[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125806-en":3,"doc-seo-125806-105":30,"detail-sidebar-cat-0-en-105":91},{"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":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},125806,4398048949847,"Eliana","https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267",8,"Research & Report","Enhancing Anthracnose Detection in Mango at Early Stages Using Hyperspectral Imaging and Machine Learning","Anthracnose, caused by Colletotrichum sp. infections, threatens mango production worldwide and is difficult to detect and control because symptoms appear late. Existing control approaches depend on corrective detection once the disease is visibly advanced. Hyperspectral imaging enables non-destructive assessment of external and internal fruit damage, supporting earlier intervention. This study evaluates early anthracnose detection in two mango varieties using hyperspectral imaging and machine learning, correlating wavelengths with physicochemical symptoms and building a robust spectral detection model.","1 Enhancing anthracnose detection in mango at early stages using hyperspectral  \n2 imaging and machine learning  \n3 Carlos Velásqueza,b, Nuria Aleixos Borrásb, Juan Gomez-Sanchisc, Sergio Cuberod, Flavio Prietoa, José  \n4 Blascod*  \n5 a Universidad Nacional de Colombia, Carrera 45, Bogotá, Colombia ([cvelasquez@unal.edu.co](cvelasquez@unal.edu.co))  \n6 b Departamento de Ingeniería Gráfica. Universitat Politècnica de València. Camino de Vera, s/n, 46022, Valencia, España  \n7 c Departamento de Ingeniería Electrónica, Universidad de Valencia, Av. de Blasco Ibáñez, 13, 46010, Valencia (Spain), 8 d Centro de Agroingeniería. Instituto Valenciano de Investigaciones Agrarias. CV-315, km 10,7 . Moncada (Valencia)  \n9 Spain ([blasco_josiva@gva.es](blasco_josiva@gva.es))  \n10  \n11 Abstract  \n12 Anthracnose, caused by Colletotrichum sp. infections, poses a significant threat to mango production  \n13 worldwide, resulting in substantial losses. This devastating disease is challenging to detect and control, 14 primarily due to its ability to spread rapidly. The methods currently used to control anthracnose are primarily  \n15 corrective, relying on disease detection in the late stages when the infection becomes visible. Hence, there is a  \n16 need for tools to detect the infection at early stages, before symptoms appear. Hyperspectral imaging systems  \n17 offer a promising avenue for developing non-destructive solutions to assess and detect external and internal  \n18 damage in fruit, including decay caused by anthracnose. These advanced imaging systems make early detection  \n19 possible before the symptoms are visible, allowing for timely intervention and potentially more effective disease  \n20 control. This work aims to evaluate the possibility of early detection of anthracnose in two different mango  \n21 varieties using hyperspectral imaging and machine learning methods. Secondly, it seeks to establish correlations  \n22 between specific wavelengths and the physicochemical symptoms associated with anthracnose. Lastly, it  \n23 intends to develop a robust model for the spectral detection of anthracnose on mango fruit. Mangoes were  \n24 inoculated with spores of Colletotrichum gloeosporioides. Hyperspectral images of control and infected fruit  \n25 were captured in the 450–970 nm spectral range. Five machine-learning models were used to obtain the method  \n26 that best fits the spectral data. Using the full spectrum and ten selected bands, two neural network models could  \n27 detect early anthracnose infection in mango fruit within 48 hours after pathogen inoculation.  \n28 Keywords: Mangifera indica L, anthracnose detection, wavelength selection, fruit quality.  \n29  \n30 1. Introduction  \n31 Mango (Mangifera indica L.) is one of the most consumed tropical fruit worldwide (Galán Saúco, 2017) . Its  \n32 attractiveness lies in the variety, flavour and nutrients it provides in the human diet (Evans et al., 2017;  \n33 Bambalele et al., 2021) . However, yields ofthis crop are dropping globally. While the cultivated area has grown  \n34 by 8.2 % from 2018 to 2021, its production has increased by only 4.98 % in the same period, reaching 57.01  \n35 million tons in 2021 (FAO, 2022a) . This situation has been observed by producers and exporters of this fruit, 36 such as Mexico and Thailand, which have experienced stagnation in their production due to adverse climatic  \n37 conditions (periods of heavy rain, prolonged cold seasons) (FAO, 2022b), which has altered the production  \n38 cycles and the global supply chain of this cultivar.  \n39  \n40 In recent years, mango has positioned itself as one of the top 3 fruit crops in Colombia, just behind orange and 41 avocado, and has gained economic relevance because it can be harvested during 10 of the 12 months of the year 42 due to the country’s privileged geographical location near the equator. This enables the production of this fruit 43 and its supply to international markets due to the shorter harvesting seaso","cbCaiiiUWRL7P93n","https://ap.wps.com/l/cbCaiiiUWRL7P93n","pdf",1880060,1,35,"English","en",105,"# Abstract\n# 1. Introduction\n## Mango production context and challenges\n## Anthracnose impact and current detection limitations\n# 2. Materials and Methods\n## Hyperspectral imaging setup and spectral range\n## Inoculation procedure and sample groups\n## Machine-learning models and evaluation approach\n# 3. Results\n## Selected wavelengths and correlations\n## Early detection performance across models\n# 4. Discussion\n## Practical implications for early, non-destructive detection\n# 5. Conclusion","[{\"question\":\"Why is early anthracnose detection important in mango production?\",\"answer\":\"Anthracnose spreads rapidly and is typically detected only after external symptoms appear, which leads to corrective actions that arrive too late. Detecting it earlier enables timely intervention and more effective disease control.\"},{\"question\":\"How do hyperspectral imaging and machine learning work together in this study?\",\"answer\":\"Mango fruits are imaged using hyperspectral sensors in the 450–970 nm range, capturing both control and infected samples. Five machine-learning models analyze full-spectrum data and selected bands to identify the earliest detectable infection.\"},{\"question\":\"What was achieved regarding early detection timing after inoculation?\",\"answer\":\"Two neural network models using either the full spectrum or ten selected bands could detect early anthracnose infection within 48 hours after pathogen inoculation.\"}]","Enhancing Anthracnose Detection in Mango at Early Stages Using Hyperspectral Imaging and Machine Learning | PDF",1785901317,88,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"enhancing-anthracnose-detection-in-mango-at-early-stages-using-hyperspectral-imaging-and-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/enhancing-anthracnose-detection-in-mango-at-early-stages-using-hyperspectral-imaging-and-machine-learning/125806/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is early anthracnose detection important in mango production?","Question",{"text":75,"@type":76},"Anthracnose spreads rapidly and is typically detected only after external symptoms appear, which leads to corrective actions that arrive too late. Detecting it earlier enables timely intervention and more effective disease control.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How do hyperspectral imaging and machine learning work together in this study?",{"text":80,"@type":76},"Mango fruits are imaged using hyperspectral sensors in the 450–970 nm range, capturing both control and infected samples. Five machine-learning models analyze full-spectrum data and selected bands to identify the earliest detectable infection.",{"name":82,"@type":73,"acceptedAnswer":83},"What was achieved regarding early detection timing after inoculation?",{"text":84,"@type":76},"Two neural network models using either the full spectrum or ten selected bands could detect early anthracnose infection within 48 hours after pathogen inoculation.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]