CLIMAI: Anticipating and reducing climate-driven mosquito-borne disease risks through data and collaboration
PI and co-PIs: Clara Bermúdez-Tamayo (University of Granada, Spain); Puerto López del Amo González (University of Granada, Spain); Demetrio Carmona Derqui (University of Granada, Spain); Josué Martínez de la Puente (Doñana Biological Station EBD-CSIC, Spain); Jordi Figuerola (Doñana Biological Station EBD-CSIC, Spain); Valéry Ridde (French National Research Institute for Sustainable Development (IRD), France); Emmanuel Bonnet (French National Research Institute for Sustainable Development (IRD), France); Belén Rodríguez-Fonseca (Complutense University of Madrid, Spain); Irene Polo Sánchez (Complutense University of Madrid, Spain); Lyda Osorio (Universidad del Valle, Colombia); Mabel Carabali (McGill University, Canada); Gina Polo Infante (Pontificia Universidad Javeriana, Colombia); Jaime Jiménez-Pernett (Andalusian School of Public Health, Spain); Ainhoa Ruiz Azarola (Andalusian School of Public Health, Spain); Olga Leralta Piñán (Andalusian School of Public Health, Spain); Marta Martín del Rey (Complutense University of Madrid, Spain); Fabio Augusto González-Osorio (National University of Colombia, Colombia); Fabián Méndez Paz (Universidad del Valle, Colombia); Mario Rivera-Izquierdo (University of Granada, Spain); Ana Eduviges Sancho Jiménez (Ministry of Health, Costa Rica)
Funding amount: $125,000.00
Project overview: Climate change is altering temperature and rainfall patterns in ways that increase the spread and intensity of mosquito-borne diseases such as dengue, malaria, chikungunya, and West Nile virus, affecting both tropical and temperate regions and disproportionately impacting vulnerable populations. A key challenge for climate adaptation in public health is the lack of integrated systems that combine climate data with health outcomes, social conditions, public policies, and community responses. CLIMAI addresses this gap by creating a publicly accessible, machine-learning-ready dataset that integrates climate variables, disease indicators, social determinants of health, public health interventions, and primary data on community knowledge, attitudes, and practices collected in high-risk areas. Machine learning tools are used to generate risk maps and support early identification of vulnerable areas. Working with public health authorities, healthcare professionals, and communities in Colombia and Spain, and supported by an international team from Ibero-America, France, and Canada, CLIMAI aims to deliver scalable tools that strengthen climate-informed public health decision-making and support more equitable and resilient health systems.
Health Behavioral and Social Science Public Policy Societal Adaptation & Resilience Reinforcement Learning