{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T06:25:16Z","timestamp":1787034316303,"version":"build-2736575974"},"reference-count":62,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:00:00Z","timestamp":1787011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Plant Sci."],"abstract":"<jats:p>\n                    Deep learning is an emerging, powerful technology that facilitates object detection in plant science, enabling applications such as disease diagnostics and identification of plant species and crop varieties using image analysis. In this study, we demonstrated the success of deep learning algorithms when used in identifying Tanzania-released cassava varieties (\n                    <jats:italic>TARICASS4<\/jats:italic>\n                    ,\n                    <jats:italic>Kiroba<\/jats:italic>\n                    , and\n                    <jats:italic>Mkuranga1<\/jats:italic>\n                    ) through image analysis. Three deep learning algorithms (YOLO v8, SSD-MobileNet v2, and Faster R-CNN with ResNet-50) were trained using a dataset of 19,800 images from leaves, petioles and stems of cassava plants of the three varieties. Trained algorithms achieved promising performance in identifying the cassava varieties using each of the three plant parts (mAP50\u226585.7%), with the highest values recorded for leaves (mAP50\u226592.7%). Of the three models, the YOLO v8 model showed the consistent promising performance for the three plant parts, with an mAP50 of 97.3% for leaves. Further findings from confusion matrices confirmed the superior performance of YOLO v8 for leaves, with performance of \u226598% for each of the three varieties. YOLO v8 also achieved high levels of performance for stems and petioles for all varieties. Our results confirm that deep learning models can be effectively applied for AI-based identification of field-grown cassava. The approach developed for cassava has strong potential for scaling to additional cassava varieties as well as other Vegetatively Propagated Crops, and for use by seed producers and regulators who could benefit from the use of a field-usable tool for verifying variety \u2018true-to-typeness\u2019.\n                  <\/jats:p>","DOI":"10.3389\/fpls.2026.1888478","type":"journal-article","created":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T05:37:04Z","timestamp":1787031424000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning algorithms enable accurate identification of cassava varieties (Manihot esculenta Crantz) using image analysis"],"prefix":"10.3389","volume":"17","author":[{"given":"Moses","family":"Malibiche","sequence":"first","affiliation":[{"name":"International Institute of Tropical Agriculture (IITA)","place":["Dar es Salaam, Tanzania"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonas","family":"Nickas","sequence":"additional","affiliation":[{"name":"International Institute of Tropical Agriculture (IITA)","place":["Dar es Salaam, Tanzania"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hemed","family":"Msofe","sequence":"additional","affiliation":[{"name":"Tanzania Official Seed Certification Institute (TOSCI)","place":["Morogoro, Tanzania"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James P.","family":"Legg","sequence":"additional","affiliation":[{"name":"International Institute of Tropical Agriculture (IITA)","place":["Dar es Salaam, Tanzania"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,18]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"2689","DOI":"10.3390\/electronics10212689","article-title":"Artificial neural networks based optimization techniques: a review","volume":"10","author":"Abdolrasol","year":"2021","journal-title":"Electronics"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.3389\/fagro.2024.1433204","article-title":"Perception and adoption by cassava farmers of the PlantVillage Nuru application disseminated in the agricultural environment of C\u00f4te d\u2019Ivoire: a case study in the departments of Dabou, Bouak\u00e9, and Man","volume":"6","author":"Adj\u00e9i","year":"2024","journal-title":"Front. Agron."},{"key":"B3","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1016\/j.eswa.2017.05.039","article-title":"Deep learning for biological image classification","volume":"85","author":"Affonso","year":"2017","journal-title":"Expert Syst. Appl."},{"key":"B4","doi-asserted-by":"publisher","first-page":"13","DOI":"10.9790\/2380-07151320","article-title":"Selection of descriptors in a morphological characteristics considered in cassava accessions by means of multivariate techniques","volume":"7","author":"Afonso","year":"2014","journal-title":"J. Agric. Veterinary Sci."},{"key":"B5","doi-asserted-by":"publisher","first-page":"2001","DOI":"10.3390\/agriculture14112001","article-title":"Factors influencing adoption of the PlantVillage Nuru application for cassava mosaic disease diagnosis among farmers in Benin","volume":"14","author":"Ahoya","year":"2024","journal-title":"Agriculture"},{"key":"B6","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1186\/s12870-025-07919-3","article-title":"Deep learning-based seed variety classification: a case study in maize","volume":"26","author":"Akbarpour","year":"2026","journal-title":"BMC Plant Biol."},{"key":"B7","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1007\/s10681-022-02992-3","article-title":"Deep learning: as the new frontier in high-throughput plant phenotyping","volume":"218","author":"Arya","year":"2022","journal-title":"Euphytica"},{"key":"B8","doi-asserted-by":"publisher","first-page":"13900","DOI":"10.5897\/ajb11.929","article-title":"Morphological and molecular based diversity studies of some cassava (Manihot esculenta Crantz) germplasm in Ghana","volume":"10","author":"Asare","year":"2011","journal-title":"Afr. J. Biotechnol."},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/j.atech.2022.100097","article-title":"Rapid classification of tef [Eragrostis tef (Zucc.) Trotter] grain varieties using digital images in combination with multivariate technique","volume":"3","author":"Asefa","year":"2023","journal-title":"Smart Agric. Technol."},{"key":"B10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-026-35252-8","article-title":"Machine learning approach for wheat variety identification using single-seed imaging","volume":"16","author":"Bagherpour","year":"2026","journal-title":"Sci. Rep."},{"key":"B11","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.biosystemseng.2018.05.013","article-title":"Factors influencing the use of deep learning for plant disease recognition","volume":"172","author":"Barbedo","year":"2018","journal-title":"Biosyst. Eng."},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780198737407.003.0006","article-title":"Cassava processing in southeast asia","author":"Booth","year":"1978","journal-title":"Cassava Harvesting and Processing"},{"key":"B13","first-page":"195","article-title":"New developments in the international union for the protection of new varieties of plants (UPOV)","author":"Button","year":"2006"},{"key":"B14","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1007\/s11103-004-5010-5","article-title":"Cassava breeding: opportunities and challenges","volume":"56","author":"Ceballos","year":"2004","journal-title":"Plant Mol. Biol."},{"key":"B15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-024-79211-7","article-title":"Lightweight enhanced YOLOv8n underwater object detection network for low light environments","volume":"14","author":"Ding","year":"2024","journal-title":"Sci. Rep."},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/j.carbpol.2025.123314","article-title":"Coordinated transcriptional regulation of carbohydrate-related pathways contributes to the difference of starch accumulation between starchy cassava and sugary cassava","volume":"354","author":"Ding","year":"2025","journal-title":"Carbohydr. Polym."},{"key":"B17","unstructured":"Development of a cassava seed certification system in Tanzania: Evaluation of CGIAR contributions to a policy outcome trajectory\n          \n          \n            \n              Douthwaite\n              B.\n            \n          \n          \n          2020"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2020.563386","article-title":"Image-based high-throughput detection and phenotype evaluation method for multiple lettuce varieties","volume":"11","author":"Du","year":"2020","journal-title":"Front. Plant Sci."},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1016\/j.eja.2025.127926","article-title":"TrSC2Y: a transfer-learning-based model from UAV hyper-spectra imagery for field-scale canola yield prediction by integrating DSSAT with PROSAIL","volume":"174","author":"Du","year":"2026","journal-title":"Eur. J. Agron."},{"key":"B20","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1016\/j.procs.2022.11.206","article-title":"Classification performance evaluation from multilevel logistic and support vector machine algorithms through simulated data in Python","volume":"214","author":"F\u00e1vero","year":"2022","journal-title":"Proc. Comput. Sci."},{"key":"B21","doi-asserted-by":"publisher","first-page":"15596","DOI":"10.1038\/s41598-024-66281-w","article-title":"Advancing common bean (Phaseolus vulgaris L.) disease detection with YOLO driven deep learning to enhance agricultural AI","volume":"14","author":"Gomez","year":"2024","journal-title":"Sci. Rep."},{"key":"B22","doi-asserted-by":"publisher","first-page":"344","DOI":"10.15625\/0866-7160\/v38n3.8570","article-title":"Morphological characterization and classification of cassava (Manihot esculenta Crantz) in Vietnam","volume":"3","author":"Ha","year":"2016","journal-title":"Academia J. Biol."},{"key":"B23","first-page":"1315602","article-title":"The survey of one-stage anchor-free real-time object detection algorithms","author":"He","year":"2024"},{"key":"B24","doi-asserted-by":"publisher","first-page":"101","DOI":"10.21608\/ajar.2020.149437","article-title":"Identification of squash landraces using UPOV descriptors and morphological traits","volume":"45","author":"Helaly","year":"2020","journal-title":"Al-Azhar J. Agric. Res."},{"key":"B25","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1016\/B978-0-08-040826-2.50050-3","article-title":"Cassava: manihot esculenta crantz","volume-title":"Genetic Improvement of Vegetable Crops","author":"Hershey","year":"1993"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1201\/9780429035258-17","article-title":"Cassava in asia:Present situation and its future potential in agro-industry","volume":"189","author":"Howeler","year":"2004"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.3390\/machines11070677","article-title":"YOLO-v1 to YOLO-v8, the rise of YOLO and its complementary nature toward digital manufacturing and industrial defect detection","volume":"11","author":"Hussain","year":"2023","journal-title":"Machines"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1016\/j.measen.2022.100441","article-title":"A comprehensive review on detection of plant disease using machine learning and deep learning approaches","volume":"24","author":"Jackulin","year":"2022","journal-title":"Measurement: Sensors"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1509","DOI":"10.1111\/2041-210X.13473","article-title":"Detecting plant species in the field with deep learning and drone technology","volume":"11","author":"James","year":"2020","journal-title":"Methods Ecol. Evol."},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2021.738685","article-title":"Deep learning algorithms correctly classify Brassica rapa varieties using digital images","volume":"12","author":"Jung","year":"2021","journal-title":"Front. Plant Sci."},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.3390\/agronomy12112722","article-title":"Deep learning-based method for classification of sugarcane varieties","volume":"12","author":"Kai","year":"2022","journal-title":"Agronomy"},{"key":"B32","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1016\/j.aiia.2025.01.013","article-title":"Advancing precision agriculture: a comparative analysis of YOLOv8 for multi-class weed detection in cotton cultivation","volume":"15","author":"Khan","year":"2025","journal-title":"Artif. Intell. Agric."},{"key":"B33","article-title":"Propagation of cassava","volume":"21","author":"Krochmal","year":"1969","journal-title":"World Crops"},{"key":"B34","doi-asserted-by":"publisher","first-page":"17498","DOI":"10.1038\/s41598-025-02527-5","article-title":"Genetic diversity and agro-morphological characterization of cassava varieties provides insight for breeding and crop improvement","volume":"15","author":"Kumar","year":"2025","journal-title":"Sci. Rep."},{"key":"B35","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1016\/j.jssas.2021.02.008","article-title":"Wheat varieties identification based on a deep learning approach","volume":"20","author":"Laabassi","year":"2021","journal-title":"J. Saudi Soc Agric. Sci."},{"key":"B36","article-title":"Neural identification of images showing selected varieties of stored potatoes","volume":"63","author":"Lange","year":"2018","journal-title":"J. Res. Appl. Agric. Eng."},{"key":"B37","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"B38","first-page":"453","article-title":"Commercially sustainable cassava seed systems in Africa","volume-title":"In Root, Tuber and Banana Food System Innovations: Value Creation for Inclusive Outcomes","author":"Legg","year":"2022"},{"key":"B39","first-page":"120","article-title":"Classification of sweet potato variety using convolutional neural network","author":"Mercurio","year":"2019"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2016.01419","article-title":"Using deep learning for image-based plant disease detection","volume":"7","author":"Mohanty","year":"2016","journal-title":"Front. Plant Sci."},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2020.590889","article-title":"Accuracy of a smartphone-based object detection model, PlantVillage Nuru, in identifying the foliar symptoms of the viral diseases of cassava\u2013CMD and CBSD","volume":"11","author":"Mrisho","year":"2020","journal-title":"Front. Plant Sci."},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.3389\/fsufs.2025.1564907","article-title":"Accelerated cassava varietal turnover in Tanzania, a direct result of cassava seed system interventions","volume":"9","author":"Msami","year":"2025","journal-title":"Front. Sustain. Food Syst."},{"key":"B43","doi-asserted-by":"publisher","first-page":"771","DOI":"10.1146\/annurev-arplant-070523-042828","article-title":"Deep learning in image-based plant phenotyping","volume":"75","author":"Murphy","year":"2024","journal-title":"Annu. Rev. Plant Biol."},{"key":"B44","doi-asserted-by":"publisher","first-page":"831","DOI":"10.22214\/ijraset.2022.40755","article-title":"Real time object detection using ssd and mobilenet","volume":"10","author":"Palwankar","year":"2022","journal-title":"Int. J. For. Res. Appl. Sci. Eng. Technol."},{"key":"B45","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1007\/s10462-026-11491-z","article-title":"Deep transfer learning for image classification: a survey","volume":"49","author":"Plested","year":"2026","journal-title":"Artif. Intell. Rev"},{"key":"B46","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1093\/gigascience\/gix083","article-title":"Deep machine learning provides state-of-the-art performance in image-based plant phenotyping","volume":"6","author":"Pound","year":"2017","journal-title":"GigaScience"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2017.01852","article-title":"Deep learning for image-based cassava disease detection","volume":"8","author":"Ramcharan","year":"2017","journal-title":"Front. Plant Sci."},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2019.00272","article-title":"A mobile-based deep learning model for cassava disease diagnosis","volume":"10","author":"Ramcharan","year":"2019","journal-title":"Front. Plant Sci."},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/7812410","article-title":"Fault detection method based on improved Faster R-CNN: take ResNet-50 as an example","volume":"2022","author":"Renjun","year":"2022","journal-title":"Geofluids"},{"key":"B50","first-page":"4","article-title":"Improvement of a propagation technique for cassava using single leaf-bud cuttings: a preliminary report","volume":"8","author":"Roca","year":"1981","journal-title":"Cassava Newslett."},{"key":"B51","doi-asserted-by":"publisher","DOI":"10.1002\/efd2.127","article-title":"Cassava (Manihot esculenta Crantz)\u2014a potential source of phytochemicals, food, and nutrition\u2014an updated review","volume":"5","author":"Scaria","year":"2024","journal-title":"EFood"},{"key":"B52","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1007\/s10722-025-02346-7","article-title":"Characterization of cassava (Manihot esculenta [Cranz]) genotypes sourced from different regions in southwestern Ethiopia using morphological traits","volume":"72","author":"Semman","year":"2025","journal-title":"Genet. Resour. Crop Evol."},{"key":"B53","doi-asserted-by":"publisher","first-page":"1787","DOI":"10.1016\/j.jia.2023.10.019","article-title":"Integrating artificial intelligence and high-throughput phenotyping for crop improvement","volume":"23","author":"Sheikh","year":"2024","journal-title":"J. Integr. Agric."},{"key":"B54","doi-asserted-by":"publisher","DOI":"10.3390\/agriengineering8010017","article-title":"Comparative study of the performance of SqueezeNet and GoogLeNet CNN models in the identification of Kazakhstani potato varieties","volume":"8","author":"Shynybay","year":"2026","journal-title":"AgriEngineering"},{"key":"B55","doi-asserted-by":"publisher","DOI":"10.1155\/2017\/7361042","article-title":"Deep learning for plant identification in natural environment","volume":"2017","author":"Sun","year":"2017","journal-title":"Comput. Intell. Neurosci."},{"key":"B56","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.108458","article-title":"The evolution of object detection methods","volume":"133","author":"Sun","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"B57","doi-asserted-by":"publisher","DOI":"10.1016\/j.tifs.2024.104337","article-title":"The dawn of intelligent technologies in tea industry","volume":"144","author":"Wei","year":"2024","journal-title":"Trends Food Sci. Technol."},{"key":"B58","doi-asserted-by":"publisher","first-page":"15756","DOI":"10.1038\/s41598-021-95240-y","article-title":"A novel method for peanut variety identification and classification by improved VGG16","volume":"11","author":"Yang","year":"2021","journal-title":"Sci. Rep."},{"key":"B59","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/2993\/1\/012059","article-title":"An insulator defect detection model based on improved YOLOv8","volume":"2993","author":"Zhang","year":"2025","journal-title":"J. Physics: Conf. Ser."},{"key":"B60","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2022.806878","article-title":"YOLO-VOLO-LS: a novel method for variety identification of early lettuce seedlings","volume":"13","author":"Zhang","year":"2022","journal-title":"Front. Plant Sci."},{"key":"B61","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2025.111140","article-title":"A hybrid and high-performance model for tea cultivars discrimination using canopy images with convolutional neural network and machine learning algorithm","volume":"240","author":"Zhang","year":"2026","journal-title":"Comput. Electron. Agric."},{"key":"B62","doi-asserted-by":"publisher","DOI":"10.3390\/molecules25010152","article-title":"A rapid and highly efficient method for the identification of soybean seed varieties: hyperspectral images combined with transfer learning","volume":"25","author":"Zhu","year":"2019","journal-title":"Molecules"}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1888478\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T05:37:06Z","timestamp":1787031426000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1888478\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,18]]},"references-count":62,"alternative-id":["10.3389\/fpls.2026.1888478"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2026.1888478","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,18]]},"article-number":"1888478"}}