaces https://scholia.toolforge.org/ | Republishing is intended for sharing or reviewing search results on climate topics | Enrichment is for data scientists to make use of reports >>>

#ClimateKG - the #IPCC #AR6 reports are a pretty big beast. Authored over 7 years they are the ultimate #statusupdate of planet earth. Quant data: https://doi.org/10.5281/zenodo.17521936 - Reports 7, Pages 10,047, Words 8,047,000, Citations 48,400, Data 66,834, Figures 1,672, Authors 1,106, Glossary 925, Acronyms 3,041, Lang 5+. The entity relationship model is need to map the parts of the reports, relations, then to allow markup of entities, concepts, etc

#ClimateKG project is developing an Entity Relation Model to represent the syntactic structure of a scientific document in a knowledge graph.

We are reaching out to ask for recommendations of projects, literature, methods, etc.

The ClimateKG will hold #IPCC #AR6 corpus of 7 reports for browsing, republishing, enrichment.

Knowledge graph uses #Wikibase / #MediaWiki

Write up: https://github.com/TIBHannover/climate-knowledge-graph/issues/51

IPCC AR6 corpus: https://doi.org/10.5281/zenodo.17516065

ClimateKG project: https://tibhannover.github.io/climate-knowledge-graph

Workshop #semanticClimate : AI-Assisted Literature Review at WII, Dehradun, North India - @ Wildlife Institute of India (WII) https://semanticclimate.github.io/p/en/events/ALR_bio/ Session 1 : Fundamentals of AI and Natural Language Processing (NLP)
Session 2 : Workspace Demo: AI over NLP using our Semantic Toolkit
Session 3 : DIY! AI over Your Own Literature Metadata #ClimateKG

🧵 8/8 - At TIB #ClimateKG is based in the Open Science Lab @tibosl and makes use of expertise from the NFDI4Culture @nfdi4culture
which are clustered around #LOD and @Wikibase (cultural heritage consortium of the larger German National Research Data Infrastructure Consortium) projects: #Wikibase4Research, Computational Publishing Service #CPS and #Antelope (terminology service). The following services can be found no the NFDI4Culture website - https://nfdi4culture.de/services.html

🧵 7/8 - #ClimateKG TIB #knowledgegraph expertise further supports the work - ClimateKG partners with and is supported in knowledge graph expertise by Lab Knowledge Infrastructures led by Dr Markus Stocker. https://www.tib.eu/en/research-development/research-groups-and-labs/knowledge-infrastructures | One project of the lab is looking at how fully computational papers can be created, athored as #reborn papers with specific IPCC examples 'The global impacts of COVID-19 lockdowns on urban air pollution: A critical review and recommendations' https://doi.org/10.48366/dvy9yr04

🧵 6/8 - #ClimateKG is based at TIB and makes use of the knowledge graph work going on in T&D. TIB is one of the largest science libraries in the world and is a global hub for knowledge graph R&D — service development, and infrastructure provision — especially the Open Research Knowledge Graph (ORKG). https://orkg.org/ - as an examples ORKG Curation grants https://orkg.org/page/curation-grants-2024-call-for-applications | AI assisted search https://ask.orkg.org/ #climatechange #knowledge #graphs https://ask.orkg.org/s/j5hiede20dy1jni

🧵 3/8 - ClimateKG comes directly out of the five year old #semanticClimate open research group founded by Dr. Gitanjali Yadav of the National Institute of Plant Genome Research #NIPGR Delhi, Dr Peter Murray-Rust of Cambridge University, and Simon Worthington (TIB) which works on software tool development for semantic enrichment. #ClimateKG. Photo: National Conclave on AI and Ethics - https://semanticclimate.github.io/p/en/past-events/AI_Ethics/

🧵 2/8 - Climate Knowledge Graph is a development project for a service to structuring large climate change corpora to be machine readable, for re-publishing, and AI LLM search — all using open science methods. #ClimateKG - see an outline here https://github.com/TIBHannover/climate-knowledge-graph

job offer at @tibhannover working on building a knowedge graph for UN IPCC Reports - Software Developer (m/f/d) https://www.tib.eu/en/tib/careers-and-apprenticeships/vacancies/details/stellenausschreibung-nr-20-2025 deadline April 20 #FediHire #fedijobs #getfedihired - Some context and background on the project #ClimateKG #semanticClimate #knowledgegraph 🧵 1/8

🧵 9/9 How did we get here. #ClimateKG comes out of the five year old #semanticClimate (#sC) open research group founded by Dr. Gitanjali Yadav of the National Institute of Plant Genome Research (NIPGR), Delhi, Dr Peter Murray-Rust of Cambridge University, and Simon Worthington. We works on software tool development for semantic enrichment. #semanticClimate is active on a daily basis as a community and NIPGR supports an internship programme, hackathons, & outreach. Web: https://semanticclimate.github.io/

🧵 8/9 The 'Goal': Dissemination of IPCC Reports and #climatechange lit using #semantification as a basis. #ClimateKG is aimed at being a service for indexing and publishing. Status: Prototype (PoC) #1: 'IPCC Reports and City Climate Change Plans: Proof of concept prototype - Open Climate Reader' https://semanticclimate.github.io/city-open-climate-reader/ - Currently interfaces are for search and #RAG #LLM - all built on #openscience based #digitalsoveriegn tech. The goal sits off in future, over the horizon - but its we're going

🧵 7/9 #ClimateKG foundational software: Dictionaries, machine learning, etc. This all comes from team #semanticClimate. Status: Production. Here is a live demo that explains the tool chain of https://colab.research.google.com/github/semanticClimate/sC-tools-demo/blob/main/TTWW_demo_sC_tools.ipynb for machine learning and #TBL 5*-ification of data - shout out to the developers DEVELOPERS: 1. pygetpapers - Ayush Garg 2. amilib - Peter Murray-Rust 2. docanalysis - Shweata N Hegde 2. Jupyter notebooks - Parijat Bhadra, Renu Kumari

🧵 5/9 Data relationship model: Status Pre-alpha - This will be the core of 2025 work. The content has been preped, the #Wikibase infra is ready. Plans are to #KISS and build up a simple framework for the #climate community to connect to. Experiments have been made on #Wikibasecloud https://kg-ipclimatec-reports.wikibase.cloud/wiki/Main_Page - thanks to Egon Willighagen, Lars Willighagen 🚀 #ClimateKG #semanticClimate

🧵 4/9 IPCC Glossary semantification and enhancement. The 800+ terms from AR5 and AR6 have had several experimental rounds carried out: Screenscraped to GitHub, loaded into a Wikibase install, demonstrated as a index to tag documents, rendered out to Paged Media CSS with Wikipedia enhancements, and translation to Hindi. #ClimateKG #semanticClimate - In #wikibase https://climatekg.semanticclimate.net/index.php?title=IPCC_Begriffe as Paged Media CSS using #vivliostyle https://vivliostyle.vercel.app/#src=https://raw.githubusercontent.com/semanticClimate/glossary-demo/main/ipccglossary.jsonld

🧵 3/9 Next is a Report top level data structure: Table of Contents (Visualisation) of AR6 70 chapters. Status #Alpha - the chapters of Sixth Assessment Report — IPCC. Using #graphvis in Python the chapters and their connections are automatically mapped #semanticClimate #ClimateKG https://github.com/semanticClimate/internship_sC/tree/MEBIN/TOC The TOC structure is designed to provide a clear and hierarchical representation of report sections, including chapters, glossaries, supplemental materials, and cross-chapter references.

Software Developer (m/f/d) job offer at @tibhannover working on building a knowedge graph for UN IPCC Reports https://www.tib.eu/en/tib/careers-and-apprenticeships/vacancies/details/stellenausschreibung-nr-20-2025 deadline April 20 #FediHire #fedijobs #getfedihired #ClimateKG #semanticClimate - Here's a breakdown of what we'll be doing over next year - 🧵 1/9

🧵 6/6 #ClimateKG would be able to return a search result that gives links to all the related IPCC Report chapters, but also provide a list of authors, their global locations, the related research paper citations used in the report — all as neat search results and as a full text publication package. The derivative publications would be automatically typeset, available multi-format, and as semantically marked up outputs.😸 Apply for the #developer #job here: https://www.tib.eu/en/tib/careers-and-apprenticeships/vacancies/details/stellenausschreibung-nr-20-2025 @tibhannover

🧵 5/6 - using #ClimateKG the #IPCC reports can have search and logical reasoning, for example if the following question was asked: ‘How to design a city climate action plan to mitigate against extreme weather such as floods and fires — what are the mitigation policy options — and where are the authoring scientists geographically based?’.

🧵 4/6 IPCC Reports are published as PDF and some being available as webpages.
The #ClimateKG project will create a knowledge graph of the reports, initially with the #openaccess parts of IPCC Sixth Assessment Report (AR6) https://www.ipcc.ch/report/ar6/syr/ - to provide two open resources for others to use: 1. a modern open web index for searching IPCC Reports, and: 2. a publishing engine that can package search results. A knowledge graph is a database that precisely describes entities and relationships.