[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117557-en":3,"doc-seo-117557-105":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},117557,2336464648746,"Skyler","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Towards crop yield prediction using Automated Machine Learning","Crop yield forecasting helps mitigate production risks and supports the UN “Zero Hunger” goal by enabling earlier recognition of potential yield failures. This work develops an AutoML-driven approach for crop yield prediction, reducing the heavy manual effort typically required to build accurate Machine Learning models. Public weather, phenological, and yield observations are used to create a dataset for winter wheat and winter barley at Germany’s regional district level. An initial evaluation compares four AutoML frameworks and three baseline models, showing consistently significantly improved performance from AutoML.","C. Hoffmann et al.: Resiliente Agri-Food-Systeme,  \n Lecture Notes in Informatics (LNI), Gesellschaft für Informatik, Bonn 2023 89 Towards crop yield prediction using Automated Machine Learning  \nJonathan Heil1, Juan Manuel Valencia 1 and Anthony Stein 1  \nAbstract: Recently, several Machine Learning models for crop yield prediction have been introduced in literature. The models differ in the underlying methodological approaches and show variations in the temporal and spatial resolution of the databases. For the creation of the models, a deep understanding of Machine Learning is required. Therefore, Automated Machine Learning, which aims to automate the creation process of Machine Learning models, offers a promising solution as an easy entry point in Machine Learning for crop yield prediction to non-professionals. Based on publicly available data for weather, phenological and yield observations, in this work, we created a dataset for winter wheat and winter barley on Germany’s regional districts level. Furthermore, an initial evaluation of four state ofthe art Automated Machine Learning frameworksand three baseline models has been conducted. The results showed almost always significantly better performance of models created by Automated Machine Learning.  \nKeywords: crop yield prediction, Automated Machine Learning, open source data, winter wheat, winter barley  \n1 Introduction  \nThe prediction of crop yields can play an important role to prevent yield failures and therefore contributes to the second Sustainable Development Goal “Zero Hunger” of the United Nations [Un15]. For instance, farmers can make use of crop yield predictions as a decision support tool to recognise potential losses and take actions to save the harvest [Ru19] . Furthermore, an accurate prediction of crop yields enables the different levels in the value chain to react to potential yield shortages or bumper crops, for example with marketing activities [Sh20]. Moreover, crop yield predictions also serve for researchers to examine influential factors such as weather conditions on crop yields [We20] . Several Machine Learning models have been introduced for the prediction of crop yields [vKC20] . The models vary in their underlying methodological approaches as well as the used data, e.g. Convolutional Neural Networks [Sr22] or Random Forest models [Vo19], weather station data [We20] or satellite images [Pe22] . However, strong expertise in Machine Learning and a deep understanding of the data is required to build reliable models. Accordingly, a high amount of manual effort for constructing a crop yield prediction model is needed. Therefore, Automated Machine Learning (AutoML) is a suitable solution to overcome the problems of expertise and time-consuming model construction. The idea  \n1 University of Hohenheim, Department of Artificial Intelligence in Agricultural Engineering, Garbenstraße 9, 70599 Stuttgart, [jonathan.heil@uni-hohenheim.de](jonathan.heil@uni-hohenheim.de); [juanmanuel.valenciapineda@uni-hohenheim.de](juanmanuel.valenciapineda@uni-hohenheim.de), [anthony.stein@uni-hohenheim.de](anthony.stein@uni-hohenheim.de)  \n 90 Jonathan Heil et al.   \nbehind AutoML is to automate the processes to build a Machine Learning model [Fe20] . This involves typical steps in the Machine Learning process, such as preprocessing of the data, model selection or the optimization of hyperparameters. AutoML frameworks showed promising results in benchmark tests on classification and regression problems [Er20] .  \nThe heterogeneous and sophisticated research area of crop yield prediction exposes as a well-suited use case for AutoML: (1) Open access databases for yield observations [St22], climate data [De22b; De22a] and satellite images [Pe22] are available. (2) Researchers pursue different aims in their studies. Some are using the Machine Learning models to search for influential factors on crop yields [We20], others try to improve the models’prediction accuracies [Sr22] ","cbCainhWQjUMlMdw","https://ap.wps.com/l/cbCainhWQjUMlMdw","pdf",477224,1,12,"English","en",105,"# Introduction\n# Crop yield prediction using Machine Learning","[{\"question\":\"Why is crop yield prediction important for farmers and the value chain?\",\"answer\":\"Accurate forecasts help farmers recognize potential losses and take actions to save the harvest. They also enable stakeholders to respond to shortages or bumper crops through planning and marketing activities.\"},{\"question\":\"What data is used to build the dataset in this study?\",\"answer\":\"The dataset is created from publicly available weather, phenological, and yield observations, covering winter wheat and winter barley at Germany’s regional districts level.\"},{\"question\":\"How is Automated Machine Learning evaluated in the work?\",\"answer\":\"Four state-of-the-art AutoML frameworks are evaluated alongside three baseline models. Results show that models created by AutoML generally achieve significantly better performance.\"}]","Towards crop yield prediction using Automated Machine Learning | PDF",1785676966,30,{"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},"towards-crop-yield-prediction-using-automated-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/towards-crop-yield-prediction-using-automated-machine-learning/117557/",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","2026-08-02",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 crop yield prediction important for farmers and the value chain?","Question",{"text":75,"@type":76},"Accurate forecasts help farmers recognize potential losses and take actions to save the harvest. They also enable stakeholders to respond to shortages or bumper crops through planning and marketing activities.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What data is used to build the dataset in this study?",{"text":80,"@type":76},"The dataset is created from publicly available weather, phenological, and yield observations, covering winter wheat and winter barley at Germany’s regional districts level.",{"name":82,"@type":73,"acceptedAnswer":83},"How is Automated Machine Learning evaluated in the work?",{"text":84,"@type":76},"Four state-of-the-art AutoML frameworks are evaluated alongside three baseline models. Results show that models created by AutoML generally achieve significantly better performance.","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},[93,97,101,105,110,115,120,122,127,130,134],{"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":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":29,"slug":121},"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":106,"slug":137},19,"General","general"]