Fig. 3From: Data-driven and interpretable machine-learning modeling to explore the fine-scale environmental determinants of malaria vectors biting rates in rural Burkina FasoMultilevel Spearman’s correlation between the vectors’ biting rates and the landscape variables. Biting rates were separated into presence/absence of bites (left) and abundance of bites (i.e. positive counts only) (right). Unit of biting rates: number of landings on human/person/night. Unit of landscape variables: % of landscape occupied by each land cover class. Landscape variables were extracted in four spatial buffer zones around the sampling locations (250 m radius, 500 m, 1 km, 2 km) for each main vector species. Only correlations with coefficient > 0.1 and p-values < 0.2 are displayed. Stars indicate the range of the p-value: *** p-value ∈ [0, 0.001]; ** p-value ∈ [0.001, 0.01]; * p-value ∈ [0.01, 0.05]; absence of stars: p-value ∈ [0.05, 0.2]Back to article page