{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T06:24:26Z","timestamp":1787293466694,"version":"build-2736575974"},"reference-count":39,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T00:00:00Z","timestamp":1787270400000},"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                    Potato is one of the world\u2019s most important staple crops, yet its productivity is persistently compromised by foliar diseases particularly early blight (\n                    <jats:italic>Alternaria solani<\/jats:italic>\n                    ) and late blight (\n                    <jats:italic>Phytophthora infestans<\/jats:italic>\n                    ) which together account for substantial annual yield losses. Conventional visual diagnosis by agronomists is laborintensive, subjective, and ill-suited to large-scale deployment, while prevailing deep learning solutions tend to degrade under real-world variability in illumination, background, and leaf orientation, and typically require large, annotated datasets that are rarely available in field conditions. To address these limitations, we propose a hybrid deep learning framework that couples ConvMixer, for localized lesionscale feature extraction, with a Vision Transformer (ViT), for modeling long-range spatial dependencies, and aggregates their representations through an elementwise ensemble. The pipeline is preceded by EnviroSpect, a novel preprocessing scheme that independently remaps hue, enhances saturation, and normalizes intensity in a custom hue\u2013saturation\u2013intensity (HSI)-based color space to preserve disease-discriminative cues under heterogeneous imaging conditions. Classification is performed by a prototypical-network-based head, which leverages class prototypes computed from training features to produce similarity-based decisions that complement standard softmax classification. The framework was trained and evaluated on three datasets: PlantVillage, Potato Plants, and a custom field-acquired AgriPlant set, together comprising 5,304 images across three disease classes. The proposed model attains classification accuracies of 99% on PlantVillage and 98% on Potato Plants, with a macro F1-score of 99.02%, precision of 99.20%, and recall of 98.85%, consistently outperforming individual ConvMixer, ViT, ResNet18, MobileNetV2, and InceptionV3 baselines. Ablation and statistical significance analyses (\n                    <jats:italic>p&amp;lt;<\/jats:italic>\n                    0.05) confirm that each component \u2014 the hybrid backbone, EnviroSpect preprocessing, and the prototypical network head contribute meaningfully to overall performance, with EnviroSpect providing the largest single improvement. Importantly, the model achieves these results with only 8.9 M parameters and 19 ms per-image graphics processing unit (GPU) inference, striking a favorable accuracy\u2013 efficiency balance for deployment on resource-constrained edge devices. The proposed framework achieves a strong accuracy\u2013efficiency balance for potato leaf disease detection and offers a transferable foundation that could be extended toward scalable, environment-robust plant-disease monitoring in other crops and agricultural scenarios.\n                  <\/jats:p>","DOI":"10.3389\/fpls.2026.1886452","type":"journal-article","created":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T05:37:44Z","timestamp":1787290664000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["EnviroSpect-guided ConvMixer\u2013ViT framework for environment-robust potato leaf disease detection"],"prefix":"10.3389","volume":"17","author":[{"given":"Abida","family":"Sharif","sequence":"first","affiliation":[{"name":"Shien-Ming Wu School of Intelligent Engineering, South China University of Technology","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mudassir","family":"Khalil","sequence":"additional","affiliation":[{"name":"Computer Engineering Department, Bahauddin Zakariya University","place":["Multan, Pakistan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad Zaheer","family":"Sajid","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, George Mason University","place":["Fairfax, VA, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reem","family":"Alshenaifi","sequence":"additional","affiliation":[{"name":"Department of Information Technology, College of Computer and Information Sciences, Majmaah University","place":["Al Majmaah, Saudi Arabia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jarrar","family":"Amjad","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Kansas State University","place":["Manhattan, KS, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,21]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"695","DOI":"10.1007\/s11540-024-09760-x","article-title":"Early detection of potato disease using an enhanced convolutional neural network-long short-term memory deep learning model","volume":"68","author":"Alzakari","year":"2024","journal-title":"Potato Res"},{"key":"B2","first-page":"428","article-title":"CNN based disease detection approach on potato leaves","author":"Asif","year":"2020"},{"key":"B3","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/s11540-025-09981-8","article-title":"Lightweight and interpretable hybrid deep network for potato leaf disease detection using CBAM and vision transformer","volume":"69","author":"Bajpai","year":"2026","journal-title":"Potato Res."},{"key":"B4","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/s12530025-09781-y","article-title":"Mathematical modeling and optimization of vision transformers for disease classification in agronomic imaging","volume":"17","author":"Benbakreti","year":"2026","journal-title":"Evolving Syst."},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.108307","article-title":"Potato leaf disease detection with a novel deep learning model based on depthwise separable convolution and transformer networks","volume":"133","author":"Catal Reis","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"B6","doi-asserted-by":"publisher","first-page":"20797","DOI":"10.1007\/s11042-022-12620-w","article-title":"Mobile convolution neural network for the recognition of potato leaf disease images","volume":"81","author":"Chen","year":"2022","journal-title":"Multimed. Tools Appl."},{"key":"B7","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.4108\/eetsis.3937","article-title":"Potato leaf disease recognition and prediction using convolutional neural networks","volume":"10","author":"Ghosh","year":"2023","journal-title":"EAI Endorsed Scal. Inf. Syst."},{"key":"B9","doi-asserted-by":"crossref","first-page":"520","DOI":"10.1590\/S0102-05362013000400002","article-title":"Methodology for evaluation of disease severity in potato tubers","volume":"31","author":"Granja","year":"2013","journal-title":"Hortic. Bras."},{"key":"B10","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1201\/9781003393580-24","article-title":"Potato plant leaf diseases detection and identification using convolutional neural networks","volume":"1","author":"Gurusamy","year":"2023","journal-title":"Artificial Intelligence, Blockchain, Computing and Security"},{"key":"B11","doi-asserted-by":"crossref","DOI":"10.1007\/978-981-33-6424-0_8","article-title":"A deep learning-based approach for potato disease classification","volume-title":"Computer Vision and Machine Learning in Agriculture. Algorithms for Intelligent Systems","author":"Hasan","year":"2021"},{"key":"B12","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1704.04861","article-title":"Mobilenets: efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.3390\/app14178038","article-title":"Attention-based light weight deep learning models for early potato disease detection","volume":"14","author":"Kasana","year":"2024","journal-title":"Appl. Sci."},{"key":"B15","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-59338-4_4","article-title":"Artificial intelligence in potato leaf disease classification: a deep learning approach","volume-title":"Machine Learning and Big Data Analytics Paradigms: Analysis, Applications and Challenges","author":"Khalifa","year":"2021"},{"key":"B16","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1007\/s12230-015-9445-9","article-title":"Introduction to 2013 symposium on bacterial diseases of potatoes","volume":"92","author":"Kirk","year":"2015","journal-title":"Am. J. Potato Res."},{"key":"B17","doi-asserted-by":"publisher","first-page":"38209","DOI":"10.1007\/s11042-023-16882-w","article-title":"Artificial driving based EfficientNet for automatic plant leaf disease classification","volume":"83","author":"Kotwal","year":"2024","journal-title":"Multimed. Tools Appl."},{"key":"B18","doi-asserted-by":"publisher","first-page":"31101","DOI":"10.1007\/s11042-023-14663-z","article-title":"Classification and identification of disease in potato leaf using hierarchical based deep learning convolutional neural network","volume":"82","author":"Kumar","year":"2023","journal-title":"Multimed. Tools Appl."},{"key":"B19","doi-asserted-by":"publisher","first-page":"50401","DOI":"10.1007\/s11042-023-17610-0","article-title":"Modified transfer learning frameworks to identify potato leaf diseases","volume":"83","author":"Lanjewar","year":"2024","journal-title":"Multimed. Tools Appl."},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2022.899754","article-title":"The detection method of potato foliage diseases in complex background based on instance segmentation and semantic segmentation","volume":"13","author":"Li","year":"2022","journal-title":"Front. Plant Sci."},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1155\/acis\/7614841","article-title":"Early detection and classification of potato leaf disease using convolutional neural networks","volume":"2025","author":"Mulugeta","year":"2025","journal-title":"Appl. Comput. Intell. Soft Comput."},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.3390\/agriculture13040841","article-title":"EfficientPNet\u2014an optimized and efficient deep learning approach for classifying disease of potato plant leaves","volume":"13","author":"Nazir","year":"2023","journal-title":"Agriculture"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2023.1222596","article-title":"Identification of QTL associated with plant vine characteristics and infection response to late blight, early blight, and Verticillium wilt in a tetraploid potato population derived from late blight-resistant Palisade Russet","volume":"14","author":"Park","year":"2023","journal-title":"Front. Plant Sci."},{"key":"B24","doi-asserted-by":"publisher","first-page":"358","DOI":"10.3864\/j.issn.0578-1752.at-2004-2094","article-title":"Development of China\u2019s potato industry and food safety","volume":"38","author":"Qu","year":"2005","journal-title":"Sci. Agric. Sin."},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1007\/s11540-024-09763-8","article-title":"Potato leaf disease classification using optimized machine learning models and feature selection techniques","author":"Radwan","year":"2024","journal-title":"Potato Res"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10172064","article-title":"Multi-level deep learning model for potato leaf disease recognition","volume":"10","author":"Rashid","year":"2021","journal-title":"Electronics"},{"key":"B27","first-page":"72","article-title":"Identification of disease in potato leaves using convolutional neural network (CNN) algorithm","author":"Rozaqi","year":"2020"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.3390\/agronomy14102230","article-title":"Comparison of deep learning models for multi-crop leaf disease detection with enhanced vegetative feature isolation and definition of a new hybrid architecture","volume":"14","author":"Saleem","year":"2024","journal-title":"Agronomy"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1499909","article-title":"Optimized classification of potato leaf disease using EfficientNet-LITE and KE-SVM in diverse environments","volume":"16","author":"Sangar","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B30","first-page":"554","article-title":"Classification of diseased potato leaves using machine learning","author":"Sharma","year":"2021"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1409.1556","article-title":"Very deep convolutional networks for largescale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv"},{"key":"B32","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1186\/s12870-025-06679-4","article-title":"Potato plant disease detection: leveraging hybrid deep learning models","volume":"25","author":"Sinamenye","year":"2025","journal-title":"BMC Plant Biol."},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1088\/1757-899x\/1022\/1\/012121","article-title":"Potato plant leaves disease detection and classification using machine learning methodologies","volume":"1022","author":"Singh","year":"2021","journal-title":"IOP Conf. Ser. Mater. Sci. Eng."},{"key":"B34","first-page":"4077","article-title":"Prototypical networks for few-shot learning","author":"Snell","year":"2017"},{"key":"B35","first-page":"82","article-title":"Potato leaf disease classification based on distinct color and texture feature extraction","author":"Suttapakti","year":"2019"},{"key":"B36","first-page":"461","article-title":"Potato leaf diseases detection using deep learning","author":"Tiwari","year":"2020"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2201.09792","article-title":"Patches are all you need","author":"Trockman","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"B38","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1007\/s11540-022-09588-3","article-title":"Potato processing industry in China: current scenario, future trends and global impact","volume":"66","author":"Wang","year":"2023","journal-title":"Potato Res."},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.3390\/agronomy12040906","article-title":"Maize small leaf spot classification based on improved deep convolutional neural networks with a multi-scale attention mechanism","volume":"12","author":"Yin","year":"2022","journal-title":"Agronomy"}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1886452\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T05:37:48Z","timestamp":1787290668000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1886452\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,21]]},"references-count":39,"alternative-id":["10.3389\/fpls.2026.1886452"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2026.1886452","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,21]]},"article-number":"1886452"}}