Geospatial modelling of dry season habitats of the malaria vector, Anopheles funestus, in south-eastern Tanzania

New directions for malaria vector control using geography and geospatial analysis

As we strive towards the ambitious goal of malaria elimination, we must embrace integrated strategies and interventions. Like many diseases, malaria is heterogeneously distributed. This inherent spatial component means that geography and geospatial data is likely to have an important role in malaria control strategies. For instance, focussing interventions in areas where malaria risk is highest is likely to provide more cost-effective malaria control programmes. Equally, many malaria vector control strategies, particularly interventions like larval source management, would benefit from accurate maps of malaria vector habitats - sources of water that are used for malarial mosquito oviposition and larval development. In many landscapes, particularly in rural areas, the formation and persistence of these habitats is controlled by geographical factors, notably those related to hydrology. This is especially true for malaria vector species like Anopheles funestsus that show a preference for more permanent, often naturally occurring water sources like small rivers and spring-fed ponds. Previous work has embraced geographical concepts, techniques, and geospatial data for studying malaria risk and vector habitats. But there is much to be learnt if we are to fully exploit what the broader geographical discipline can offer in terms of operational malaria control, particularly in the face of a changing climate. This chapter outlines potential new directions related to several geographical concepts, data sources and analytical approaches, including terrain analysis, satellite imagery, drone technology and field-based observations. These directions are discussed within the context of designing new protocols and procedures that could be readily deployed within malaria control programmes, particularly those within sub-Saharan Africa, with a particular focus on experiences in the Kilombero Valley and the Zanzibar Archipelago, United Republic of Tanzania.

Using image segmentation models to analyse high-resolution earth observation data: new tools to monitor disease risks in changing environments

BACKGROUND

In the near future, the incidence of mosquito-borne diseases may expand to new sites due to changes in temperature and rainfall patterns caused by climate change. Therefore, there is a need to use recent technological advances to improve vector surveillance methodologies. Unoccupied Aerial Vehicles (UAVs), often called drones, have been used to collect high-resolution imagery to map detailed information on mosquito habitats and direct control measures to specific areas. Supervised classification approaches have been largely used to automatically detect vector habitats. However, manual data labelling for model training limits their use for rapid responses. Open-source foundation models such as the Meta AI Segment Anything Model (SAM) can facilitate the manual digitalization of high-resolution images. This pre-trained model can assist in extracting features of interest in a diverse range of images. Here, we evaluated the performance of SAM through the Samgeo package, a Python-based wrapper for geospatial data, as it has not been applied to analyse remote sensing images for epidemiological studies.

RESULTS

We tested the identification of two land cover classes of interest: water bodies and human settlements, using different UAV acquired imagery across five malaria-endemic areas in Africa, South America, and Southeast Asia. We employed manually placed point prompts and text prompts associated with specific classes of interest to guide the image segmentation and assessed the performance in the different geographic contexts. An average Dice coefficient value of 0.67 was obtained for buildings segmentation and 0.73 for water bodies using point prompts. Regarding the use of text prompts, the highest Dice coefficient value reached 0.72 for buildings and 0.70 for water bodies. Nevertheless, the performance was closely dependent on each object, landscape characteristics and selected words, resulting in varying performance.

CONCLUSIONS

Recent models such as SAM can potentially assist manual digitalization of imagery by vector control programs, quickly identifying key features when surveying an area of interest. However, accurate segmentation still requires user-provided manual prompts and corrections to obtain precise segmentation. Further evaluations are necessary, especially for applications in rural areas.