[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124461-en":3,"doc-seo-124461-105":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":20,"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},124461,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","Detection of Hazelnut Orchards with Sentinel-2 imagery and machine learning classification algorithms","Hazelnut (Corylus avellana L.) is a key Turkish crop, with Sakarya as a major growing region where efficient large-scale monitoring is needed. The study uses field surveys from about 150 hazelnut orchards to build training data and stacks multi-temporal Sentinel-2 imagery across six acquisition dates covering major phenological stages. Vegetation indices (NDVI, AVI, SAVI, EVI) improve class separability, and supervised classification is performed with Random Forest and XGBoost with hyperparameter tuning and cross-validation. Both models detect hazelnut orchards well, with RF showing stronger quantitative and visual performance.","Detection of Hazelnut Orchards with Sentinel-2 imagery and machine learning classification  \nalgorithms  \nGafur Semi Sengul 1, Ilay Nur Tumer 2, Elif Sertel 3, Beyza Ustaoglu 4  \n1 ITU, Civil Engineering Faculty, 80626 Maslak Istanbul, Turkey – [sengulg18@itu.edu.tr](sengulg18@itu.edu.tr)  \n2 ITU, Civil Engineering Faculty, 80626 Maslak Istanbul, Turkey – [tumer17@itu.edu.tr](tumer17@itu.edu.tr)  \n3 ITU, Civil Engineering Faculty, 80626 Maslak Istanbul, Turkey – [sertele@itu.edu.tr](sertele@itu.edu.tr)  \n4 SAU, Humanities and Social Sciences Faculty, 54050 Esentepe Sakarya, Turkey – [bustaoglu@sakarya.edu.tr](bustaoglu@sakarya.edu.tr)  \nKeywords: Hazelnut, Remote sensing, Sentinel-2, Machine learning, Classification, Phenological stages.  \nAbstract  \nHazelnut (Corylus avellana L.) is an economically important crop in Turkey, with Sakarya being a major cultivation region. Effective large-scale monitoring of hazelnut orchards can be achieved using remote sensing and machine learning techniques. In this study, field surveys were conducted in approximately 150 hazelnut orchards in Sakarya to provide training data. Multi-temporal Sentinel-2 imagery from six acquisition dates capturing key phenological stages was stacked for the classification of hazelnut orchards and other land use/land cover (LULC) types. Vegetation indices including NDVI, AVI, SAVI, and EVI were applied to enhance class separability. Supervised classification was performed using Random Forest (RF) and Extreme Gradient Boosting (XGBoost) algorithms, with hyperparameters optimized via RandomizedSearchCV and cross-validation. Both models achieved high performance in detecting hazelnut orchards; however, RF yielded better overall results in quantitative metrics and visual assessments. These findings demonstrate that integrating multi-temporal Sentinel-2 data, vegetation indices, and machine learning enables accurate large-scale mapping of hazelnut orchards in Sakarya.  \n1. Introduction  \nHazelnut (Corylus avellana L.) is a highly preferred agricultural product due to their rich nutritional value and widespread use across various industries. Turkey, with its climate and geography in the Black Sea region, provides ideal conditions for hazelnut cultivation and holds a leading position globally. According to Food and Agricultural Organization data for 2023, Turkey ranked first in both hazelnut production and exports, accounting for approximately 58% of global production (FAO , 2025) . This has made hazelnut a valuable economic commodity for Turkey, prompting the implementation of various policies aimed at increasing productivity. In particular, the increase in regularly maintained and newly established orchards in Sakarya has significantly improved yield levels, positioning the province as the third-largest hazelnut-producing region in the country with 12.7% in 2023 (TEPGE, 2024) . Due to the vast areas involved in hazelnut cultivation, remote sensing technologies have not only become a practical tool but also a necessity for monitoring and analyzing production areas effectively.  \nRemote sensing technologies, such as multispectral imagery, have brought new opportunities to the sustainable agriculture sector and land use/land cover (LULC) classification. To effectively analyze the large volume and complexity of remote sensing data, advanced computational techniques are required. In this context, machine learning methods are commonly used to detect agricultural areas and to assess the health and density of trees and crops. These advantages not only facilitate largescale monitoring but also enhance the ability to distinguish specific crop types, such as hazelnut, based on their unique spatial and spectral characteristics. Sentinel-2 with 12 spectral bands, providing a 10 meters spatial resolution for visible bands (Red, Green, Blue), 20 meters for infrared and some other bands, and 60 meters for atmospheric bands. This multi-band  \ncapability, coupled with its high tempora","cbCaioHHAOR6zRlB","https://ap.wps.com/l/cbCaioHHAOR6zRlB","pdf",1031605,1,5,"English","en",105,"# Introduction\n## Remote sensing for agricultural monitoring\n## Sentinel-2 and multi-temporal analysis\n## Vegetation indices for crop discrimination\n## Machine learning methods for classification\n## Related work on hazelnut orchard detection","[{\"question\":\"How was training data for hazelnut orchard detection collected?\",\"answer\":\"Field surveys were conducted in approximately 150 hazelnut orchards in Sakarya to provide training data for the classification models.\"},{\"question\":\"What Sentinel-2 information was used in the classification workflow?\",\"answer\":\"Multi-temporal Sentinel-2 imagery from six acquisition dates was stacked, capturing key phenological stages for hazelnut orchards and other land use/land cover types.\"},{\"question\":\"Which machine learning algorithms were compared, and which performed better?\",\"answer\":\"Random Forest (RF) and Extreme Gradient Boosting (XGBoost) were used for supervised classification. RF achieved better overall results in quantitative metrics and visual assessments.\"}]","Detection of Hazelnut Orchards with Sentinel-2 imagery and machine learning classification algorithms | PDF",1785822434,13,{"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},"detection-of-hazelnut-orchards-with-sentinel-2-imagery-and-machine-learning-classification-algorithms","",{"@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/detection-of-hazelnut-orchards-with-sentinel-2-imagery-and-machine-learning-classification-algorithms/124461/",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","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"How was training data for hazelnut orchard detection collected?","Question",{"text":75,"@type":76},"Field surveys were conducted in approximately 150 hazelnut orchards in Sakarya to provide training data for the classification models.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What Sentinel-2 information was used in the classification workflow?",{"text":80,"@type":76},"Multi-temporal Sentinel-2 imagery from six acquisition dates was stacked, capturing key phenological stages for hazelnut orchards and other land use/land cover types.",{"name":82,"@type":73,"acceptedAnswer":83},"Which machine learning algorithms were compared, and which performed better?",{"text":84,"@type":76},"Random Forest (RF) and Extreme Gradient Boosting (XGBoost) were used for supervised classification. RF achieved better overall results in quantitative metrics and visual assessments.","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},[93,97,101,105,109,114,119,122,127,130,134],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":21,"slug":137},19,"General","general"]