Location Intelligence Powered by Machine Learning Automation for Mapping Malaria Mosquito Habitats Employing an Unmanned Aerial Vehicle (UAV) for Implementing “Seek and Destroy” for Commercial Roadside Ditch Foci and Real Time Larviciding Rock Pit Quarry Habitats in Peri-Domestic Agro-Pastureland Ecosystems in Northern Uganda

Abstract

Public health emergencies stemming from infectious disease outbreaks is creating a serious threat to global health security. For example, climate change and extreme weather events threaten to alter and affect geographic areas pertaining to disease vulnerability, such as greater risks of mosquito-borne diseases (dengue, malaria, yellow fever and Zika). The emergence of these disease outbreaks and their influence globally has sparked a renewed attention on global health security and the application of location intelligence. Persistent outbreaks characterize a ‘new normal’ that points to major deficiencies in preparedness, response and recovery initiatives. Malaria mosquito An. gambiae s.l., arabiensis s.s. and funestus s.s represent the main malaria mosquito vectors in sub-Saharan Africa. As reported in WHO (Jacob et al. in Open Remote Sensing 17:11–24, [1]), Malaria is a life-threatening disease caused by parasites that are transmitted to people through the bites of infected female Anopheles mosquitoes. It is preventable and curable. In 2019, there were an estimated 229 million cases of malaria worldwide. The estimated number of malaria deaths stood at 409,000 in 2019. Children aged under 5 years are the most vulnerable group affected by malaria; in 2019, they accounted for 67% (274,000) of all malaria deaths worldwide. The WHO African Region carries a disproportionately high share of the global malaria burden. In 2019, the region was home to 94% of malaria cases and deaths. Sensemaking lies at the heart of location intelligence. Location intelligence is defined as the collection and analysis of geospatial data that are transformed into strategic insights to support operations. Weick (Krizhevsky et al. in Advances in Neural Information Processing Systems, pp 1097–1105, [2]) refers to sensemaking in terms of ‘…how we structure the unknown so as to be able to act in it. Sensemaking involves coming up with a plausible understanding—a map—of a shifting world; testing this map with others through data collection, action, and conversation; and then refining, or abandoning, the map depending on how credible it is’ (Lin et al. in Proceedings of the IEEE International Conference on Computer Vision 2017, pp. 2980–2988, [3]). The application of machine learning algorithms are emerging as key public health intelligence approaches to support tactical, operational and strategic sensemaking. Recent advances that identify the reflective signatures of active mosquito breeding sites, and their temporal evolution, have made predictive algorithms possible to search and identify previously unidentified larval habitats from a Unmanned Aerial Vehicle (UAV), and monitor their activity in real time. Spectral signature is the variation of reflectance of a material (i.e., emittance as a function of wavelength) (www.esri.com). These real time aerial surveys can provide spatiotemporal data for targeting interventions to eliminate vectors before they become adult airborne biting mosquitoes, to reduce malaria transmission. Reference capture point habitats for Anopheles gambiae s.l., An. arabiensis s.s. and An. funestus s.s, the main malaria mosquito vectors in sub- Saharan Africa [www.who.int], may also be separately identified with this methodology. This chapter points to the application of predictive algorithms coupled with drone surveillance to support sensemaking in support of spatiotemporal data for targeting interventions to eliminate vectors before they become adult airborne biting mosquitoes, to reduce malaria transmission. The sensemaking applies not only to the targeted interventions to eliminate vectors, but also strategic sensemaking that contextualizes this intervention as part of a more holistic/systemic and strategic intervention encompassing a myriad of coordinated interventions across the disaster management spectrum (mitigation, preparedness, response, recovery).