[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119985-en":3,"doc-seo-119985-105":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},119985,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",8,"Research & Report","Solar Irradiance Forecasting with Natural Language Processing of Cloud Observations - Modified Shapley Additive Explanations","Forecasting solar power plant generation requires accurate consideration of meteorological parameters that link extraterrestrial solar irradiance to irradiance on tilted photovoltaic panels. Cloudiness is a major driver and can be represented not only as sky coverage percentage but also by cloud types, vertical-layer distribution, and cloud height. The work converts historical natural-language cloud records into a binary feature vector for machine learning, improving short-term solar irradiance forecasts by 5–15% depending on the quality metric. To address reduced interpretability from additional features, it applies an additive explanation method based on Shapley values to clarify why specific forecasts are produced, supporting trustworthy explainable AI for power-industry decision-making.","algorithms  \nArticle  \nSolar Irradiance Forecasting with Natural Language Processing of Cloud Observations and Interpretation of Results with Modified Shapley Additive Explanations  \nPavel V. Matrenin 1,2, *, Valeriy V. Gamaley 2, Alexandra I. Khalyasmaa 1 and Alina I. Stepanova 1  \nCitation: Matrenin, P.V.; Gamaley, V.V.; Khalyasmaa, A.I.; Stepanova, A.I. Solar Irradiance Forecasting with Natural Language Processing of Cloud Observations and Interpretation of Results with Modified Shapley Additive Explanations. Algorithms 2024, 17, 150 . [https://doi.org/10.3390/a17040150](https://doi.org/10.3390/a17040150)  \nAcademic Editors: Juvenal Rodriguez-Resendiz and José Manuel Álvarez-Alvarado  \nReceived: 5 March 2024  \nRevised: 31 March 2024  \nAccepted: 1 April 2024  \nPublished: 2 April 2024  \nCopyright: © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) .  \n1 Ural Power Engineering Institute, Ural Federal University Named after the First President of Russia  \nB.N. Yeltsin, 19 Mira Str., 620002 Yekaterinburg, Russia; [a.i.khaliasmaa@urfu.ru](a.i.khaliasmaa@urfu.ru) (A.I.K.); [a.i.stepanova@urfu.me](a.i.stepanova@urfu.me) (A.I.S.)  \n2 Faculty of Power Engineering, Novosibirsk State Technical University, 20 K. Marx Ave.,  \n630073 Novosibirsk, Russia; [gamaley1996@gmail.com](gamaley1996@gmail.com)  \n* [Correspondence: p.v.matrenin@urfu.ru](Correspondence: p.v.matrenin@urfu.ru)  \nAbstract: Forecasting the generation of solar power plants (SPPs) requires taking into account meteorological parameters that influence the difference between the solar irradiance at the top of the atmosphere calculated with high accuracy and the solar irradiance at the tilted plane of the solar panel on the Earth’s surface. One of the key factors is cloudiness, which can be presented not only asa percentage of the sky area covered by clouds but also many additional parameters, such as the typeof clouds, the distribution of clouds across atmospheric layers, and their height. The use of machine learning algorithms to forecast the generation of solar power plants requires retrospective data over a long period and formalising the features; however, retrospective data with detailed information about cloudiness are normally recorded in the natural language format. This paper proposes an algorithm for processing such records to convert them into a binary feature vector. Experiments conducted on data from a real solar power plant showed that this algorithm increases the accuracy of short-term solar irradiance forecasts by 5–15%, depending on the quality metric used. At the sametime, adding features makes the model less transparent to the user, which is a significant drawback from the point of view of explainable artificial intelligence. Therefore, the paper uses an additive explanation algorithm based on the Shapley vector to interpret the model’s output. It is shown that this approach allows the machine learning model to explain why it generates a particular forecast, which will provide a greater level of trust in intelligent information systems in the power industry.  \nKeywords: solar irradiance forecasting; photovoltaic power plant; distributed generation; machine learning; account meteorological parameters; data pre-processing; explainable artificial intelligence  \n1. Introduction  \nThe development of distributed generation (DG) is aimed at generating electrical energy near the point of its consumption and introducing energy sources with relatively low power and compact dimensions. Typically used are installations running on diesel or gas and renewable energy sources (RES) such as photovoltaic/solar power plants (SPP), wind power plants and mini-hydroelectric power plants.  \n","cbCairsWo0MRbgRP","https://ap.wps.com/l/cbCairsWo0MRbgRP","pdf",5410450,1,20,"English","en",105,"# Introduction\n## Distributed generation and forecasting challenges\n## Time-series forecasting approaches for renewable energy\n# Cloud data as a natural-language input\n# Proposed processing algorithm and binary feature vector\n# Explainable AI via modified Shapley additive explanations\n# Experimental results and discussion","[{\"question\":\"Why is cloudiness crucial for solar irradiance forecasting?\",\"answer\":\"Cloudiness strongly affects the difference between top-of-atmosphere irradiance and the irradiance incident on tilted PV panels. It can be described through coverage percentage as well as cloud type, vertical distribution, and height.\"},{\"question\":\"How does the paper handle natural-language cloud records?\",\"answer\":\"It proposes an algorithm that processes such records and converts them into a binary feature vector suitable for machine learning model input.\"},{\"question\":\"How is model interpretability addressed in this approach?\",\"answer\":\"Because adding features can reduce transparency, the study uses an additive explanation algorithm based on Shapley values to explain why the model outputs a particular forecast.\"}]","Solar Irradiance Forecasting with Natural Language Processing of Cloud Observations - Modified Shapley Additive Explanations | PDF",1785727479,50,{"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},"solar-irradiance-forecasting-with-natural-language-processing-of-cloud-observations-modified-shapley-additive-explanations","",{"@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/solar-irradiance-forecasting-with-natural-language-processing-of-cloud-observations-modified-shapley-additive-explanations/119985/",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},"Why is cloudiness crucial for solar irradiance forecasting?","Question",{"text":75,"@type":76},"Cloudiness strongly affects the difference between top-of-atmosphere irradiance and the irradiance incident on tilted PV panels. It can be described through coverage percentage as well as cloud type, vertical distribution, and height.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the paper handle natural-language cloud records?",{"text":80,"@type":76},"It proposes an algorithm that processes such records and converts them into a binary feature vector suitable for machine learning model input.",{"name":82,"@type":73,"acceptedAnswer":83},"How is model interpretability addressed in this approach?",{"text":84,"@type":76},"Because adding features can reduce transparency, the study uses an additive explanation algorithm based on Shapley values to explain why the model outputs a particular forecast.","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},[93,97,101,105,110,114,119,122,126,129,133],{"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":29,"slug":113},6,"Technology","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":21,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":127,"show_sort_weight":21,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":106,"slug":136},19,"General","general"]