[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128359-en":3,"doc-seo-128359-105":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},128359,962085571259,"Theodora","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Exploring frogeye leaf spot disease severity in soybean based on hyperspectral data analysis and machine learning with Orange data mining","Advancement in hyperspectral remote sensing enables categorization of frogeye leaf spot (FLS) severity in soybean, yet limited work has evaluated Orange data mining as a visual programming approach for analyzing hyperspectral reflectance for crop disease detection. The study classifies FLS severity using hyperspectral reflectance and machine learning, applying Savitzky-Golay smoothing, ReliefF feature selection, and multiple classifiers evaluated by accuracy, F1, precision, and ROC-based metrics. Orange workflow with a spectroscopic widget supports severity determination.","Agr. Nat. Resour. 59 (2025) 590201  \n\n| \u003Cbr>\u003Cbr>\u003Cbr>AGRICULTURE AND NATURAL RESOURCES\u003Cbr>\u003Cbr>Journal homepage: [http://anres.kasetsart.org](http://anres.kasetsart.org) |  |  |\n| --- | --- | --- |\n| Research article\u003Cbr>Exploring frogeye leaf spot disease severity in soybean based on hyperspectral data analysis and machine learning with Orange data mining\u003Cbr>Yuhao Anga, Helmi Zulhaidi Mohd Shafrib,*, Mohammed Mustafa Al-Habshib\u003Cbr>a Faculty of Sustainable Agriculture, Universiti Malaysia Sabah Sandakan Campus, Locked BagNo. 3, 90509 Sandakan, Sabah, Malaysia\u003Cbr>b Department of Civil Engineering and Geospatial Information Science Research Centre (GISRC), Faculty of Engineering, Universiti Putra Malaysia (UPM), 43400 Serdang, Selangor, Malaysia |  |  |\n| Article Info |  | Abstract |\n| Article history:\u003Cbr>Received 14 May 2024\u003Cbr>Revised 19 August 2024\u003Cbr>Accepted 24 December 2024 Available online 28 April 2025 |  | Importance of the work: The advancement of hyperspectral remote sensing technology has facilitated the examination of its potential for categorizing frogeye leaf spot (FLS) severity in soybean. No study has yet investigated the Orange mining tool as a visual programming approach to analyze hyperspectral reflectance data, especially in crop disease detection. Objectives: To classify the severity level of FLS disease in soybean using hyperspectral reflectance data and machine learning algorithms.\u003Cbr>Materials and Methods: Hyperspectral reflectance data were used from healthy and FLS-affected soybeans. Initially, the data were smoothed by applying the Savitzky-Golay filtering technique to remove spectrum noise. The ReliefF feature selection technique was used to determine the most influential wavelengths for the classification of FLS disease severity in soybean. Next, machine learning methods (decision tree, gradient boosting, random forest, stacking and neural network) were used to classify FLS severity in soybean. The performance was evaluated using overall accuracy, F1, precision and the curve metric receiver-operating characteristic. All these steps were conducted using the Orange data mining software.\u003Cbr>Results: Neural network scored the highest overall accuracy (98.6%) after conducting the filtering technique. Furthermore, the ReliefF-gradient boosting and the random forest algorithms achieved promising overall levels of accuracy (97.4% and 96.9%, respectively) after implementing the filtering and feature selection techniques.\u003Cbr>Main finding: The integration of the workflow and the specially designed spectroscopic widget in the Orange data mining software made it possible to process the hyperspectral reflectance data and to determine the severity level of the disease on the affected crop samples. |\n| Keywords:\u003Cbr>Feature selection, Hyperspectral remote sensing, Machine learning,\u003Cbr>Orange data mining software |  |  |\n\n* Corresponding author.  \nE-mail [address:](address: helmi@upm.edu.my/hzms2312@gmail.com)[ helmi@upm.edu.my](address: helmi@upm.edu.my/hzms2312@gmail.com)[/](address: helmi@upm.edu.my/hzms2312@gmail.com)[hzms2312@gmail.com](address: helmi@upm.edu.my/hzms2312@gmail.com) (H.Z.M. Shafri)  \nonline 2452-316X print 2468-1458/Copyright © 2025. This is an open access article under the CC BY-NC-ND license ([http://creativecommons.org/licenses/by-nc-nd/4.0/](http://creativecommons.org/licenses/by-nc-nd/4.0/)), production and hosting by Kasetsart University Research and Development Institute on behalf of Kasetsart University.  \n[https://doi.org/10.34044/j.anres.2025.59.2.01](https://doi.org/10.34044/j.anres.2025.59.2.01)  \nIntroduction  \nSoybean is the second largest cop producing primarily edible oils and a major source of proteins (Dreoni et al., 2022) . Globally, the majority of soybeans are fed to pigs (Parrini,2023) . The global total soybean production in 2021 was 367.76 million tons with the forecast that soybean production would decline by 4.63% or 17.04 million tons in the near future (Tetrault, 2023) . ","cbCaif3yOmue04xR","https://ap.wps.com/l/cbCaif3yOmue04xR","pdf",1385664,3,1,11,"English","en",105,"# Introduction\n## Hyperspectral remote sensing for disease assessment\n## Visual identification challenges","[{\"question\":\"What is the main objective of this study on soybean frogeye leaf spot?\",\"answer\":\"To classify the severity level of frogeye leaf spot in soybean using hyperspectral reflectance data and machine learning algorithms.\"},{\"question\":\"How were hyperspectral data processed before classification?\",\"answer\":\"The spectra were smoothed using Savitzky-Golay filtering to remove noise, and ReliefF was used to select the most influential wavelengths for severity classification.\"},{\"question\":\"Which machine learning method achieved the best overall accuracy and what were the key results?\",\"answer\":\"Neural networks achieved the highest overall accuracy (98.6%) after filtering. ReliefF-gradient boosting and random forest also performed strongly (97.4% and 96.9%).\"}]","Exploring frogeye leaf spot disease severity in soybean based on hyperspectral data analysis and machine learning with Orange data mining | PDF",1785947051,28,{"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},"exploring-frogeye-leaf-spot-disease-severity-in-soybean-based-on-hyperspectral-data-analysis-and-machine-learning-with-orange-data-mining","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":20},"https://docshare.wps.com/document/research-report/",{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/exploring-frogeye-leaf-spot-disease-severity-in-soybean-based-on-hyperspectral-data-analysis-and-machine-learning-with-orange-data-mining/128359/",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","2026-08-27","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 this study on soybean frogeye leaf spot?","Question",{"text":76,"@type":77},"To classify the severity level of frogeye leaf spot in soybean using hyperspectral reflectance data and machine learning algorithms.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How were hyperspectral data processed before classification?",{"text":81,"@type":77},"The spectra were smoothed using Savitzky-Golay filtering to remove noise, and ReliefF was used to select the most influential wavelengths for severity classification.",{"name":83,"@type":74,"acceptedAnswer":84},"Which machine learning method achieved the best overall accuracy and what were the key results?",{"text":85,"@type":77},"Neural networks achieved the highest overall accuracy (98.6%) after filtering. ReliefF-gradient boosting and random forest also performed strongly (97.4% and 96.9%).","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},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"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":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]