[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128188-en":3,"doc-seo-128188-105":31,"detail-sidebar-cat-0-en-105":92},{"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":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128188,2336475104042,"Skyler","https://ap-avatar.wpscdn.com/avatar/22000c4c32af1715be0?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786537525561427321",8,"Research & Report","Machine-learning-based probabilistic forecasting of solar irradiance in Chile","Renewable electricity reached 63.4% of Chile’s total power demand by the end of 2023, driving rapid photovoltaic (PV) growth despite strong volatility in solar conditions. Integrating PV into the grid requires accurate short-term forecasts, motivating probabilistic modeling of solar irradiance rather than only deterministic values. Eight-member short-term ensemble forecasts for 2021 are generated with WRF, then calibrated using EMOS with a censored Gaussian distribution and a machine-learning-based distributional regression network (DRN). A neural-network post-processing variant further improves eight-member predictions. Results across 30 station sites show substantial gains in calibration and point accuracy, with corrected ensembles performing best overall and DRN generally surpassing EMOS.","Adv. Stat. Clim. Meteorol. Oceanogr., 11, 89–105, 2025 [https://doi.org/10.5194/ascmo-1](https://doi.org/10.5194/ascmo-1)1-89-2025 © Author(s) 2025 . This work is distributed under the Creative Commons Attribution 4 .0 License.  \nMachine-learning-based probabilistic forecasting of solar irradiance in Chile  \nSándor Baran 1 , Julio C. Marín2,3 , Omar Cuevas3,4 , Mailiu Díaz5 , Marianna Szabó 1 , Orietta Nicolis5 ,  \nand Mária Lakatos 1  \n1Faculty of Informatics, University of Debrecen, Debrecen, Hungary  \n2Department of Meteorology, University of Valparaíso, Valparaíso, Chile  \n3 Center for Atmospheric Studies and Climate Change (CEACC), University of Valparaíso, Valparaíso, Chile  \n4Institute of Physics and Astronomy, University of Valparaíso, Valparaíso, Chile  \n5Faculty of Engineering, Andrés Bello University, Viña del Mar, Chile Correspondence: Sándor Baran ([baran.sandor@inf.unideb.hu](baran.sandor@inf.unideb.hu))  \nReceived: 5 December 2024 – Revised: 1 March 2025 – Accepted: 22 March 2025 – Published: 11 June 2025  \nAbstract. By the end of 2023, renewable sources covered 63.4 % of the total electric-power demand of Chile, and, in line with the global trend, photovoltaic (PV) power showed the most dynamic increase. Although Chile's Atacama Desert is considered to be the sunniest place on Earth, PV power production, even in this area, can be highly volatile. Successful integration of PV energy into the country's power grid requires accurate short-term PV power forecasts, which can be obtained from predictions of solar irradiance and related weather quantities. Nowadays, in weather forecasting, the state-of-the-art approach is the use of ensemble forecasts based on multiple runs of numerical weather prediction models. However, ensemble forecasts still tend to be uncalibrated or biased, thus requiring some form of post-processing. The present work investigates probabilistic forecasts of solar irradiance for regions III and IV in Chile. For this reason, eight-member short-term ensemble forecasts of solar irradiance for the calendar year 2021 are generated using the Weather Research and Forecasting (WRF) model; these are then calibrated using the benchmark ensemble model output statistics (EMOS) method based on a censored Gaussian law and its machine-learning-based distributional regression network (DRN) counterpart. Furthermore, we also propose a neural-network-based post-processing method, resulting in improved eightmember ensemble predictions. All forecasts are evaluated against station observations for 30 locations in the study area, and the skill of post-processed predictions is compared to the raw WRF ensemble. Our case study confirms that all studied post-processing methods substantially improve both the calibration of probabilistic forecasts and the accuracy of point forecasts. Among the methods tested, the corrected ensemble exhibits the best overall performance. Additionally, the DRN model generally outperforms the corresponding EMOS approach.  \n1 Introduction  \nAccording to the latest report of the International Renewable Energy Agency (IRENA, 2024), the largest ever increase in renewable-power capacity was observed in 2023, nearly 75 % of which was newly installed solar energy. As a result, by the end of 2023, the renewable-energy share had reached 43 % of the global installed power capacity, and this ratio was even higher in South America (71.4 %) . In particular, renewable sources covered 63.4 % of the total electric-power de-  \nmand of Chile, 39.7 % of which came from photovoltaic (PV) energy. In line with the global trend, with the addition of 1949 MW, in 2023, PV power accounted for the most substantial increase of 30 .4 % .  \nAlthough Chile's Atacama Desert is considered to be the sunniest place on Earth, with the highest long-term solar irradiance (Rondanelli et al., 2015), PV power production can be highly volatile, which raises a strong demand for accurate PV power forecasts from power grid operators. A sta","cbCaifoIshKxDTa0","https://ap.wps.com/l/cbCaifoIshKxDTa0","pdf",2615713,2,1,17,"English","en",105,"# Introduction\n## Renewable energy and forecasting needs\n## Ensemble forecasts and post-processing approaches\n## Study focus and methods","[{\"question\":\"Why are probabilistic solar irradiance forecasts important for Chile’s power grid?\",\"answer\":\"PV production in Chile can be highly volatile, and accurate short-term forecasting is needed for reliable grid integration. Probabilistic forecasts based on solar irradiance support this requirement more effectively than uncalibrated deterministic outputs.\"},{\"question\":\"How are the probabilistic forecasts for solar irradiance generated in this study?\",\"answer\":\"The study creates eight-member short-term ensemble forecasts for 2021 using the WRF numerical weather prediction model. These ensemble outputs are then calibrated and post-processed using statistical and machine-learning methods.\"},{\"question\":\"Which post-processing methods are compared, and what is the overall best performer?\",\"answer\":\"The forecasts are calibrated using EMOS with a censored Gaussian law and a DRN machine-learning distributional regression approach. A neural-network-based post-processing method is also proposed; the corrected ensemble shows the best overall performance, and DRN generally outperforms EMOS.\"}]","Machine-learning-based probabilistic forecasting of solar irradiance in Chile | PDF",1785945398,43,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"machine-learning-based-probabilistic-forecasting-of-solar-irradiance-in-chile","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/machine-learning-based-probabilistic-forecasting-of-solar-irradiance-in-chile/128188/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-27","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why are probabilistic solar irradiance forecasts important for Chile’s power grid?","Question",{"text":76,"@type":77},"PV production in Chile can be highly volatile, and accurate short-term forecasting is needed for reliable grid integration. Probabilistic forecasts based on solar irradiance support this requirement more effectively than uncalibrated deterministic outputs.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How are the probabilistic forecasts for solar irradiance generated in this study?",{"text":81,"@type":77},"The study creates eight-member short-term ensemble forecasts for 2021 using the WRF numerical weather prediction model. These ensemble outputs are then calibrated and post-processed using statistical and machine-learning methods.",{"name":83,"@type":74,"acceptedAnswer":84},"Which post-processing methods are compared, and what is the overall best performer?",{"text":85,"@type":77},"The forecasts are calibrated using EMOS with a censored Gaussian law and a DRN machine-learning distributional regression approach. A neural-network-based post-processing method is also proposed; the corrected ensemble shows the best overall performance, and DRN generally outperforms EMOS.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]