[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121104-en":3,"doc-seo-121104-105":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},121104,8796095461564,"Liam","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Prediction of Hourly Wind Speed Time Series at Unsampled Locations Using Machine Learning","Various models for wind speed mapping have been advanced, with growing focus on wind speed distribution. This study extends mapping methods to predict hourly wind speed time series at locations without direct measurements. A quantile mapping (QM) based approach is compared with a traditional and machine-learning interpolation model. ERA5 reanalysis inputs are used to capture local orographic effects and large-scale wind fields, while GWA bias-correction is used for comparison. Results show QM and machine learning models using ERA5 outperform GWA in time series correlation and probability distribution, despite higher computation.","1 Prediction of hourly wind speed time series at unsampled  \n2 locations using machine learning  \n3  \n4  \n5 Freddy Houndekindo 1*, Taha B.M.J. Ouarda 1  \n6  \n7 1Canada Research Chair in Statistical Hydro-Climatology, Institut national de la recherche  \n8 scientifique, Centre Eau Terre Environnement, INRS-ETE, 490 de la Couronne, Québec, QC, 9 G1K 9A9, Canada  \n10  \n11  \n12  \n13  \n14  \n15  \n16 *Corresponding author: Freddy Houndekindo  \n17 490, Couronne street, Québec, QC, G1K 9A9, Canada  \n18 Tel: +1 418-654-3842  \n19 E-mail: [freddy.houndekindo@inrs.ca](freddy.houndekindo@inrs.ca)[ ](freddy.houndekindo@inrs.ca)20  \n21  \n22 Abbreviations  \na.g.l CDF  \nDEMECCC ERA5-WSQ GWA GWA-ERA5 IAV  \nIDW LGBM  \nLGBMQR  \nLGBMSI  \nLGBMSI-ERA5  \nLGMBQR-ERA5  \nMAE ME MRMR OP PC PD QM  \nQM-ERA5  \nQR R2  \nRCov RFSIRMSETS  \nWDC  \nWRAWSWSD WSNEP WSQ WSTS  \nAbove ground level Cumulative distribution function Digital elevation model  \nEnvironment and Climate Change Canada  \nWind speed quantiles extracted from the ERA5 dataset (m/s) Global wind atlas  \nBias-corrected ERA5 using GWA (m/s) Interannual variability  \nInverse distance weighting Light gradient-boosting machine Lightgbm for quantile regression LGBM for spatial interpolation  \nLGBMSI using the ERA5 wind data as covariates LGBMQR using ERA5-WSQ as covariates Mean absolute error (m/s)  \nMean error (m/s)  \nMinimum redundancy maximum relevancy algorithm Overlap percentage (%)  \nPearson correlation Probability distribution Quantile mapping  \nQuantile mapping bias correction of ERA5 wind data  \nQuantile regression  \nCoefficient of determination  \nRobust coefficient of variation Random forest for spatial interpolation Root-mean-squared error (m/s)  \ntime series  \nWind Duration Curve method  \nWind resource assessment  \nWind speed  \nWind speed distribution  \nWind speed non-exceedance probabilities  \nWind speed quantiles  \nWind speed time series  \n23  \n24  \n25 Abstract  \n26 Various models for wind speed mapping have been developed, with increasing attention on models  \n27 focusing on mapping wind speed distribution. This study extends these models to predict hourly  \n28 wind speed time series at unsampled locations. A model based on the quantile mapping (QM)  \n29 procedure was compared to a traditional and machine-learning model to interpolate wind speed  \n30 spatially. These proposed models were also used with inputs from the ERA5 reanalysis dataset, 31 enabling them to consider local variation in orography and large-scale wind fields. A widely used  \n32 procedure for mean bias correction of reanalysis based on the Global Wind Atlas (GWA) was  \n33 implemented and compared to the proposed models. It was found that the QM and machine learning  \n34 model, both using input from ERA5, significantly outperformed GWA bias correction in terms of  \n35 time series correlation and probability distribution. Despite being more computationally intensive  \n36 than GWA bias correction, both models are recommended due to their significantly (in a statistical  \n37 sense) superior performance.  \n38 Keywords: Bias-correction, ERA5, Light gradient-boosting machine, Quantile regression, 39 Reanalysis, Wind resource assessment  \n40  \n41 1. Introduction  \n42 The past decades have witnessed a significant uptake of wind energy in various parts of the world  \n43 [1] . This growth reflects a global shift toward more renewable energy sources, with wind power  \n44 playing a prominent role in energy supply [2] . The intermittent nature of wind speed still poses  \n45 some challenges to the development of the renewable energy source [3] . Due to the cubic  \n46 relationship between wind speed and power output, inaccuracies in estimating wind speed are  \n47 amplified when estimating the energy production, leading to suboptimal design of wind energy  \n48 infrastructure and jeopardizing the profitability and sustainability of the project [4] .  \n49 Prospective studies to evaluate the wind resource across a large region at a high spatial ","cbCaiiZOv0i3rf5d","https://ap.wps.com/l/cbCaiiZOv0i3rf5d","pdf",1625476,1,35,"English","en",105,"# 1. Introduction\n## Wind energy relevance and challenges\n## Wind resource assessment data sources\n## Role of reanalysis datasets (ERA5, MERRA-2)\n## Limitations of direct reanalysis application","[{\"question\":\"What problem does the study address?\",\"answer\":\"The study addresses the challenge of predicting hourly wind speed time series at locations where in-situ measurements are not available.\"},{\"question\":\"Which modeling approaches are compared?\",\"answer\":\"It compares a quantile mapping (QM) model with a traditional and a machine-learning model for spatial interpolation, and also benchmarks against bias correction using the Global Wind Atlas (GWA).\"},{\"question\":\"How do the proposed methods perform against GWA bias correction?\",\"answer\":\"Using ERA5 inputs, the QM and machine-learning models significantly outperform GWA bias correction in terms of time series correlation and probability distribution, though they require more computation.\"}]","Prediction of Hourly Wind Speed Time Series at Unsampled Locations Using Machine Learning | PDF",1785733752,88,{"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},"prediction-of-hourly-wind-speed-time-series-at-unsampled-locations-using-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/prediction-of-hourly-wind-speed-time-series-at-unsampled-locations-using-machine-learning/121104/",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","2026-08-03",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},"What problem does the study address?","Question",{"text":75,"@type":76},"The study addresses the challenge of predicting hourly wind speed time series at locations where in-situ measurements are not available.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which modeling approaches are compared?",{"text":80,"@type":76},"It compares a quantile mapping (QM) model with a traditional and a machine-learning model for spatial interpolation, and also benchmarks against bias correction using the Global Wind Atlas (GWA).",{"name":82,"@type":73,"acceptedAnswer":83},"How do the proposed methods perform against GWA bias correction?",{"text":84,"@type":76},"Using ERA5 inputs, the QM and machine-learning models significantly outperform GWA bias correction in terms of time series correlation and probability distribution, though they require more computation.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]