{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T16:05:10Z","timestamp":1778774710334,"version":"3.51.4"},"reference-count":29,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T00:00:00Z","timestamp":1773014400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"University of Agricultural Sciences Bangalore","award":["9331\/6330 2022-23"],"award-info":[{"award-number":["9331\/6330 2022-23"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>\n                    Artificial intelligence (AI) enables rapid and precise plant disease detection, offering transformative potential for crop protection. Maize downy mildew (MDM), a destructive disease, causes substantial yield losses, making early detection critical. In this study, we evaluated the performance of thirteen machine-learning (ML) and deep-learning (DL) algorithms for classifying healthy and infected maize leaves using a curated field dataset. Model performance was assessed using multiple metrics, including accuracy, precision, recall, F1-score, and AUC-ROC. Among the tested models, VGG16 achieved the highest performance, with 97% accuracy, 0.98 precision, 0.95 recall, 0.97 F1-score, and an AUC-ROC of 0.99. Training and validation curves indicated minimal overfitting, demonstrating robust generalization. Feature visualization using t-SNE revealed clear separability between healthy and diseased samples, while Grad-CAM analysis confirmed that VGG16 focused on biologically relevant symptomatic regions, such as chlorotic streaks and leaf discoloration. Confusion matrix analysis further validated near-perfect classification, with very few misclassifications. Furthermore, we developed a web-based application (\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/maize-mdm.streamlit.app\/\" xlink:type=\"simple\">https:\/\/maize-mdm.streamlit.app\/<\/jats:ext-link>\n                    ) that not only classifies MDM but also provides farm-level advisory measures. Two-year field trials of DSS-guided fungicide applications effectively suppressed MDM, reducing disease severity (PDI 3.20\u20135.20; PROC 93\u221296%), increasing grain yield (75.6\u201380.2 q\/ha; PIOC 195\u2212289%), and improving economic returns (B:C ratio 3.36\u20133.57) compared to untreated controls. Overall, this study demonstrates that AI-driven models, integrated with web-based decision support, provide accurate, interpretable, and actionable solutions for precision management of maize diseases, contributing to improved yield, profitability, and sustainable agricultural practices.\n                  <\/jats:p>","DOI":"10.1371\/journal.pone.0343517","type":"journal-article","created":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T17:44:12Z","timestamp":1773078252000},"page":"e0343517","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":2,"title":["Artificial intelligence\u2013Driven detection and decision support system for precision management of maize downy mildew"],"prefix":"10.1371","volume":"21","author":[{"given":"Jadesha","family":"G","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anurag","family":"Dhole","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7194-463X","authenticated-orcid":true,"given":"Deepak","family":"D","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2026,3,9]]},"reference":[{"issue":"5","key":"pone.0343517.ref001","doi-asserted-by":"crossref","first-page":"1295","DOI":"10.1007\/s12571-022-01288-7","article-title":"Global maize production, consumption and trade: trends and R&D implications","volume":"14","author":"O Erenstein","year":"2022","journal-title":"Food Sec"},{"key":"pone.0343517.ref002","first-page":"212","article-title":"Prediction of Maize Leaf Disease Detection to improve Crop Yield using Machine Learning based Models.","author":"R Kilaru","year":"2022"},{"issue":"3","key":"pone.0343517.ref003","doi-asserted-by":"crossref","first-page":"544","DOI":"10.1007\/s00122-003-1280-6","article-title":"Identification of QTLs conferring resistance to downy mildews of maize in Asia","volume":"107","author":"MLC George","year":"2003","journal-title":"Theor Appl Genet"},{"key":"pone.0343517.ref004","doi-asserted-by":"crossref","first-page":"43","DOI":"10.3114\/fuse.2022.09.05","article-title":"Peronosporaceae species causing downy mildew diseases of Poaceae, including nomenclature revisions and diagnostic resources","volume":"9","author":"JA Crouch","year":"2022","journal-title":"Fungal Syst Evol"},{"key":"pone.0343517.ref005","doi-asserted-by":"crossref","first-page":"127441","DOI":"10.1016\/j.eja.2024.127441","article-title":"Smart solutions for maize farmers: Machine learning-enabled web applications for downy mildew management and enhanced crop yield in India","volume":"164","author":"G J, Castelino E, Mahadevu P, Kitturmath MS, Lohithaswa HC, Karjagi CG, et al","year":"2025","journal-title":"Eur J Agron"},{"key":"pone.0343517.ref006","doi-asserted-by":"crossref","first-page":"110951","DOI":"10.1016\/j.compag.2025.110951","article-title":"Ai-powered decision-support system for maize Turcicum Leaf Blight: Novel ensemble models for disease forecasting with integrated fungicide advisory","volume":"239","author":"G Jadesha","year":"2025","journal-title":"Comput Electron Agric"},{"issue":"2","key":"pone.0343517.ref007","doi-asserted-by":"crossref","first-page":"2334","DOI":"10.11591\/ijece.v15i2.pp2334-2344","article-title":"Plant disease detection using vision transformers","volume":"15","author":"M Ali","year":"2025","journal-title":"IJECE"},{"issue":"11","key":"pone.0343517.ref008","doi-asserted-by":"crossref","first-page":"1260","DOI":"10.4236\/ajps.2023.1411086","article-title":"Relevance of Advanced Plant Disease Detection Techniques in Disease and Pest Management for Ensuring Food Security and Their Implication: A Review","volume":"14","author":"MA John","year":"2023","journal-title":"AJPS"},{"issue":"5","key":"pone.0343517.ref009","doi-asserted-by":"crossref","first-page":"381","DOI":"10.9734\/jabb\/2024\/v27i5796","article-title":"Transforming Agriculture through Artificial Intelligence: Advancements in Plant Disease Detection, Applications, and Challenges","volume":"27","author":"Sahoo L, Mohapatra D, Raghuvanshi HR, Kumar S, Kaur R, Anshika., et al","year":"2024","journal-title":"JABB"},{"issue":"3","key":"pone.0343517.ref010","doi-asserted-by":"crossref","first-page":"542","DOI":"10.3390\/agriengineering3030035","article-title":"Tomato Leaf Diseases Classification Based on Leaf Images: A Comparison between Classical Machine Learning and Deep Learning Methods","volume":"3","author":"L Tan","year":"2021","journal-title":"AgriEngineering"},{"key":"pone.0343517.ref011","doi-asserted-by":"crossref","first-page":"1538163","DOI":"10.3389\/fpls.2025.1538163","article-title":"Leveraging deep learning for plant disease and pest detection: a comprehensive review and future directions","volume":"16","author":"M Shoaib","year":"2025","journal-title":"Front Plant Sci"},{"issue":"2","key":"pone.0343517.ref012","first-page":"115","article-title":"Disease detection in bean leaves using deep learning","volume":"65","author":"S Sertta\u015f","year":"2023","journal-title":"Commun Fac Sci Univ Ank Ser A2-A3 Phys Sci Eng"},{"issue":"4","key":"pone.0343517.ref013","doi-asserted-by":"crossref","first-page":"698","DOI":"10.3390\/rs17040698","article-title":"Advances in Deep Learning Applications for Plant Disease and Pest Detection: A Review","volume":"17","author":"S Wang","year":"2025","journal-title":"Remote Sens"},{"key":"pone.0343517.ref014","first-page":"100764","article-title":"DeepCrop: Deep learning-based crop disease prediction with web application","volume":"14","author":"MdM Islam","year":"2023","journal-title":"J Agric Food Res"},{"issue":"4","key":"pone.0343517.ref015","first-page":"328","article-title":"Convolutional Neural Networks for Leaf Image-Based Plant Disease Classification","volume":"8","author":"SB Jadhav","year":"2019","journal-title":"IJ-AI"},{"issue":"5","key":"pone.0343517.ref016","doi-asserted-by":"crossref","first-page":"1","DOI":"10.24018\/ejece.2022.6.5.458","article-title":"DenseNet Based Model for Plant Diseases Diagnosis","volume":"6","author":"M Bakr","year":"2022","journal-title":"EJECE"},{"issue":"2","key":"pone.0343517.ref017","doi-asserted-by":"crossref","first-page":"445","DOI":"10.12928\/telkomnika.v22i2.25840","article-title":"Classification of grapevine leaves images using VGG-16 and VGG-19 deep learning nets","volume":"22","author":"M A. Rajab","year":"2024","journal-title":"TELKOMNIKA"},{"issue":"1","key":"pone.0343517.ref018","article-title":"Corn leaf disease diagnosis: enhancing accuracy with resnet152 and grad-cam for explainable AI","volume":"25","author":"Gopalan K, Srinivasan S,. P, Singh M, Mathivanan SK, Moorthy U","year":"2025","journal-title":"BMC Plant Biol"},{"issue":"49","key":"pone.0343517.ref019","doi-asserted-by":"crossref","first-page":"10829","DOI":"10.1021\/acs.jafc.7b03898","article-title":"Discovery of a New Fungicide Candidate through Lead Optimization of Pyrimidinamine Derivatives and Its Activity against Cucumber Downy Mildew","volume":"65","author":"A Guan","year":"2017","journal-title":"J Agric Food Chem"},{"issue":"2","key":"pone.0343517.ref020","doi-asserted-by":"crossref","first-page":"380","DOI":"10.31127\/tuje.1406755","article-title":"Detection of cotton leaf disease with machine learning model","volume":"8","author":"U Hyder","year":"2024","journal-title":"Turkish J Eng"},{"key":"pone.0343517.ref021","doi-asserted-by":"crossref","first-page":"1243822","DOI":"10.3389\/fpls.2023.1243822","article-title":"A New Deep Learning-based Dynamic Paradigm Towards Open-World Plant Disease Detection","volume":"14","author":"J Dong","year":"2023","journal-title":"Front Plant Sci"},{"issue":"1","key":"pone.0343517.ref022","doi-asserted-by":"crossref","first-page":"10","DOI":"10.9790\/0661-16151016","article-title":"An Overview of the Research on Plant Leaves Disease detection using Image Processing Techniques","volume":"16","author":"MsKR Gavhale","year":"2014","journal-title":"IOSRJCE"},{"key":"pone.0343517.ref023","first-page":"716","article-title":"A Review of Machine Learning Approaches in Plant Leaf Disease Detection and Classification.","author":"MV Applalanaidu","year":"2021"},{"issue":"11","key":"pone.0343517.ref024","doi-asserted-by":"crossref","first-page":"4539","DOI":"10.4049\/jimmunol.1602077","article-title":"Using Visualization of t-Distributed Stochastic Neighbor Embedding To Identify Immune Cell Subsets in Mouse Tumors","volume":"198","author":"NV Acuff","year":"2017","journal-title":"J Immunol"},{"issue":"15","key":"pone.0343517.ref025","doi-asserted-by":"crossref","first-page":"2625","DOI":"10.1002\/jsfa.3765","article-title":"Efficacy of new commercial formulations to control downy mildew and dissipation of their active fungicides in wine after good agricultural practices","volume":"89","author":"RM Gonz\u00e1lez\u2010Rodr\u00edguez","year":"2009","journal-title":"J Sci Food Agric"},{"issue":"6","key":"pone.0343517.ref026","doi-asserted-by":"crossref","first-page":"2053","DOI":"10.1007\/s11119-021-09806-x","article-title":"Automation in Agriculture by Machine and Deep Learning Techniques: A Review of Recent Developments","volume":"22","author":"MH Saleem","year":"2021","journal-title":"Precision Agric"},{"issue":"5","key":"pone.0343517.ref027","doi-asserted-by":"crossref","first-page":"055402","DOI":"10.1088\/1361-6501\/ab0793","article-title":"A novel bearing fault diagnosis method based on 2D image representation and transfer learning-convolutional neural network","volume":"30","author":"P Ma","year":"2019","journal-title":"Meas Sci Technol"},{"issue":"8","key":"pone.0343517.ref028","doi-asserted-by":"crossref","first-page":"1637","DOI":"10.1162\/neco_a_01504","article-title":"Using Global t-SNE to Preserve Intercluster Data Structure","volume":"34","author":"Y Zhou","year":"2022","journal-title":"Neural Comput"},{"issue":"12","key":"pone.0343517.ref029","doi-asserted-by":"crossref","first-page":"3001","DOI":"10.3390\/agronomy14123001","article-title":"Machine Learning and Deep Learning for Crop Disease Diagnosis: Performance Analysis and Review","volume":"14","author":"HN Ngugi","year":"2024","journal-title":"Agronomy"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0343517","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T17:44:21Z","timestamp":1773078261000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0343517"}},"subtitle":[],"editor":[{"given":"C","family":"Anilkumar","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,3,9]]},"references-count":29,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3,9]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0343517","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,9]]}}}