Mapping Malaria Vector Habitats in West Africa: Drone Imagery and Deep Learning Analysis for Targeted Vector Surveillance

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...

Full description

Saved in:

Bibliographic Details
Published in:	Remote sensing (Basel, Switzerland) Vol. 15; no. 11; p. 2775
Main Authors:	Trujillano, Fedra, Garay, Gabriel Jimenez, Alatrista-Salas, Hugo, Byrne, Isabel, Nunez-Del-Prado, Miguel, Chan, Kallista, Manrique, Edgar, Johnson, Emilia, Apollinaire, Nombre, Kouame Kouakou, Pierre, Oumbouke, Welbeck A, Tiono, Alfred B, Guelbeogo, Moussa W, Lines, Jo, Carrasco-Escobar, Gabriel, Fornace, Kimberly
Format:	Journal Article
Language:	English
Published:	Switzerland MDPI AG 26-05-2023
Subjects:	Accuracy Agriculture Artificial intelligence Breeding sites Building construction Classification Color imagery Control programs Datasets Deep learning Disease control Distribution Drone aircraft drone images Drones Ecology Environmental aspects Environmental risk epidemiological control Habitats High resolution Identification and classification Identification methods image classification Image processing Image resolution Land cover Machine learning Malaria malaria vector Mosquitoes Remote sensing Risk factors Tillage Tropical diseases Unmanned aerial vehicles Vector-borne diseases Workflow Côte d'Ivoire Burkina Faso West Africa deep learning epidemiological control drone images image classification malaria vector
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	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.
Bibliography:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 Academic Editor: Hua Liu
ISSN:	2072-4292 2072-4292
DOI:	10.3390/rs15112775