Integrating expertise from national and regional agencies on climate adaptation and weather warning systems, climate science and policy research, visualization and AI, the proposed project explores if and to what extent AI-based algorithms can be employed to evaluate the accuracy of impact-based weather warnings, and assesses the added value of integrating AI-based information into the existing weather warning systems.
This project sets out for three main tasks:
- Assessment of approaches for collecting image and text data appropriate for AI-based analysis derived from citizen science campaigns and social media
- Development of machine learning algorithms for text and image analysis
- Development and assessment of the application and results as part of a co-design process with climate adaptation experts, as well as with experts for the SMHI national weather warning system and involved authorities at local, regional and central level.