Machine Learning – Based Prediction of Daily Global Solar Radiation Using Local Meteorological Observations

Öz

This study aims to predict the daily total global solar irradiance (GHI) utilizing machine learning methods using meteorological indicators such as relative humidity (RH), wind speed (WS), temperature (TE), atmospheric pressure (AP), sunshine duration (SD) measured daily between 2015 and 2022 at the station within the Hakkari Provincial Directorate of Meteorology. Solar irradiance prediction is of great importance, especially in terms of determination of the solar energy potential, photovoltaic (PV) system performance analysis, and energy planning. In this context, Extreme Gradient Boosting (XGBoost), random forest (RF), support vector regression (SVR), linear regression (LR) algorithms were applied, and the prediction successes of the models were compared using coefficient of determination (R²), mean absolute error (MAE), root mean square error (RMSE), and correlation coefficient (R) performance criteria. The findings denoted that SD, TE and AP were the most effective determinants of daily solar radiation. Furthermore, among the four different algorithms used in the GHI estimation study, the SVR model was found to exhibit superior performance compared to the other models, with R²=0.703, RMSE=1.381, MAE=0.983, and R=0.838. In the LR model, R² was calculated as 0.685, RMSE as 1.422, MAE as 1.082, and R as 0.827. The RF and XGBoost algorithms, respectively, showed similar performance with R²=0.654, RMSE=1.491, MAE=1.061, R=0.808 and R²=0.646, RMSE=1.509, MAE=1.094, R=0.803. The findings demonstrate that, despite Hakkari's high altitude and variable climate conditions, reliable and cost-effective solar radiation prediction models can be developed using local meteorological data, making significant contributions to renewable energy applications.

Anahtar Kelimeler

• Solar Radiation
• Machine Learning
• Meteorological Data
• Prediction

Yerel Meteorolojik Gözlemler Kullanılarak Günlük Küresel Güneş Radyasyonunun Makine Öğrenmesine Dayalı Tahmini

Öz

Bu çalışmada, Hakkâri ili meteoroloji il müdürlüğü bünyesinde bulunan istasyondan 2015–2022 yılları arasında günlük olarak ölçülen bağıl nem (RH), rüzgâr hızı (WS), sıcaklık (TE), atmosfer basıncı (AP), güneşlenme süresi (SD) gibi meteorolojik göstergeler kullanılarak, günlük toplam küresel güneş radyasyonunun (GHI) makine öğrenmesi yöntemleri ile tahmin edilmesi amaçlanmıştır. Güneş radyasyonu tahmini, özellikle güneş enerjisi potansiyelinin belirlenmesi, fotovoltaik (PV) sistem performans analizleri ve enerji planlaması açısından büyük bir öneme sahiptir. Bu kapsamda, Extreme Gradient Boosting (XGBoost), rastgele orman (RF), destek vektör regresyonu (SVR), doğrusal regresyon (LR) algoritmaları uygulanmış; modellerin tahmin başarıları coefficient of determination (R²), mean absolute error (MAE), root mean square error (RMSE) ve correlation coefficient (R) performans kriterleri ile karşılaştırılmıştır. Sonuçlar, SD, TE ve AP’nin günlük güneş radyasyonunun en etkili belirleyicileri olduğunu göstermiştir. Ayrıca GHI tahmin çalışmasında kullanılan dört farklı algoritma arasından SVR modelinin R²=0.703, RMSE=1.381, MAE=0.983 ve R=0.838 ile diğer modellere kıyasla daha üstün performans sergilediği belirlenmiştir. LR modelinde R²=0.685, RMSE=1.422, MAE=1.082 ve R=0.827 olarak hesaplanmıştır. RF ve XGBoost algoritmaları ile sırasıyla hesaplanan R²=0.654, RMSE=1.491, MAE=1.061, R=0.808 ve R²=0.646, RMSE=1.509, MAE=1.094, R=0.803 değerleri birbirine yakın performans göstermiştir. Elde edilen bulgular, Hakkâri’nin yüksek rakımlı ve değişken iklim koşullarına rağmen yerel meteorolojik verilerin kullanılmasıyla güvenilir ve düşük maliyetli güneş radyasyonu tahmin modellerinin geliştirilebileceğini ortaya koymakta ve yenilenebilir enerji uygulamalarına önemli katkılar sunmaktadır.

Anahtar Kelimeler

• Güneş Radyasyonu
• Makine Öğrenme
• Meteorolojik Veri
• Tahmin

Kaynakça

1. [1] Sri Revathi B. A survey on advanced machine learning and deep learning techniques assisting in renewable energy generation. Environmental Science and Pollution Research. 2023; 30: 93407–93421.
2. [2] Gürel AE, Ağbulut Ü, Bakır H, Ergün A, Yıldız G. A state of art review on estimation of solar radiation with various models. Heliyon. 2023; 9(2): e13167.
3. [3] Dobruna L, Berisha A. A Data-Driven Approach for Predicting Solar Energy Production Using Machine Learning Techniques. In 2025 MIPRO 48th ICT and Electronics Convention. 2025; 180–185.
4. [4] Vanlalchhuanawmi C, Deb S, Islam MM, Ustun TS. Solar radiation prediction: A multi-model machine learning and deep learning approach. AIP Advances. 2025; 15(5): 055201.
5. [5] Sehrawat N, Vashisht S, Singh A. Solar irradiance forecasting models using machine learning techniques and digital twin: A case study with comparison. International Journal of Intelligent Networks. 2023; 4: 90–102.
6. [6] Obiora CN, Ali A, Hasan AN. Implementing extreme gradient boosting (XGBoost) algorithm in predicting solar irradiance. In 2021 IEEE PES/IAS PowerAfrica. 2021; 1–5.
7. [7] Qiu R, Liu C, Cui N, Gao Y, Li L, Wu Z, Jiang S, Hu M. Generalized Extreme Gradient Boosting model for predicting daily global solar radiation for locations without historical data. Energy Conversion and Management. 2022; 258: 115488.
8. [8] Kumar M, Namrata K, Kumar N. Data-driven hyperparameter optimized extreme gradient boosting machine learning model for solar radiation forecasting. Advances in Electrical & Electronic Engineering, 2022; 20(4): 549–559.

9. [9] Bouzgou H, Gueymard CA. Fast short-term global solar irradiance forecasting with wrapper mutual information. Renewable Energy. 2019; 133: 1055–1065.
10. [10] Soltani-Gerdefaramarzi S, Askarizadeh M. Application of Entropy Theory and Principal Component Analysis to Determine Input Variables for Estimating Solar Radiation using Machine Learning Algorithms. Physical Geography Research. 2024; 56(4): 73–87.
11. [11] Irfan M, Shaf A, Ali T, Zafar M, AlThobiani F, Almas MA, Almawgani AH. Global horizontal irradiance prediction for renewable energy system in Najran and Riyadh. AIP Advances. 2024; 14(3): 035137.
12. [12] Husain S, Khan UA. Development of machine learning models based on air temperature for estimation of global solar radiation in India. Environmental Progress & Sustainable Energy. 2022; 41(4): e13782.
13. [13] Güzel B, Sevli O, Okatan E. Forecasting solar radiation based on meteorological data using machine learning techniques: A case study of Isparta. International Journal of Engineering Research and Development. 2023; 15(2): 704–713.
14. [14] Gupta R, Yadav AK, Jha SK, Pathak PK. A robust regressor model for estimating solar radiation using an ensemble stacking approach based on machine learning. International Journal of Green Energy. 2024; 21(8): 1853–1 873.
15. [15] Mugware FW, Ravele T, Sigauke C. Short-Term Predictions of Global Horizontal Irradiance Using Recurrent Neural Networks, Support Vector Regression, Gradient Boosting Random Forest and Advanced Stacking Ensemble Approaches. Computation. 2025; 13(3): 72.
16. [16] Hissou H, Benkirane S, Guezzaz A, Azrour M, Beni-Hssane A. A novel machine learning approach for solar radiation estimation. Sustainability. 2023; 15(13): 10609.
17. [17] Gaboitaolelwe J, Zungeru AM, Yahya A, Lebekwe CK, Vinod DN, Salau AO. Machine learning based solar photovoltaic power forecasting: A review and comparison. IEEE Access. 2023; 11: 40820–40845.
18. [18] TSMS. Turkish State Meteorological Service. https://www.mgm.gov.tr
19. [19] Song Z, Cao S, Yang H. An interpretable framework for modeling global solar radiation using tree-based ensemble machine learning and Shapley additive explanations methods. Applied Energy. 2024; 364: 123238.
20. [20] Wang H, Cai R, Zhou B, Aziz S, Qin B, Voropai N, Gan L, Barakhtenko E. Solar irradiance forecasting based on direct explainable neural network. Energy Conversion and Management. 2020; 226: 113487.
21. [21] Chiranjeevi M, Karlamangal S, Moger T, Jena D. Solar irradiation prediction hybrid framework using regularized convolutional BiLSTM-based autoencoder approach. IEEE Access. 2023; 11: 131362–131375.
22. [22] Li Q, Bessafi M, Li P. Mapping prediction of surface solar radiation with linear regression models: case study over reunion island. Atmosphere. 2023; 14(9): 1331.
23. [23] Rabehi A, Guermoui M, Lalmi D. Hybrid models for global solar radiation prediction: a case study. International Journal of Ambient Energy. 2020; 41(1): 31–40.
24. [24] Ramedani Z, Omid M, Keyhani A, Shamshirband S, Khoshnevisan B. Potential of radial basis function based support vector regression for global solar radiation prediction. Renewable and Sustainable Energy Reviews. 2014; 39: 1005–1011.
25. [25] Mohammadi K, Shamshirband S, Anisi MH, Alam KA, Petković D. Support vector regression based prediction of global solar radiation on a horizontal surface. Energy Conversion and Management. 2015; 91: 433–441.
26. [26] Karasu S, Altan A. Recognition model for solar radiation time series based on random forest with feature selection approach. In 2019 11th international conference on electrical and electronics engineering (ELECO). 2019; 8–11.
27. [27] Ibrahim IA, Khatib T. A novel hybrid model for hourly global solar radiation prediction using random forests technique and firefly algorithm. Energy Conversion and Management. 2017; 138: 413–425.
28. [28] Benali L, Notton G, Fouilloy A, Voyant C, Dizene R. Solar radiation forecasting using artificial neural network and random forest methods: Application to normal beam, horizontal diffuse and global components. Renewable Energy. 2019; 132: 871–884.
29. [29] Yan H, Yan K, Ji G. Optimization and prediction in the early design stage of office buildings using genetic and XGBoost algorithms. Building and Environment. 2022; 218: 109081.
30. [30] Zhang C, Zhang Y, Pu J, Liu Z, Wang Z, Wang L. An hourly solar radiation prediction model using eXtreme gradient boosting algorithm with the effect of fog-haze. Energy and Built Environment. 2025; 6(1): 18–26.
31. [31] Fan J, Wang X, Wu L, Zhou H, Zhang F, Yu X, Lu X, Xiang Y. Comparison of Support Vector Machine and Extreme Gradient Boosting for predicting daily global solar radiation using temperature and precipitation in humid subtropical climates: A case study in China. Energy Conversion and Management. 2018; 164: 102–111.
32. [32] Yuzer EO. Comparison of calculation methods and artificial neural network results in regional solar irradiation prediction. Electrical Engineering. 2025; 107(6): 7115–7135.
33. [33] Arslan G, Bayhan B, Yaman K. Mersin/Türkiye için Ölçülen Global Güneş Işınımının Yapay Sinir Ağları ile Tahmin Edilmesi ve Yaygın Işınım Modelleri ile Karşılaştırılması. Gazi University Journal of Science Part C: Design and Technology. 2019; 7(1): 80–96.
34. [34] Ertürk S, Kara H, Akkuş C, Genç G. Türkiye’de Farklı İklim Kuşakları İçin Yapay Sinir Ağları Kullanılarak Güneş Işınımının Tahmini. Gazi University Journal of Science Part C: Design and Technology. 2023; 11(4): 885–892.
35. [35] Uzun S, Arslantaş H. Determination of Radiation Value by Month Using Artificial Neural Network Model; Ankara, Sivas, Erzurum example. Gazi University Journal of Science Part C: Design and Technology. 2024; 12(1): 315–323.