Modelling the influence of temperature and rainfall on the population dynamics of Mastomys natalensis in Nigeria

Lassa fever is a viral disease that is endemic, causing significant morbidity and mortality. However, the complexity of the disease dynamics and the interplay of environmental and climatic factors make it difficult to get a robust, accurate and reliable model for the disease outbreak prediction. The research therefore, developed a geo-computational based model for Lassa fever prediction. The geo-computational based model for Lassa fever outbreak prediction will be formulated based on random forest and the resulting model will be specified using Unified Modelling Language (UML). The simulation of the model was carried out in R Programming Language, Environmental and climatic data variables were used to drive the simulation. By integrating advanced computational techniques with geospatial and climatic variables, the model achieved a high accuracy rate of 87.74%, demonstrating its proficiency in outbreak prediction. Validation results, including an AIC value of 596.97 for the GLM model, underscore the reliability of the simulation outcomes. A predictive map generated from the model showcases its capacity to forecast outbreaks in Nigerian states. Through this approach, leveraging climatic and environmental factors for accurate prediction, this study contributed to enhancing public health preparedness and response strategies for combating Lassa fever.