[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85517-en":3,"doc-seo-85517-105":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":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},85517,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","Probabilistic Wind Power Forecasting with Tree Based Machine Learning and Weather Ensembles","Accurate wind power production forecasts are vital for integrating renewable energy into the power grid. The paper presents probabilistic forecasting of wind generation using gradient boosting trees combined with an ensemble of weather forecasts. It compares three state-of-the-art probabilistic approaches—conformalized quantile regression, natural gradient boosting, and conditional diffusion models—within a tree based learning framework. Experiments use four years of data across Belgian offshore wind farms and benchmark against power curves, calibrated wake models, and a Gaussian process baseline. Results show notable reductions in MAE and improved probabilistic skill, with the diffusion model achieving the strongest performance, and weather ensembles improving point accuracy by 17%.","Probabilistic Wind Power Forecasting with Tree-Based Machine Learning and Weather  \nEnsembles  \nMax Bruninx 1 , Diederik van Binsbergen 1,2 , Timothy Verstraeten 1 , Ann Now1 , and Jan Helsen 1  \n1Vrije Universiteit Brussel, Brussels, Belgium  \n2Norwegian University of Science and Technology, Trondheim, Norway  \narXiv :2602 . 130 10v2 [ cs .LG] 13 Jul 2026  \nAbstract—Accurate production forecasts are essential for the integration of renewable energy sources into the power grid. This paper illustrates how to obtain probabilistic forecasts of wind power generation using gradient boosting trees and an ensemble of weather forecasts. To this end, we perform a comparative analysis across three state-of-the-art probabilistic prediction methods—conformalized quantile regression, natural gradient boosting and conditional diffusion models—all of which can be combined with tree-based machine learning. The methods are validated using four years of data for all Belgian offshore wind farms. We benchmark the models against the power curve and a calibrated wake model as well as a probabilistic method using stochastic variational Gaussian process regression. The tree-based models significantly reduce the mean absolute error in comparison to the deterministic baselines. Additionally, all three methods outperform the Gaussian process baseline in probabilistic skill, while two out of the three also improve point forecast accuracy. The conditional diffusion model attains the best performance, with improvements of 5% in mean absolute error and 12% in continuous rank probability score compared to the probabilistic baseline. Last, the results indicate an average improvement in point forecast accuracy of 17% by using an ensemble of weather forecasts instead of a single provider.  \nKeywords— Probabilistic forecasting, gradient boosting trees, offshore wind farms  \nI. INTRODUCTION  \nOver the past two decades, the annual growth rate of renewable energy capacity has continued to increase, significantly reducing fossil fuel consumption and global emissions [36] . Nonetheless, the intermittent nature of renewable energy sources poses additional challenges and costs for the power system [29, 62] . Enhancing production forecasts is critical to mitigate these issues and facilitate the continued integration of renewable energy sources into the grid. The importance of this subject is also highlighted by the extensive body of research produced over the past fifty years [32] . Depending on the operational context, these forecasts may require different look-ahead horizons or granularity. Day-ahead forecasts, for example, can be used to bid on the day-ahead market [49, 26, 12] or to determine a unit commitment schedule [34, 33] . Intra-hour forecasts, on the other hand, can help maintain grid stability in real-time [65, 1] . Furthermore, these forecasts can be either point forecasts, which estimate the conditional mean, or probabilistic forecasts, which capture the entire con-  \nditional probability distribution. The widespread recognition in the literature that weather variables should be modelled as stochastic processes (see, for example,[2, 48]) has shifted the field towards the latter approach [58] .  \nThis work studies probabilistic day-ahead forecasting of wind power generation in the context of offshore wind farms. Nonetheless, the presented methodology can also be applied to different renewable energy sources or forecast horizons. Typically, Numerical Weather Predictions (NWPs) are the most important input for day-ahead forecasting, and statistical or machine learning models are employed to learn the relationship between weather forecasts and power output [21] . The primary advantage of data-driven techniques lies in their ability to adapt wind forecasts to site-specific conditions and mitigate meteorological errors. This is particularly important in the context of day-ahead forecasting, since weather forecasts typically present a high degree of uncertainty ","cbCaihrPK8Gzm6uD","https://ap.wps.com/l/cbCaihrPK8Gzm6uD","pdf",1788928,1,13,"English","en",105,"# Introduction\n## Forecasting needs and horizons\n## Point vs probabilistic forecasts\n## Weather inputs and error sources\n## Tree based probabilistic modeling approach","[{\"question\":\"What problem does the paper address in wind power forecasting?\",\"answer\":\"It targets improving wind power production forecasts to better support renewable integration into the power grid, focusing specifically on probabilistic day-ahead forecasting for offshore wind farms.\"},{\"question\":\"Which probabilistic methods are compared in the study?\",\"answer\":\"The paper compares conformalized quantile regression, natural gradient boosting, and conditional diffusion models, and shows how these can be combined with tree-based machine learning.\"},{\"question\":\"How do weather ensembles and tree-based models affect forecasting accuracy?\",\"answer\":\"Tree-based models significantly reduce mean absolute error versus deterministic baselines, and all three probabilistic methods improve probabilistic skill over a Gaussian process baseline; using an ensemble of weather forecasts instead of a single provider improves point forecast accuracy by 17% on average.\"}]",1784204126,33,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"probabilistic-wind-power-forecasting-with-tree-based-machine-learning-and-weather-ensembles","",{"@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/probabilistic-wind-power-forecasting-with-tree-based-machine-learning-and-weather-ensembles/85517/",4,{"url":51,"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":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",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 problem does the paper address in wind power forecasting?","Question",{"text":74,"@type":75},"It targets improving wind power production forecasts to better support renewable integration into the power grid, focusing specifically on probabilistic day-ahead forecasting for offshore wind farms.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"Which probabilistic methods are compared in the study?",{"text":79,"@type":75},"The paper compares conformalized quantile regression, natural gradient boosting, and conditional diffusion models, and shows how these can be combined with tree-based machine learning.",{"name":81,"@type":72,"acceptedAnswer":82},"How do weather ensembles and tree-based models affect forecasting accuracy?",{"text":83,"@type":75},"Tree-based models significantly reduce mean absolute error versus deterministic baselines, and all three probabilistic methods improve probabilistic skill over a Gaussian process baseline; using an ensemble of weather forecasts instead of a single provider improves point forecast accuracy by 17% on average.","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":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"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":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]