[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127057-en":3,"doc-seo-127057-105":29,"detail-sidebar-cat-0-en-105":90},{"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":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},127057,962084931830,"Theodore","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Optimum Combination of Spectral Variables for Crop Mapping in Heterogeneous Landscapes - Sentinel-2 Time Series and Machine Learning","A workflow is proposed for more efficient large-scale crop mapping using Sentinel-2 time-series imagery, statistical attribute selection, and machine learning. The approach tests the optimal combination of vegetation-related spectral variables by deriving 16 vegetation indices across RGB, NIR, SWIR, and Red Edge regions to capture diverse spectro-temporal LULC profiles. PCA is used for dimensionality reduction, then highly correlated variables feed spectro-temporal classification via Random Forest, TempCNN, and LightTAE under three strategies. Results show scenario C2 achieves the strongest LULC accuracy at crop-pattern level, highlighting the value of Red Edge-based qualitative and quantitative sampling variability for heterogeneous landscapes.","Optimum Combination of Spectral Variables for Crop Mapping in Heterogeneous Landscapes based on Sentinel-2 Time Series and Machine Learning  \nJosé Galdino de Oliveira Júnior 1; Júlio César Dalla Mora Esquerdo 1,2 & Rubens Augusto Camargo Lamparelli 1,3  \n1 UNICAMP-Universidade Estadual de Campinas, Brazil;  \n2 Embrapa Agricultura Digital, Brazil;  \n3 NIPE-Núcleo Interdisciplinar de Planejamento Energético, Brazil  \nKeywords: Remote sensing, Random Forest, SITS, Red Edge, agricultural monitoring.  \nAbstract  \nThis article aimed to determine a workflow for more efficient large-scale crop mapping using a time series of images from the Sentinel-2 Satellite, statistical methods of attribute selection, and machine learning. The proposed methodology explores the best possible combination of spectral variables related to vegetation (16 vegetation indices in the RGB, NIR, SWIR, and Red Edge regions) to characterize different spectro-temporal profiles of Land Use and Land Cover (LULC) in spatially heterogeneous landscapes. First, we applied a data dimensionality reduction analysis using the PCA (Principal Component Analysis) method. Subsequently, the variables that showed the highest statistical correlation between each other were used in the spectro-temporal classification process, using the Random Forest, TempCNN, and LightTAE algorithms, following three different strategies: C1 (ALL), C2 (BE + IV (Red Edge)) and C3 (BE + IV (without Red Edge)), where ALL – All variables; BE – Spectral Bands; IV – Vegetation Indices. Given the results found, the C2 classification scenario (with bands B3, B4, B5, B6, B7, B8, and B8A and the NDRE1, RESI, and MSR indexes) demonstrated the best LULC classification accuracy at the crop pattern level, compared to the other scenarios, with average values of 0.91, 0.88, 0.91, 0.89, and 0.89 (Global Accuracy, Producer Accuracy, User Accuracy, Kappa index, and F1-Score, respectively, for the TempCNN model), the which emphasized the importance of both qualitative and quantitative variability of sampling data and variables based on the Red Edge region for improving LULC classification processes in large-scale heterogeneous landscapes.  \n1. Introduction  \nAgricultural monitoring is a fundamental step for effective decision-making in the field, both concerning production management and the reduction of harmful impacts on the environment arising from the intensification of agricultural practices (Ajadi et al., 2021; Wang et al., 2021; Pott et al., 2022) . However, the efficiency of crop monitoring, especially on a large scale, depends on the correct use of strategies for extracting, manipulating, and processing sample data.  \nAmong the most common monitoring methods is information extraction regarding production cycles, carried out directly in the field through occasional and recurring technical visits (Talukdar et al., 2020) . However, obtaining this sample data is still subject to limiting factors such as high operational costs and high time consumption to carry out this process (Pott et al., 2021; Mahlayeye; Darvishzadeh and Nelson, 2022) . On the other hand, remote sensing data (orbital, suborbital, or proximal) makes it possible to obtain multiple relevant information from the Earth's surface mapping with a more suitable temporal frequency.  \nSpecifically, in studies on the estimation of agricultural production, remote sensing can obtain several aspects intrinsic to the biophysical characteristics of vegetation present in the field, such as level of plant phenology, occurrence of water stress, impact of seasonal climate changes on cycles production, crop productivity prediction, among others (Mercier et al., 2020; Debella-Gilo; Gjertsen, 2021) . It can result in a considerable reduction in operational costs related to carrying out large-scale agricultural monitoring (Wang et al., 2023) .  \nArslan, Topakci & Demir (2022), on the other hand, reinforce that mapping and monitoring such spatio-temporal changes becom","cbCaifJsNQWJM9l0","https://ap.wps.com/l/cbCaifJsNQWJM9l0","pdf",1175373,1,"English","en",105,"# 1. Introduction\n## Agricultural monitoring and sampling constraints\n## Remote sensing for production estimation and vegetation phenology\n## Challenges in tropical large-scale mapping and current LULC systems\n## Sentinel-2 Red Edge and time-series classification potential\n## Literature review: time-series fusion and ML strategies","[{\"question\":\"What workflow is proposed for large-scale crop mapping?\",\"answer\":\"It combines Sentinel-2 time-series images, statistical attribute selection, PCA-based dimensionality reduction, and spectro-temporal classification using Random Forest, TempCNN, and LightTAE under defined variable-selection strategies.\"},{\"question\":\"How are spectral variables and vegetation indices selected?\",\"answer\":\"Sixteen vegetation indices derived from RGB, NIR, SWIR, and Red Edge regions are evaluated, and PCA is applied first. Then variables showing the highest statistical correlation are used to form spectro-temporal classification inputs.\"},{\"question\":\"Which strategy performed best for LULC classification accuracy and why?\",\"answer\":\"Scenario C2 (including selected spectral bands and Red Edge-related indices) showed the best crop-pattern-level LULC accuracy, emphasizing the importance of Red Edge qualitative and quantitative variability in improving classification for heterogeneous landscapes.\"}]","Optimum Combination of Spectral Variables for Crop Mapping in Heterogeneous Landscapes - Sentinel-2 Time Series and Machine Learning | PDF",1785936584,20,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"optimum-combination-of-spectral-variables-for-crop-mapping-in-heterogeneous-landscapes-sentinel-2-time-series-and-machine-learning","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/optimum-combination-of-spectral-variables-for-crop-mapping-in-heterogeneous-landscapes-sentinel-2-time-series-and-machine-learning/127057/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":22,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What workflow is proposed for large-scale crop mapping?","Question",{"text":74,"@type":75},"It combines Sentinel-2 time-series images, statistical attribute selection, PCA-based dimensionality reduction, and spectro-temporal classification using Random Forest, TempCNN, and LightTAE under defined variable-selection strategies.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How are spectral variables and vegetation indices selected?",{"text":79,"@type":75},"Sixteen vegetation indices derived from RGB, NIR, SWIR, and Red Edge regions are evaluated, and PCA is applied first. Then variables showing the highest statistical correlation are used to form spectro-temporal classification inputs.",{"name":81,"@type":72,"acceptedAnswer":82},"Which strategy performed best for LULC classification accuracy and why?",{"text":83,"@type":75},"Scenario C2 (including selected spectral bands and Red Edge-related indices) showed the best crop-pattern-level LULC accuracy, emphasizing the importance of Red Edge qualitative and quantitative variability in improving classification for heterogeneous landscapes.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":28,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":28,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]