Designing participatory early warning systems that integrate localized data collection, artificial intelligence, and hazard physics modelling to improve risk awareness, communication, and adaptive capacity at the community level.
Summary
This research line aims to design participatory early warning systems that integrate local data collection, artificial intelligence, and physical hazard modeling to enhance risk awareness, communication, and adaptive capacity at the community level. Leveraging expertise in climate impacts, extreme events, and environmental modeling, the goal is to co-develop effective warning strategies that are responsive to local contexts and needs. The approach emphasizes the active involvement of communities in data gathering, validation, and system operation, fostering co-production of knowledge and empowering local populations to better understand and respond to environmental threats. By combining cutting-edge AI techniques with community engagement, this research seeks to strengthen resilience and promote inclusive disaster risk reduction.
Objectives
To design and implement participatory early warning systems that combine localized data collection, artificial intelligence, and hazard modelling to enhance risk awareness, communication, and adaptive capacity at the community level.
