Company or Institution
ETH Zurich
Industry
Other
Website
Country
Switzerland
Sustainable Development Goals (SDGs)
SDG 7: Affordable and Clean Energy
SDG 13: Climate Action
SDG 17: Partnerships to achieve the Goal
General description of the AI solution
We developed an artificial intelligence (AI) model to identify international climate finance from the project descriptions of official development assistance. From the project description, the AI model can categorize if a project is relevant for climate finance and, if yes, to what climate-relevant purpose it contributes (e.g., adaptation, solar energy). We have applied the model on 2.7 million project descriptions and validated the results extensively, via user studies and third-party data. Setting the AI model into practice can help to solve a fundamental problem of international climate finance: accountability. Currently, contributing nations are reporting their climate flows without independent verification checks. Our model could solve this issue in a cost-efficient way by flagging projects that have either been omitted by reporting contributors or potentially been over-reported.
Github, open data repository, prototype or working demo
https://github.com/MalteToetzke/consistent-and-replicable-estimation-of-bilateral-climate-finance
Publications
Toetzke, M., Stünzi, A. & Egli, F. Consistent and replicable estimation of bilateral climate finance. Nature Climate Change (2022). doi: https://doi.org/10.1038/s41558-022-01482-7
Roberts, T., Weikmans, R. Checking contentious counting. Nature Climate Change (2022). doi:
https://www.nature.com/articles/s41558-022-01483-6
Toetzke, M., Banholzer, N. & Feuerriegel, S. Monitoring global development aid with machine learning. Nat Sustain (2022). https://www.nature.com/articles/s41893-022-00874-z
Needs
Funding
Public Exposure