Jojo666/computational-malaria-modelling

Statistical and AI Malaria Modelling in Africa # Malaria Modelling Experiments This repository contains a collection of modelling experiments exploring different computational approaches for analysing malaria transmission dynamics. The goal of the repository is to prototype and compare modelling approaches commonly used in infectious disease modelling, including: mechanistic epidemiological models statistical and machine learning models spatiotemporal forecasting methods deep learning approaches neural surrogate models for simulation acceleration ## Data All examples currently use synthetic datasets designed to resemble realistic malaria transmission patterns. The synthetic data generation process incorporates several known epidemiological and environmental drivers of malaria dynamics, including: seasonal rainfall cycles temperature suitability for mosquito development vegetation and environmental indicators spatial autocorrelation between neighbouring regions lagged relationships between climate drivers and malaria incidence interannual variability resembling ENSO-driven fluctuations The datasets therefore mimic key properties observed in real malaria surveillance data while remaining fully reproducible and suitable for methodological experimentation.