Spatial modelling of vector-borne diseases: Where? When? How many?

Avia-GIS R&D team has an extensive expertise in the spatial modeling of vector-borne diseases (VBDs) to address critical concerns regarding the epidemiology and control of VBDs. Our work focuses on dissecting the complex interactions between vectors, hosts, and the environmental conditions that facilitate disease transmission. Through the integration of machine learning techniques, our endeavors to predict not only the presence and activity of disease vectors but also the potential for disease outbreaks and their impact on populations in a one health context.Central to our approach are three questions concerning the vector: (1) Where is the vector present? (2) When will the vector be active? and (3) How many vectors will be active at any given time? These inquiries are crucial for understanding the spatial and temporal dynamics of vector populations, which in turn influence the transmission of vector-borne diseases. Answering these questions, aids in identifying areas and times of high transmission risk, thereby enabling more effective vector control strategies and disease prevention measures.Parallel to the vector-focused analysis, similar questions need to be answered from the disease perspective: (1) Where can the disease occur? (2) When will there be an outbreak? and (3) How much of he population will be affected? This aspect of our work is aimed at predicting the geographical spread and timing of disease outbreaks, as well as estimating the potential number of cases. Such predictions are vital for public health planning and response, as they help in allocating resources efficiently and implementing timely interventions to mitigate the impact of outbreaks.The integration of insights from both the vector and disease aspects forms the foundation of an early warning system. Such a system combines data on vector presence and activity with information on environmental and climatic conditions, host population, and historical disease incidence to forecast where and when outbreaks are likely to occur, and how severe they may be. Machine learning techniques play a pivotal role in this process, enabling the analysis of large datasets and the identification of patterns that may not be apparent through traditional epidemiological methods.