Biting midges of the genus Culicoides are vectors of Bluetongue (BTV) and Epizootic Hemorrhagic Disease virus (EHD), both of which pose serious threats to livestock, particularly cattle and sheep, causing significant economic losses to the farming industry. An increase in BTV and EHD outbreaks across Europe coincides with the changing climate landscape, urging us to improve our limited knowledge of Culicoides biology.

Using machine learning (ML) approaches, we identify the environmental determinants in Culicoides population dynamics by leveraging entomological survey data collected during a large-scale surveillance campaign in France, and make predictions under different climate change scenarios.

With this, we demonstrate how ML approaches, in the context of vector-borne diseases, can be a powerful tool for identifying areas exposed to increased future risk of Culicoides-borne disease outbreaks.