Journal of Research in Environmental Health

Journal of Research in Environmental Health

Estimation of Solar Radiation Using Statistical Methods and Artificial Neural Network (Case Study-Tehran Synoptic Station)

Document Type : Research article

Authors
Amir Zarei 1
Sirvan Zarei 2
Seyyed Erfan Momenpour 3
Mohamad Reza Golanbaryan 4
Abass Solimanpor 5
1 Ph.D Student, Department of GIS & RS, Facuity of Earth sciences, Shahid Beheshti University,Tehran, Iran
2 MSc, Department of Health, Safety and Environment (HSE), Workplace Health Promotion Research Center,School of Public Health and Safety,Shahid Beheshti University of Medical Scienses,Tehran,Iran
3 Ph. D. Student , Department of Climatology, Faculty of Geography, University of Tehran, Tehran,Iran
4 MSc Student, Department of Hydraulic Structures ,Faculty of Civil Engineering, University of Maragheh, Iran
5 MSc, Department of Watershed Engineering, Faculty of Natural Resources, Isfahan University of Technology, Isfahan, Iran
10.22038/jreh.2025.82332.1683
Abstract
Background and purpose: Solar radiation is one of the important and influential parameters in agricultural hydrology and meteorology studies. According to the purpose of the research, which is to predict the amount of solar radiation, the type of research can be considered user . 

Materials and Methods: The statistical year in question is for one year (from the first of Farudin 1402 to the end of Farudin 1403) and the data used are the daily data of Tehran synoptic station. It includes the maximum and minimum temperature, maximum and minimum relative humidity and maximum wind speed (5 cases) and PM10 data (PM2.5 from Tehran city pollution measurement station). Correlation relationship between solar radiation as a dependent variable and other parameters (independent components) was done through Pearson's correlation coefficient in SPSS.26 software.

Results: and the results showed that solar radiation with minimum and maximum temperature, maximum wind speed, and PM10 have a direct correlation with maximum and minimum relative humidity, wind direction and PM2.5 have an inverse correlation. The estimation of solar radiation has been done using multiple linear regression and artificial neural network (MLP) methods, with a coefficient of determination (R2) of nearly 87% that performs better than the other two methods. (Enter and Stepwise)

Conclusion: Also, the comparison of the training and test period of the model shows that the ANN method with the mean square error (MSE) of megajoules per square meter per day, the absolute value of the error is 82.02 and the explanation coefficient is 88.0 in the test phase and 1.87 megajoules respectively. 35.86 and 81.0 Joules per square centimeter per day in the training phase of the models have performed better than other models in estimating solar radiation.
 
Open Access Policy: This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited. To view a copy of this licence, visit https://creativecommons.org/licenses/by/4.0/
Keywords
Solar Radiation
Meteorological Parameters
Multiple linear Regression
Artificial Neural Network
  1. Layeghi, M. 2019. Solar energy, technologies and applications. Jahad daneshgahi publication. (Persian).
  2. Zohoori M., (2012): Exploiting Renewable Energy Sources in Iran. Interdisciplinary J. of Contemporary Research in Business ,4, pp:849-862.
  3. Solangi K.H., M.R. Islam, R. Saidur, N.A. Rahim and H. Fayaz, (2011): A review on global solar energy policy. Renewable and Sustainable Energy Reviews, 15, pp: 2149-2163. https://doi.org/10.1016/j.rser.2011.01.007
  4. Shaddel, M., Javan, D.S., Baghernia, P., 2019. Estimation of hourly global solar irradiation on tilted absorbers from horizontal one using Artificial Neural Network for case study of Mashhad. Renew. Sustain. Energy Rev. 53, 59e67. https://doi.org/10.1016/j.rser.2015.08.023
  5. Abdelhafidi, N., Bachari, N.E.I. and Abdelhafidi, Z., 2021. Estimation of solar radiation using stepwise multiple linear regression with principal component analysis in Algeria. Meteorology and Atmospheric Physics, 133(2), pp.205-216. and hydroclimatic model validation. Water and Resources Research, 35(1), 233-241 https://doi.org/10.1007/s00703-020-00739-0
  6. Rahimikhoob A. 2020. Estimating global solar radiation using artificial neural network and air temperature data in a semi-arid environment. Renew. Energy. 35, 2131-2135. https://doi.org/10.1016/j.renene.2010.01.029
  7. Hunt, L.A., Kuchar, L., Swanton, C.J., 2018. Estimation of solar radiation for use in crop modeling. Agric. Meteorol. 91, 293-300. https://doi.org/10.1016/S0168-1923(98)00055-0
  8. Sabziparvar A.A., and Shetaee H. 2019. Estimation of global solar radiation in arid and semi-arid climates of East and West Iran, Energy 32: 649-655. https://doi.org/10.1016/j.energy.2006.05.005
  9. Yadav, A. K. and Chandel, S. S. (2019). Solar energy potential assessment of western Himalayan Indian state of Himachal Pradesh using J48 algorithm of WEKA in ANN based prediction model. Renewable Energy, 75, 675- 693. https://doi.org/10.1016/j.renene.2014.10.046
  10. Mehdizadeh, S., Behmanesh, J. and Khalili, K., 2018. Comparison of artificial intelligence methods and empirical equations to estimate daily solar radiation. Journal of Atmospheric and Solar-Terrestrial Physics, 146, pp.215-227. https://doi.org/10.1016/j.jastp.2016.06.006
  11. Okundamiya MS, Emagbetere JO, Ogujor EA (2021) Evaluation of various global solar radiation models for Nigeria. Int J Green Energy 13(5):505-512. https://doi.org/10.1080/15435075.2014.968921
  12. Olalekan, S., Abdullahi, M. I. and Olabisi, A. (2021). Modeling of Solar Radiation Using Artificial Neural Network for Renewable Energy Application. Journal of Applied Physics, 10(2), 6-12
  13. Meenal, R. and Selvakumar, A.I., 2022. Assessment of SVM, empirical and ANN based solar radiation prediction models with most influencing input parameters. Renewable Energy, 121, pp.324-343. https://doi.org/10.1016/j.renene.2017.12.005
  14. Radosevic, N., Duckham, M., Liu, G.J. and Sun, Q., 2021. Solar radiation modeling with KNIME and Solar Analyst: Increasing environmental model reproducibility using scientific workflows. Environmental Modelling & Software, 132, p.104780 https://doi.org/10.1016/j.envsoft.2020.104780
  15. Zeng J, Qiao W (2020) Short-term solar power prediction using a support vector machine. Renewable Energy 52:118-127. https://doi.org/10.1016/j.renene.2012.10.009
  16. Yadav, A. K. and Chandel, S. S. (2019). Solar energy potential assessment of western Himalayan Indian state of Himachal Pradesh using J48 algorithm of WEKA in ANN based prediction model. Renewable Energy, 75, 675- 693. https://doi.org/10.1016/j.renene.2014.10.046
  17. Ball RA, Purcell LC, Carey SK (2018) Evaluation of solar radiation prediction models in North America. Agronomy Journal 96:391-397 https://doi.org/10.2134/agronj2004.3910
  18. Belmahdi, B., Louzazni, M. and El Bouardi, A., 2022. One month-ahead forecasting of mean daily global solar radiation using time series models. Optik, 219, p.165207. https://doi.org/10.1016/j.ijleo.2020.165207
  19. Taki, M., Rohani, A. and Yildizhan, H., 2023. Application of machine learning for solar radiation modeling. Theoretical and Applied Climatology, 143(3-4), pp.1599-1613. https://doi.org/10.1007/s00704-020-03484-x
  20. Yang, H., Griffiths, P. R. and Tate, J. D. (2018). Comparison of partial least squares regression and multi-layer neural networks for quantification of nonlinear systems and application to gas phase Fourier transform infrared spectra. Analytica Chimica Acta, 489(2), 125-136. https://doi.org/10.1016/S0003-2670(03)00726-8
  21. Tabari, H., Grismer, M. E. and Trajkovic, S. (2019). Comparative analysis of 31 reference evapotranspiration methods under humid conditions. Irrigation Science, 31(2), 107-117. https://doi.org/10.1007/s00271-011-0295-z
  22. Nwokolo, S.C., Obiwulu, A.U., Ogbulezie, J.C. and Amadi, S.O., 2022. Hybridization of statistical machine learning and numerical models for improving beam, diffuse and global solar radiation prediction. Cleaner Engineering and Technology, 9, p.100529. https://doi.org/10.1016/j.clet.2022.100529
  23. Soltani-Gerdefaramarzi, S. (2023). Prediction of solar radiation intensity in Yazd station by using regression model based on principal components (PCR). Journal of Agricultural Meteorology, 11(1), 6-16. doi: 10.22125/agmj.2023.352446.1140.
  24. Jahantigh, N., & Piri, J. (2023). Estimation of solar radiation in different climates of Iran using hybrid machine learning methods. Journal Of Applied and Computational Sciences in Mechanics, 35(2), 37-54. doi: 10.22067/jacsm.2022.79378.1144.
  25. Rehman, S., Mohandes, M., 2018. Artificial neural network estimation of global solar radiation using air temperature and relative humidity. Energy Policy 36, 571-576 https://doi.org/10.1016/j.enpol.2007.09.033
  26. Razi, M. A. and Athappilly, K. (2021). A comparative predictive analysis of neural networks (NNs), nonlinear regression and classification and regression tree (CART) models. Expert Systems with Applications, 29(1), 65-74. https://doi.org/10.1016/j.eswa.2005.01.006
  27. Legates D. R. and Mc Cabe Jr. G. J. (2017). Evaluating the use of goodness-of-fit measures in hydrologic
  28. Mohammadi B, Emamgholizadeh S. Using principal component analysis to inputs the effective rainfall estimates based on entries to help support vector machine and artificial neural network. Journal of Rainwater Catchment Systems 2017; 4 (4):67-75.