AI-Based Predictive Surveillance of Malaria in Northern Nigeria Using Climate and Demographic Data

Malaria remains a major public health challenge in North Nigeria, where climate conditions and demographic pressures contribute to recurring outbreaks (WHO, 2023). Traditional surveillance systems often struggle with delays and limited data, making it difficult to predict malaria trends accurately (Nigeria Malaria Indicator Survey, 2021). This study applies Artificial Intelligence (AI) techniques to explore how climate and demographic information can support early prediction of malaria cases in the region. A regional dataset containing monthly temperature, rainfall, air quality index, UV index, population density, and malaria incidence was analyzed. Machine learning models were developed using climate lag features, seasonal patterns, and demographic indicators to improve forecasting performance, following approaches successfully applied in previous climate-disease modeling studies. The results show that rainfall, temperature, and population density are strong predictors of malaria incidence in North Nigeria, consistent with findings from prior ecological and epidemiological research. The AI-based model produced reliable monthly forecasts, demonstrating the potential of integrating climate and demographic data for predictive malaria surveillance. This approach provides a practical tool that can enhance early warning systems and support better planning and prevention efforts in North Nigeria, aligning with calls for innovative, data-driven malaria control strategies across Africa.