ABSTRACT:
This study aims to enhance malaria control strategies in Zimbabwe by developing a proactive, spatially explicit framework for identifying, classifying, and mapping habitats of malaria-transmitting mosquito vectors. The core objective is to address limitations associated with reactive case reporting by providing data-driven, predictive insights that support targeted public health interventions. The research applies an integrated remote sensing and geospatial modelling approach. Multispectral satellite imagery and environmental variables are combined with spatial analysis and machine learning techniques to detect and classify mosquito breeding habitats. Field validation is incorporated to improve classification reliability. The outputs are synthesized into high-resolution malaria risk maps, which are further integrated into a web-based application designed for real-time visualization and monitoring of malaria risk patterns. The study is expected to produce detailed malaria risk maps capable of distinguishing habitats associated with malaria-causing mosquito species from those of non-vector species. These outputs will enable precise identification of high-risk areas, supporting more efficient allocation of malaria control resources. An operational web-based platform will demonstrate the feasibility of translating geospatial and predictive modelling outputs into actionable decision-support tools for public health authorities. The proposed framework demonstrates the value of combining remote sensing, spatial analysis, and predictive modelling for malaria vector surveillance. By shifting from reactive to anticipatory risk mapping, the study contributes to advancing geospatial health methodologies and provides a scalable model that can be adapted for other vector-borne diseases within sub-Saharan Africa. The findings support improved malaria prevention planning by enabling targeted vector control, enhanced surveillance, and evidence-informed decision-making. The web-based application offers a practical tool for public health practitioners to prioritize interventions, optimize resource use, and strengthen communication between data analysts and malaria control programmes.