RESUMEN
Disease control programs are needed to identify the breeding sites of mosquitoes, which transmit malaria and other diseases, in order to target interventions and identify environmental risk factors. The increasing availability of very-high-resolution drone data provides new opportunities to find and characterize these vector breeding sites. Within this study, drone images from two malaria-endemic regions in Burkina Faso and Côte d'Ivoire were assembled and labeled using open-source tools. We developed and applied a workflow using region-of-interest-based and deep learning methods to identify land cover types associated with vector breeding sites from very-high-resolution natural color imagery. Analysis methods were assessed using cross-validation and achieved maximum Dice coefficients of 0.68 and 0.75 for vegetated and non-vegetated water bodies, respectively. This classifier consistently identified the presence of other land cover types associated with the breeding sites, obtaining Dice coefficients of 0.88 for tillage and crops, 0.87 for buildings and 0.71 for roads. This study establishes a framework for developing deep learning approaches to identify vector breeding sites and highlights the need to evaluate how results will be used by control programs.
RESUMEN
To provide information for public health policy on mosquito nets in the Amazon region of Colombia, we conducted landing catches to estimate Anopheles species composition and biting activity. Two hundred twenty person-nights of catches were done in seven locations over a period of 14 mo. A total of 1,780 Anopheles mosquitoes were caught (8.1 per person-night). Among the nine species found, An. oswaldoi Peryassú was the most common (776 mosquitoes, 44%), followed by An. darlingi Root s.l. (498, 28%). An. oswaldoi was the most common species collected outdoors, where its biting rate dropped steadily from a peak of >15 bites/person-night at the start of the night (1800-1900 hours) to approximately equal to 2 bites/person-night before dawn. An. darlingi was the most common species collected indoors, with a biting rate of approximately equal to 3-4 bites/person-night until about midnight, when the rate dropped below 1 bite/person-night, before showing a secondary peak before dawn. Sixty-four mosquito nets were analyzed by the technique of high-performance liquid chromatography (HPLC) for levels of deltamethrin (DM). All but two (62) of these were reported by their owners to have been impregnated with insecticide, and 53 were found by HPLC to have deltamethrin. However, one half (32) of the nets had concentrations <4 mg/m2 and therefore were likely to have been inadequately protective. An inverse association was found between the reported time between washes and deltamethrin concentration. These findings show a need for additional protection from mosquitoes when not inside nets, as well as for more effective impregnation, possibly through wash-resistant insecticide formulation.