The purpose of this research is to design, deploy and validate artificial intelligence (AI) algorithms operating on drone videos to enable a real time methodology for optimizing predictive mapping unknown, geographic locations (henceforth, geolocation) of potential, seasonal, Anopheles (gambiae, and funestus) larval habitats in an agro-village, epi-entomological, intervention site (Akonyibedo village) in Gulu District, Northern Uganda. Formulae are developed for classifying the drone swath, capture point, land cover in Akonyibedo agro-village. An AI algorithm is designed for constructing a smartphone application (app) in order to enable automatic detection of potential larval habitats from drone videos. The aim of this work is to enable scaling up to larger intervention sites (e.g., district level, sub-county) and then throughout entire Uganda. We demonstrate how capture point, stratifiable, drone swath coverage in Akonyibedo village can be accomplished employing temporal series of re-centered, real time, imaged, Anopheline, larval habitat, seasonal, map projections. We also define a remote methodology for detecting unknown, georeferenceable, capture point geolocations of potential, seasonal, breeding sites employing multispectral, wavelength, signature, reflux emissivities in a drone spectral library. Our results show that high-resolution drone imagery when processed employing state of the art AI algorithms can discriminate a profile of water bodies where Anopheles mosquitoes are most likely to breed (overall ground truth accuracy of 100%). Live, high definition, Anopheline larval habitat signature maps can be generated in real-time drone AI app on a smartphone or Apple device while the image is being captured or larvicidal application is taking place.
Key words: Anopheles, larval habitat, drones, artificial intelligence (AI), malaria, Uganda.
Copyright © 2022 Author(s) retain the copyright of this article.
This article is published under the terms of the Creative Commons Attribution License 4.0