ClimAID: An AI-integrated Global Hybrid Climate-Disease Modelling Framework

This study presents ClimAID, an AI-integrated, calibration-enhanced climate–disease modelling framework designed to produce reproducible, climate-informed infectious disease predictions at fine administrative scales, with a central emphasis on its deterministic reporting module. The framework integrates a terminal-based reproducibility wizard, browser interface, and a deterministic AI-assisted reporter that generates standardized, transparent, and fully reproducible documentation across datasets and geographic contexts. By combining epidemiological data, high-resolution meteorological variables, and CMIP6 climate projections, ClimAID ensures consistency in both analytical outputs and their interpretation. Demonstrated in a dengue-endemic district in India, the workflow includes data preprocessing, integration of lagged predictors, model calibration, and scenario-based projections. The deterministic reporter minimizes subjectivity in scientific reporting, reduces manual effort, and ensures consistency across analyses. Coupled with dual-baseline outbreak risk flagging, ClimAID extends beyond prediction toward reliable early warning. Its scalable design supports global application and future enhancements in climate–health surveillance systems.