Morgan S Tarpenning, Juliet T Bramante, Kavita D Coombe, Katherine E Woo, Andrew J Chamberlin, Paul S Mutuku, Giulio A De Leo, Angelle Desiree LaBeaud, Bryson A Ndenga, Francis M Mutuku, Joelle I Rosser
{"title":"Comparison of unmanned aerial vehicle imaging to ground truth walkthroughs for identifying and classifying trash sites serving as potential Aedes aegypti breeding grounds.","authors":"Morgan S Tarpenning, Juliet T Bramante, Kavita D Coombe, Katherine E Woo, Andrew J Chamberlin, Paul S Mutuku, Giulio A De Leo, Angelle Desiree LaBeaud, Bryson A Ndenga, Francis M Mutuku, Joelle I Rosser","doi":"10.1186/s13071-025-06706-1","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Trash piles and abandoned tires that are exposed to the elements collect water and create productive breeding grounds for Aedes aegypti mosquitoes, the primary vector for multiple arboviruses. Unmanned aerial vehicle (UAV) imaging provides a novel approach to efficiently and accurately mapping trash, which could facilitate improved prediction of Ae. aegypti habitat and consequent arbovirus transmission. This study evaluates the efficacy of trash identification by UAV imaging analysis compared with the standard practice of walking through a community to count and classify trash piles.</p><p><strong>Methods: </strong>We conducted UAV flights and four types of walkthrough trash surveys in the city of Kisumu and town of Ukunda in western and coastal Kenya, respectively. Trash was classified on the basis of a scheme previously developed to identify high and low risk Aedes aegypti breeding sites. We then compared trash detection between the UAV images and walkthrough surveys.</p><p><strong>Results: </strong>Across all walkthrough methods, UAV image analysis captured 1.8-fold to 4.4-fold more trash than the walkthrough method alone. Ground truth validation of UAV-identified trash showed that 94% of the labeled trash sites were correctly identified with regards to both location and trash classification. In addition, 98% of the visible trash mimics documented during walkthroughs were correctly avoided during UAV image analysis. We identified advantages and limitations to using UAV imaging to identify trash piles. While UAV imaging did miss trash underneath vegetation or buildings and did not show the exact composition of trash piles, this method was efficient, enabled detailed quantitative trash data, and granted access to areas that were not easily accessible by walking.</p><p><strong>Conclusions: </strong>UAVs provide a promising method of trash mapping and classification, which can improve research evaluating trash as a risk factor for infectious diseases or aiming to decrease community trash exposure.</p>","PeriodicalId":19793,"journal":{"name":"Parasites & Vectors","volume":"18 1","pages":"93"},"PeriodicalIF":3.0000,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11883972/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Parasites & Vectors","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s13071-025-06706-1","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PARASITOLOGY","Score":null,"Total":0}
Comparison of unmanned aerial vehicle imaging to ground truth walkthroughs for identifying and classifying trash sites serving as potential Aedes aegypti breeding grounds.
Background: Trash piles and abandoned tires that are exposed to the elements collect water and create productive breeding grounds for Aedes aegypti mosquitoes, the primary vector for multiple arboviruses. Unmanned aerial vehicle (UAV) imaging provides a novel approach to efficiently and accurately mapping trash, which could facilitate improved prediction of Ae. aegypti habitat and consequent arbovirus transmission. This study evaluates the efficacy of trash identification by UAV imaging analysis compared with the standard practice of walking through a community to count and classify trash piles.
Methods: We conducted UAV flights and four types of walkthrough trash surveys in the city of Kisumu and town of Ukunda in western and coastal Kenya, respectively. Trash was classified on the basis of a scheme previously developed to identify high and low risk Aedes aegypti breeding sites. We then compared trash detection between the UAV images and walkthrough surveys.
Results: Across all walkthrough methods, UAV image analysis captured 1.8-fold to 4.4-fold more trash than the walkthrough method alone. Ground truth validation of UAV-identified trash showed that 94% of the labeled trash sites were correctly identified with regards to both location and trash classification. In addition, 98% of the visible trash mimics documented during walkthroughs were correctly avoided during UAV image analysis. We identified advantages and limitations to using UAV imaging to identify trash piles. While UAV imaging did miss trash underneath vegetation or buildings and did not show the exact composition of trash piles, this method was efficient, enabled detailed quantitative trash data, and granted access to areas that were not easily accessible by walking.
Conclusions: UAVs provide a promising method of trash mapping and classification, which can improve research evaluating trash as a risk factor for infectious diseases or aiming to decrease community trash exposure.
期刊介绍:
Parasites & Vectors is an open access, peer-reviewed online journal dealing with the biology of parasites, parasitic diseases, intermediate hosts, vectors and vector-borne pathogens. Manuscripts published in this journal will be available to all worldwide, with no barriers to access, immediately following acceptance. However, authors retain the copyright of their material and may use it, or distribute it, as they wish.
Manuscripts on all aspects of the basic and applied biology of parasites, intermediate hosts, vectors and vector-borne pathogens will be considered. In addition to the traditional and well-established areas of science in these fields, we also aim to provide a vehicle for publication of the rapidly developing resources and technology in parasite, intermediate host and vector genomics and their impacts on biological research. We are able to publish large datasets and extensive results, frequently associated with genomic and post-genomic technologies, which are not readily accommodated in traditional journals. Manuscripts addressing broader issues, for example economics, social sciences and global climate change in relation to parasites, vectors and disease control, are also welcomed.