[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127025-en":3,"doc-seo-127025-105":30,"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":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},127025,2336474466412,"Ezra","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","STRATIFIED MACHINE LEARNING MODELS FOR WHEAT YIELD ESTIMATION USING REMOTE SENSING DATA","Field-level wheat yield estimation using machine learning faces difficulty when scaled to large regions because yield variability is driven by topography and climate, requiring large representative samples. The work decomposes agricultural landscape complexity via landforms and agro-ecological zones, using these classes to partition field samples with spatial constraints. Three remote-sensing-based models are trained; stratified training improves accuracy, achieving R² up to 0.72 for plain areas versus lower overall performance without constraints.","IGARSS 2024-2024 IEEE International Geoscience and Remote Sensing Symposium | 979-8-3503-6032-5/24/$31.00 ©2024 IEEE | DOI: 10. 1 109/IGARSS53475.2024. 10641044  \nSTRATIFIED MACHINE LEARNING MODELS FOR WHEAT YIELD ESTIMATION USING  \nREMOTE SENSING DATA  \nKeltoum Khechba1,2, Mariana Belgiu2, Ahmed Laamrani1,3, Qi Dong2,4, Alfred Stein²,  \nAbdelghani Chehbouni1  \n1Center for Remote Sensing Applications (CRSA), Mohammed VI Polytechnic University (UM6P), Benguerir 43150, Morocco. Email: keltoum.khechba@um6p.ma  \n2Department of Earth Observation Science Digital Society Institute UT-I-ITC-ACQUAL Faculty of  \nGeo-Information Science and Earth Observation  \n3Department of Geography, Environment & Geomatics, University of Guelph, Guelph, Ontario, Canada  \n4Key Laboratory of Earth Surface Processes and Resource Ecology, Faculty of Geographical Science,  \nBeijing Normal University, Beijing 100875, China  \nABSTRACT  \nField-Level cereal yield estimation using Machine Learning (ML) models poses a significant challenge especially when applied across large areas. A large sample size is required to represent the high yield variability caused by varying topographic and climatic conditions. To enhance ML-based prediction accuracy, we propose to decompose the complexity of agricultural landscape using landforms andagro-ecological zones and use these classes as spatially explicit constraints to partition field samples. We trained three ML models using remote sensing data to estimate wheat yield. When training ML models without the mentioned spatial constraints, we achieved an R²=0.58 and RMSE=840kg/ha. Training ML separately across various landform classes increase the accuracy. For instance, wheat yield cultivated in plain areas was predicted with R2=0.72, and RMSE=809kg/ha. These results emphasized the potential of training ML separately across main landform classes for improving the accuracy of yield predictions across diverse geographical contexts.  \nIndex Terms— Landform classification, Sentinel-2, yield, global agroecological zones, stratification.  \n1. INTRODUCTION  \nCereal crops are important for global food security, providing essential nutrition to diverse diets. This is particularly evident in semi-arid regions like Morocco, where wheat is a key staple crop. Recently, Morocco experienced a drastic drop in wheat production which highlights the need for improved  \ntechnology and farming methods to sustain and increase crop yields [1] .  \nAccurate crop yield estimates are important for understanding how various management practices and environmental conditions affect agricultural productivity [2] . Advancements in remote sensing and machine learning (ML) have significantly improved cereal monitoring and yield predictions [3][4]. The effectiveness of ML models, however, largely depends upon the availability of relevant training data that are capable of capturing the spatial variance of wheat yield. For example, the diversity of environmental and agricultural conditions characterizing the agricultural landscape of Morocco, i.e. varying climates, soil types, land use, leads to high spatial variation of wheat yield. Consequently, models trained on data from the entire study area might be challenged by the high variability at the local level. In addition, the use of remote sensing images adds to the complexity of ML-based yield predictions because of the potential noise present in these images caused by shadows, cloud cover, and terrain [5][6] . For example, mountainous areas might have more pronounced shadows and slope effects than plains [7] .  \nTo mitigate these challenges, we recognize that the landscape is naturally partitioned into homogeneous areas exhibiting similar vegetation responses to soil, terrain, climate, weather, land use, and other factors [8] . Our study aims to evaluate the effectiveness of ML trained and tested using samples that were stratified based upon existing landforms classification maps, and global agroecological zo","cbCaijQa3vp1URSP","https://ap.wps.com/l/cbCaijQa3vp1URSP","pdf",1217439,1,4,"English","en",105,"# Introduction\n# Methodology\n## Study area and data","[{\"question\":\"Why is field-level wheat yield estimation challenging across large areas?\",\"answer\":\"Large areas exhibit strong spatial variability driven by changing topographic and climatic conditions, which makes model transfer difficult without sufficiently representative training samples.\"},{\"question\":\"How does the proposed method use spatial stratification?\",\"answer\":\"It partitions field samples using landform classification maps and global agro-ecological zones so that training is constrained by spatially coherent landscape classes.\"},{\"question\":\"Which remote sensing data sources and ML models are used?\",\"answer\":\"The study uses Sentinel-1 and Sentinel-2 data and trains three models: XGBoost, Random Forest, and Multiple Linear Regression.\"}]","STRATIFIED MACHINE LEARNING MODELS FOR WHEAT YIELD ESTIMATION USING REMOTE SENSING DATA | PDF",1785936396,10,{"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":85,"head_meta":87,"extra_data":89,"updated_unix":28},"stratified-machine-learning-models-for-wheat-yield-estimation-using-remote-sensing-data","",{"@graph":36,"@context":84},[37,53,67],{"@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":21},"https://docshare.wps.com/document/stratified-machine-learning-models-for-wheat-yield-estimation-using-remote-sensing-data/127025/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"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},"Why is field-level wheat yield estimation challenging across large areas?","Question",{"text":74,"@type":75},"Large areas exhibit strong spatial variability driven by changing topographic and climatic conditions, which makes model transfer difficult without sufficiently representative training samples.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does the proposed method use spatial stratification?",{"text":79,"@type":75},"It partitions field samples using landform classification maps and global agro-ecological zones so that training is constrained by spatially coherent landscape classes.",{"name":81,"@type":72,"acceptedAnswer":82},"Which remote sensing data sources and ML models are used?",{"text":83,"@type":75},"The study uses Sentinel-1 and Sentinel-2 data and trains three models: XGBoost, Random Forest, and Multiple Linear Regression.","https://schema.org",{"og:url":52,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,133],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},5,"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":29,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":29,"slug":132},"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]