{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T10:56:42Z","timestamp":1780657002530,"version":"3.54.1"},"reference-count":30,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T00:00:00Z","timestamp":1753574400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Bourgogne-Franche-Comt\u00e9 Region","award":["ANR-17-EURE-0002"],"award-info":[{"award-number":["ANR-17-EURE-0002"]}]},{"name":"EIPHI Graduate School","award":["ANR-17-EURE-0002"],"award-info":[{"award-number":["ANR-17-EURE-0002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Future Internet"],"abstract":"<jats:p>Photovoltaic panels have become a promising solution for generating renewable energy and reducing our reliance on fossil fuels by capturing solar energy and converting it into electricity. The effectiveness of this conversion depends on several factors, such as the quality of the solar panels and the amount of solar radiation received in a specific region. This makes accurate solar irradiance forecasting essential for planning and managing efficient solar power systems. This study examines the application of machine learning (ML) models for accurately predicting global horizontal irradiance (GHI) using a three-year dataset from six distinct photovoltaic stations: NELHA, ULL, HSU, RaZON+, UNLV, and NWTC. The primary aim is to identify optimal shared features for GHI prediction across multiple sites using a 30 min time shift based on autocorrelation analysis. Key features identified for accurate GHI prediction include direct normal irradiance (DNI), diffuse horizontal irradiance (DHI), and solar panel temperatures. The predictions were performed using tree-based algorithms and ensemble learners, achieving R2 values exceeding 95% at most stations, with NWTC reaching 99%. Gradient Boosting Regression (GBR) performed best at NELHA, NWTC, and RaZON, while Multi-Layer Perceptron (MLP) excelled at ULL and UNLV. CatBoost was optimal for HSU. The impact of time-shifting values on performance was also examined, revealing that larger shifts led to performance deterioration, though MLP performed well under these conditions. The study further proposes a stacking ensemble approach to enhance model generalizability, integrating the strengths of various models for more robust GHI prediction.<\/jats:p>","DOI":"10.3390\/fi17080336","type":"journal-article","created":{"date-parts":[[2025,7,28]],"date-time":"2025-07-28T08:51:33Z","timestamp":1753692693000},"page":"336","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Efficient Machine Learning-Based Prediction of Solar Irradiance Using Multi-Site Data"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2589-5053","authenticated-orcid":false,"given":"Hassan N.","family":"Noura","sequence":"first","affiliation":[{"name":"Institut FEMTO-ST, CNRS, IUT-NFC, Universit\u00e9 Marie et Louis Pasteur, F-90000 Belfort, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zaid","family":"Allal","sequence":"additional","affiliation":[{"name":"LISTIC, Polytech Annecy-Chamb\u00e9ry, Universit\u00e9 Savoie Mont Blanc, 74944 Annecy Cedex, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1011-8665","authenticated-orcid":false,"given":"Ola","family":"Salman","sequence":"additional","affiliation":[{"name":"DeepVu, Berkeley, CA 94704, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3100-1869","authenticated-orcid":false,"given":"Khaled","family":"Chahine","sequence":"additional","affiliation":[{"name":"College of Engineering and Technology, American University of the Middle East, Egaila 54200, Kuwait"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,7,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"100015-61","DOI":"10.59717\/j.xinn-geo.2023.100015","article-title":"Climate change: Strategies for mitigation and adaptation","volume":"1","author":"Wang","year":"2023","journal-title":"Innov. Geosci."},{"key":"ref_2","first-page":"2","article-title":"Paris agreement","volume":"Volume 4","author":"Agreement","year":"2015","journal-title":"Report of the Conference of the Parties to the United Nations Framework Convention on Climate Change (21st Session, 2015: Paris)"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/j.rser.2013.06.042","article-title":"Review of solar irradiance forecasting methods and a proposition for small-scale insular grids","volume":"27","author":"Diagne","year":"2013","journal-title":"Renew. Sustain. Energy Rev."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"100453","DOI":"10.1016\/j.prime.2024.100453","article-title":"Machine Learning Algorithms for Solar Irradiance Prediction: A Recent Comparative Study","volume":"7","author":"Allal","year":"2024","journal-title":"e-Prime-Adv. Electr. Eng. Electron. Energy"},{"key":"ref_5","first-page":"1873","article-title":"Reliable solar irradiance forecasting approach based on choquet integral and deep LSTMs","volume":"17","author":"Mahmoud","year":"2020","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1355","DOI":"10.3390\/en5051355","article-title":"Short-term solar irradiance forecasting model based on artificial neural network using statistical feature parameters","volume":"5","author":"Wang","year":"2012","journal-title":"Energies"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1006","DOI":"10.1016\/j.renene.2021.06.079","article-title":"Comparison of physical and machine learning models for estimating solar irradiance and photovoltaic power","volume":"178","author":"Ramadhan","year":"2021","journal-title":"Renew. Energy"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/j.renene.2022.07.136","article-title":"Deep learning and statistical methods for short-and long-term solar irradiance forecasting for Islamabad","volume":"198","author":"Haider","year":"2022","journal-title":"Renew. Energy"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1016\/j.solener.2017.11.049","article-title":"Short-term solar irradiance forecasting via satellite\/model coupling","volume":"168","author":"Miller","year":"2018","journal-title":"Sol. Energy"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1016\/j.solener.2022.03.017","article-title":"Statistical learning for NWP post-processing: A benchmark for solar irradiance forecasting","volume":"238","author":"Verbois","year":"2022","journal-title":"Sol. Energy"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1016\/j.renene.2020.01.092","article-title":"Solar irradiance forecasting models without on-site training measurements","volume":"152","author":"Zambrano","year":"2020","journal-title":"Renew. Energy"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"113075","DOI":"10.1016\/j.enconman.2020.113075","article-title":"A minutely solar irradiance forecasting method based on real-time sky image-irradiance mapping model","volume":"220","author":"Wang","year":"2020","journal-title":"Energy Convers. Manag."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1016\/j.renene.2017.08.061","article-title":"A novel soft computing model (Gaussian process regression with K-fold cross validation) for daily and monthly solar radiation forecasting (Part: I)","volume":"115","author":"Rohani","year":"2018","journal-title":"Renew. Energy"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"542","DOI":"10.1016\/j.renene.2015.12.069","article-title":"Machine learning for solar irradiance forecasting of photovoltaic system","volume":"90","author":"Li","year":"2016","journal-title":"Renew. Energy"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1016\/j.procs.2017.09.045","article-title":"Solar irradiance forecasting using deep neural networks","volume":"114","author":"Alzahrani","year":"2017","journal-title":"Procedia Comput. Sci."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"616","DOI":"10.1504\/IJGEI.2021.118932","article-title":"Prospects and roadmaps for harvesting solar thermal power in tropical Brunei Darussalam","volume":"43","author":"Yahya","year":"2021","journal-title":"Int. J. Glob. Energy Issues"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/j.solener.2015.01.024","article-title":"Real-time forecasting of solar irradiance ramps with smart image processing","volume":"114","author":"Chu","year":"2015","journal-title":"Sol. Energy"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"136848","DOI":"10.1016\/j.scitotenv.2020.136848","article-title":"Solar irradiance measurement instrumentation and power solar generation forecasting based on Artificial Neural Networks (ANN): A review of five years research trend","volume":"715","author":"Pazikadin","year":"2020","journal-title":"Sci. Total Environ."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"123285","DOI":"10.1016\/j.jclepro.2020.123285","article-title":"Extreme gradient boosting and deep neural network based ensemble learning approach to forecast hourly solar irradiance","volume":"279","author":"Kumari","year":"2021","journal-title":"J. Clean. Prod."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"10052","DOI":"10.1002\/er.6529","article-title":"Comparison of machine learning and deep learning algorithms for hourly global\/diffuse solar radiation predictions","volume":"46","author":"Bamisile","year":"2022","journal-title":"Int. J. Energy Res."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"122353","DOI":"10.1016\/j.jclepro.2020.122353","article-title":"Assessment of machine learning, time series, response surface methodology and empirical models in prediction of global solar radiation","volume":"277","year":"2020","journal-title":"J. Clean. Prod."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"12063","DOI":"10.1016\/j.egyr.2022.09.015","article-title":"Application of improved version of multi verse optimizer algorithm for modeling solar radiation","volume":"8","author":"Ikram","year":"2022","journal-title":"Energy Rep."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Husein, M., and Chung, I.Y. (2019). Day-ahead solar irradiance forecasting for microgrids using a long short-term memory recurrent neural network: A deep learning approach. Energies, 12.","DOI":"10.3390\/en12101856"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Sansine, V., Ortega, P., Hissel, D., and Hopuare, M. (2022). Solar Irradiance Probabilistic Forecasting Using Machine Learning, Metaheuristic Models and Numerical Weather Predictions. Sustainability, 14.","DOI":"10.3390\/su142215260"},{"key":"ref_25","unstructured":"Measurement and Instrumentation Data Center (MIDC) (2024, July 19). MIDC Raw Data API Documentation, Available online: https:\/\/midcdmz.nrel.gov\/apps\/data_api_doc.pl?_idtextlist."},{"key":"ref_26","unstructured":"Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., and Dubourg, V. (2024, July 20). Scikit-Learn: Machine Learning in Python. Available online: https:\/\/scikit-learn.org\/stable\/."},{"key":"ref_27","first-page":"208","article-title":"The comparison of machine-learning methods XGBoost and LightGBM to predict energy development","volume":"Volume 23","author":"Nemeth","year":"2019","journal-title":"Proceedings of the Computational Statistics and Mathematical Modeling Methods in Intelligent Systems: Proceedings of 3rd Computational Methods in Systems and Software 2019"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"106584","DOI":"10.1016\/j.jobe.2023.106584","article-title":"Predicting the consumed heating energy at residential buildings using a combination of categorical boosting (CatBoost) and Meta heuristics algorithms","volume":"71","author":"Dasi","year":"2023","journal-title":"J. Build. Eng."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"103269","DOI":"10.1016\/j.scs.2021.103269","article-title":"Forecasting high penetration of solar and wind power in the smart grid environment using robust ensemble learning approach for large-dimensional data","volume":"75","author":"Ahmad","year":"2021","journal-title":"Sustain. Cities Soc."},{"key":"ref_30","unstructured":"Lundberg, S.M., and Lee, S.I. (2024, July 30). SHAP (SHapley Additive exPlanations). Available online: https:\/\/shap.readthedocs.io\/en\/latest\/."}],"container-title":["Future Internet"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-5903\/17\/8\/336\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:16:55Z","timestamp":1760033815000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-5903\/17\/8\/336"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,27]]},"references-count":30,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["fi17080336"],"URL":"https:\/\/doi.org\/10.3390\/fi17080336","relation":{},"ISSN":["1999-5903"],"issn-type":[{"value":"1999-5903","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,27]]}}}