[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126326-en":3,"doc-seo-126326-105":31,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},126326,962085570644,"Evangeline","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Evaluating machine learning-based elephant recognition in complex African landscapes using drone imagery","This paper evaluates a machine learning-based approach for identifying and analyzing African bush elephants within complex terrains using high-resolution drone imagery. Human-wildlife conflict creates a significant threat to elephants worldwide, making accurate and efficient monitoring crucial yet difficult across diverse landscapes. The study uses about 3,180 drone-captured images from Kasungu National Park in Malawi, covering dense forests and open bushlands. Three ML models—Faster R-CNN, RetinaNet, and Mask R-CNN—are fine-tuned and compared, revealing task-specific strengths and recognition challenges in real ecological conditions, with implications for conservation decision-making.","PAPER • OPEN ACCESS  \nEvaluating machine learning-based elephant recognition in complex African landscapes using drone imagery  \nTo cite this article: Chris McCarthy et al 2024 Environ. Res. Commun. 6 115035  \nView the article online for updates and enhancements.  \nYou may also like  \n-Advancing life cycle assessment of bioenergy crops with global land use models  \nAnders Arvesen, Florian Humpenöder, Tomás Navarrete Gutierrez et al.  \n-Financing structural and non-structural extreme heat adaptation measures in Southeast Asian cities: statuses and prospects  \nRainbow Yi Hung Lam and Laurence LDelina  \n-Framing industrial decarbonization technologies in the public sphere:  \nnarratives from the digital ‘town square’ in the United Kingdom  \nKyle S Herman, Chien-Fei Chen and Benjamin K Sovacool  \nThis content was downloaded from IP address [90.251.232.248](90.251.232.248) on 03/06/2025 at 10:14  \n Environ. Res. Commun.6(2024)115035 [https:](https://doi.org/10.1088/2515-7620/ad9380)[//](https://doi.org/10.1088/2515-7620/ad9380)[doi.org](https://doi.org/10.1088/2515-7620/ad9380)[/](https://doi.org/10.1088/2515-7620/ad9380)[10.1088](https://doi.org/10.1088/2515-7620/ad9380)[/](https://doi.org/10.1088/2515-7620/ad9380)[2515-7620](https://doi.org/10.1088/2515-7620/ad9380)[/](https://doi.org/10.1088/2515-7620/ad9380)[ad9380](https://doi.org/10.1088/2515-7620/ad9380)  \nPAPER  \nEvaluating machine learning-based elephant recognition in complex OPENACCESS African landscapes using drone imagery  \nRECEIVED  \n20July2024 Chris McCarthy1,2,∗ , Lumbani Benedicto Banda3,4, Daud Jones Kachamba2, Zuza Emmanuel Junior5 ,  \nRE27VISEDptember2024 Cornelius Chisambi6, NdaonaKumanga3, Luciano Lawrence3 and Troy Sternberg7,8  \n1 Zanvyl Krieger School ofArts&Sciences, Johns Hopkins University, Baltimore, MA,21218, United States ofAmerica  \nC5CEPTED FORNovembeU2BLICA024TION 2 Lilongwe University of Agriculture and Natural Resources (LUANAR), Bunda College of Agriculture Campus, Department of Forestry, PO Box219, Lilongwe, Malawi  \nPU28BLISHEDNovember2024 3 Lilongwe University of Agriculture and Natural Resources (LUANAR), Bunda College of Agriculture Campus, Department of  \nEnvironment and Natural Resources, PO Box219, Lilongwe, Malawi  \n  4 Africa Centre of Excellence for Climate Smart Agriculture and Biodiversity Conservation, Haramaya University, PO Box 138, Dire Dawa, Original content from this Ethiopia  \nworkmaythetermsbofetusedheCrundereative 5 School ofAgricultural Science and Practice, Royal Agricultural University, GL76JS, Cirencester, Gloucestershire, United Kingdom CommonsAttribution4 .0 6 Graduate School ofGlobal Environmental Studies, Kyoto University, Kyoto,606-8501, Japan  \nlicence. 7 CEI Centre for International Studies ISCTE—University Institute Lisbon, Avenida das Forças Armadas,1649, Lisbon, Portugal  \nAnyfurther distribution of 8 School ofGeography, University ofOxford, Oxford OX13QY, United Kingdom thisworkmust maintain ∗ Author to whomany correspondence should be addressed.  \nattribution to the  \nauthor(s)andthetitle of [E-mail:](E-mail: cmccar27@jh.edu)[ cmccar27@jh.edu](E-mail: cmccar27@jh.edu), [lumbabanda@gmail.com](lumbabanda@gmail.com), [dkachamba@gmail.com](dkachamba@gmail.com), [Emmanuel.Zuza@rau.ac.uk](Emmanuel.Zuza@rau.ac.uk), thework,journal citation [corneliuschisambi79@gmail.com](corneliuschisambi79@gmail.com), [nkumanga@gmail.com](nkumanga@gmail.com), [lawrenceluciano40@gmail.com](lawrenceluciano40@gmail.com), tsgyr@iscte-iul.pt and [and DOI.](and DOI. Troy.sternberg@geog.ox.ac.uk)[ Troy.sternberg@geog.ox.ac.uk](and DOI. Troy.sternberg@geog.ox.ac.uk)  \n Keywords: African elephants, artificial intelligence, AWS, drone imagery, machine learning, Malawi, wildlife identification  \nAbstract  \nThis paper evaluatesa machine learning-based approach for identifying and analyzing African bush elephants within complex terrains using high-resolution drone imagery. With human-wildlife conflict posing asignificant threat to elephants worldwi","cbCaioUnuhmW8V4q","https://ap.wps.com/l/cbCaioUnuhmW8V4q","pdf",2265848,2,1,12,"English","en",105,"# Introduction\n## Materials and Methods\n## Experimental Setup and ML Algorithms\n## Results and Performance Comparison\n## Discussion and Conservation Implications","[{\"question\":\"What is the main objective of the study?\",\"answer\":\"The study aims to evaluate machine learning approaches for recognizing and analyzing African bush elephants using high-resolution drone imagery in complex landscapes.\"},{\"question\":\"Which datasets and terrains are used for training and evaluation?\",\"answer\":\"The work uses approximately 3,180 drone-captured images from Kasungu National Park in Malawi, including dense forests and open bushlands.\"},{\"question\":\"How do the three ML algorithms compare for different elephant groups?\",\"answer\":\"Faster R-CNN performs strongly for adult elephants, Mask R-CNN shows better effectiveness for juveniles and infants, and RetinaNet is more adept with larger images and adult elephants but performs less well for younger ones.\"}]","Evaluating machine learning-based elephant recognition in complex African landscapes using drone imagery | PDF",1785904469,30,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"evaluating-machine-learning-based-elephant-recognition-in-complex-african-landscapes-using-drone-imagery","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/evaluating-machine-learning-based-elephant-recognition-in-complex-african-landscapes-using-drone-imagery/126326/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-21","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What is the main objective of the study?","Question",{"text":76,"@type":77},"The study aims to evaluate machine learning approaches for recognizing and analyzing African bush elephants using high-resolution drone imagery in complex landscapes.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Which datasets and terrains are used for training and evaluation?",{"text":81,"@type":77},"The work uses approximately 3,180 drone-captured images from Kasungu National Park in Malawi, including dense forests and open bushlands.",{"name":83,"@type":74,"acceptedAnswer":84},"How do the three ML algorithms compare for different elephant groups?",{"text":85,"@type":77},"Faster R-CNN performs strongly for adult elephants, Mask R-CNN shows better effectiveness for juveniles and infants, and RetinaNet is more adept with larger images and adult elephants but performs less well for younger ones.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":30,"slug":122},"research-report",{"id":124,"doc_module":4,"doc_module_name":47,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":47,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":47,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":47,"category_name":137,"show_sort_weight":107,"slug":138},19,"General","general"]