Additional file 1: of Modelling the spatial distribution of aquatic insects (Order Hemiptera) potentially involved in the transmission of Mycobacterium ulcerans in Africa

Table S1. Median and 95% confidence intervals of validation indicators (TSS, AUC and PCC) for the modelling approaches tested: generalized linear models (GLM), generalized additive models (GAM), boosted regression trees (GBM), artificial neural networks (ANN), multiple adaptive regression splines (MARS), maximum entropy (MAXENT) and random forest (RF). Figure S1. Distribution of communities reporting Buruli ulcer in Ghana (2007–2010) and Cameroon (2003–2015) over a gridded map of predicted distribution of Hemiptera families. Figure S2. Variable contribution of final ensemble models based on GBM and RF algorithms for the Naucoridae, Belostomatidae and Notonectidae. Figure S3. Variable contribution of final ensemble models based on GBM and RF algorithms for the Nepidae, Corixidae and Gerridae. (DOCX 795 kb