Abstract
Solar radiation estimation is essential with increasing energy demands for industrial and agricultural purposes to create a cleaner environment, negotiate climate change impacts, and attain sustainable development. However, the maintenance and operation of solar radiation measurements are costly due to the lack of pyranometers or their failure; hence, obtaining reliable solar radiation data is challenging in many subtropical regions. Despite its importance, a few studies use machine learning algorithms for solar radiation estimation in Bangladesh. To this end, this study contributes to filling the gap twofold. First, we presented the potentials of ensemble models, such as Bagging-REPT (reduced error pruning tree), random forest (RF), and Bagging-RF, which were compared to three standalone models, namely, Gaussian process regression (GPR), artificial neural network (ANN), and support vector machine (SVM), for estimating daily global solar radiation in three Bangladeshi regions. Second, we explore the optimal input parameters influencing solar radiation change at the regional scale using a classification and regression tree (CART)-based feature selection tool. Satellite-derived ERA5 reanalysis and NASA POWER project datasets were used as input parameters. The performance of the models was compared using performance evaluation metrics like correlation coefficient (r), root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE), index of agreement (IA), and Taylor diagram. Results suggested that the RF model performed 5.47–37.22% better than the standalone models in estimating daily solar radiation at Chuadanga in terms of RMSE. Besides, the other ensemble model Bagging-RF showed 14.9–25.03% and 11.46–30.97% greater performances in Dinajpur and Satkhira than the conventional models in RMSE metric. Besides, this study may provide knowledge to the policymakers to make critical judgments on future energy yield, efficiency, productivity, and operation, which are essential elements for investments and solar energy conversion applications in the subtropical areas of the world.
Similar content being viewed by others
Data availability
Data will be available upon reasonable request from corresponding authors.
Code Availability
Code will be available upon reasonable request on corresponding authors.
References
Abdullah SS, Malek MA, Abdullah NS, Kisi O, Yap KS (2015) Extreme learning machines: a new approach for prediction of reference evapotranspiration. J Hydrol 527:184–195. https://doi.org/10.1016/j.jhydrol.2015.04.073
Abdullah-Al-Mahbub M, Islam ARMT, Alam E, Asha MR (2023) Sustainable solar energy potential on marine passenger ships of Bay of Bengal: a way of reducing carbon dioxide emissions and disaster risk reduction. Energy Explor Exploit. https://doi.org/10.1177/01445987231173097
Abedin Z, Barua M, Paul S, Akther S, Chowdhury R, Chowdhury SU, (2017) A model for prediction of monthly solar radiation of different meteorological locations of Bangladesh using aritficial neural network data mining tool. International Conference on Electrical, Computer and Communication Engineering (ECCE), pp. 692-697. https://doi.org/10.1109/ECACE.2017.7912993
Ağbulut Ü, Gürel AE, Biçen Y (2021) Prediction of daily global solar radiation using different machine learning algorithms: evaluation and comparison. Renew Sustain Energy Rev 135. https://doi.org/10.1016/j.rser.2020.110114
Alam MS, Al-Ismail FS, Hossain MS, Rahman SM (2023) Ensemble machine-learning models for accurate prediction of solar irradiation in Bangladesh. Processes 11(3):908. https://doi.org/10.3390/pr11030908
Al-Rousan N, Al-Najjar H, Alomari O (2021) Assessment of predicting hourly global solar radiation in Jordan based on Rules, Trees, Meta, Lazy and Function prediction methods. Sustain Energy Technol Assess 44. https://doi.org/10.1016/j.seta.2020.100923
Angstrom A (1924) Solar and terrestrial radiation. Quart J Roy Met Soc 50:121–125. https://doi.org/10.1002/qj.49705021008
Azad MAK, Islam ARMT, Rahman MS, Ayen K (2021) Development of novel hybrid machine learning models for monthly thunderstorm frequency prediction over Bangladesh. Natural Hazards 108(1):1109–1135. https://doi.org/10.1007/s11069-021-04722-9
Baptista D, Morgado-Dias F (2012) Comparing different implementations for the Levenberg-Marquardt algorithm, 10th Portuguese Conference on Automatic Control e CONTROLO'12, Funchal, Madeira Island, July 16th to 18th, 2012
Bellido-Jiménez JA, Estévez J, García-Marín AP (2021) Assessing neural network approaches for solar radiation estimates using limited climatic data in the mediterranean sea. Environ Sci Proc 4:19. https://doi.org/10.3390/ecas2020-08116
Benghanem M, Mellit A (2010) Radial Basis Function Network-based prediction of global solar radiation data: application for sizing of a standalone photovoltaic system at Al-Madinah, Saudi Arabia. Energy 35(9):3751–3762. https://doi.org/10.1016/j.energy.2010.05.024
Bittencourt HR, Clarke RT (2004) Feature selection by using classification and regression trees (CART). In Proceedings of the 20th ISPRS Congress, Istanbul, Turkey, 12–23 July 2004; Volume XXXV. Commission, 7
Boateng EB, Pillay M, Davis P (2019) Predicting the level of safety performance using an artificial neural network. In: Ahram T, Karwowski W, Taiar R (eds) Human systems engineering and design. Advances in intelligent systems and computing. Springer, Cham, pp 705–710. https://doi.org/10.1007/978-3-030-02053-8_107
Boser BE, Guyon IM, Vapnik VN (1992) A training algorithm for optimal margin classifiers. Proceedings of the 5th Annual Workshop on Computational Learning Theory (COLT'92), Pittsburgh, 27-29 July 1992, 144-152
Bouzgou H, Gueymard CA (2017) Minimum redundancy – maximum relevance with extreme learning machines for global solar radiation forecasting: toward an optimized dimensionality reduction for solar time series. Solar Energy 158:595–609. https://doi.org/10.1016/j.solener.2017.10.035
Bre F, e Silva Machado RM, Lawrie LK, Crawley DB, Lamberts R (2021) Assessment of solar radiation data quality in typical meteorological years and its influence on the building performance simulation. Energy Build 250. https://doi.org/10.1016/j.enbuild.2021.111251
Breiman L (1996) Bagging predictors. Machine Learn 24(2):123–140. https://doi.org/10.1007/BF00058655
Breiman L (2001) Random Forests. Machine Learn 45(1):5–32. https://doi.org/10.1023/A:1010933404324
Breiman L (2002) Manual on setting up, using, and understanding random forests, 3d version edn. Statistics Department University of California Berkeley, USA
Buja A Stuetzle W (2000) The effect of bagging on variance, bias, and mean squared error. Preprint, AT&T Labs-Research. Retrieved from http://www.research.att.com/~andreas/\#nonpar}
Chen J, Liu Z, Yin Z, Liu X, Li X, Yin L, Zheng W (2023) Predict the effect of meteorological factors on haze using BP neural network. Urban Climate 51:101630. https://doi.org/10.1016/j.uclim.2023.101630
Daszykowski M, Walczak B, Xu Q-S, Daeyaert F, de Jonge MR, Heeres J, Koymans LMH, Lewi PJ, Vinkers HM, Janssen PA, Massart DL (2004) Classification and regression trees: - studies of HIV reverse transcriptase inhibitors. J Chem Inform Comput Sci 44(2):716–726. https://doi.org/10.1021/ci034170h
Duffie JA, Beckman WA, Worek WM (2013) Solar engineering of thermal processes, 4nd ed. John Wiley & Sons, Inc., Hoboken, New Jersey. https://doi.org/10.1115/1.2930068
Elbeltagi A, Salam R, Pal SC, Zerouali B, Shahid S, Mallick J, Islam MS, Islam ARMT (2022) Groundwater level estimation in northern region of Bangladesh using hybrid locally weighted linear regression and Gaussian process regression modeling. Theoret Appl Climatol 149:131–151. https://doi.org/10.1007/s00704-021-03909-1
El-kenawy ESM, Ibrahim A, Bailek N et al (2022) Sunshine duration measurements and predictions in Saharan Algeria region: an improved ensemble learning approach. Theor Appl Climatol 147:1015–1031. https://doi.org/10.1007/s00704-021-03843-2
Feng Y, Cui N, Gong D, Zhang Q, Zhao L (2017) Evaluation of random forests and generalized regression neural networks for daily reference evapotranspiration modelling. Agric Water Manag 193:163–173. https://doi.org/10.1016/j.agwat.2017.08.003
Feng Y, Gong D, Zhang Q, Jiang S, Zhao L, Cui N (2019) Evaluation of temperature-based machine learning and empirical models for predicting daily global solar radiation. Energy Convers Manag 198. https://doi.org/10.1016/j.enconman.2019.111780
Gagne DJ, McGovern A, Haupt SE, Sobash RA, Williams JK, Xue M (2017) Storm-based probabilistic hail forecasting with machine learning applied to convection-allowing ensembles. Weather Forecast 32:1819–1840. https://doi.org/10.1175/WAF-D-17-0010.1
Ghimire S, Deo RC, Downs NJ, Raj N (2019) Global solar radiation prediction by ANN integrated with European Centre for medium range weather forecast fields in solar rich cities of Queensland Australia. J Cleaner Prod 216:288–310. https://doi.org/10.1016/j.jclepro.2019.01.158
Gouda SG, Hussein Z, Luo S, Yuan Q (2019) Model selection for accurate daily global solar radiation prediction in China. J Cleaner Prod 221:132–144. https://doi.org/10.1016/j.jclepro.2019.02.211
Guijo-Rubio D, Durán-Rosal AM, Gutiérrez PA, Gómez-Orellana AM, Casanova-Mateo C, Sanz-Justo J, Salcedo-Sanz S, Hervás-Martínez C (2020) Evolutionary artificial neural networks for accurate solar radiation prediction. Energy 210. https://doi.org/10.1016/j.energy.2020.118374
Hissou H, Benkirane S, Guezzaz A, Azrour M, Beni-Hssane A (2023) A novel machine learning approach for solar radiation estimation. Sustainability 15:10609. https://doi.org/10.3390/su151310609
Huang L, Kang J, Wan M, Fang L, Zhang C, Zeng Z (2021) Solar radiation prediction using different machine learning algorithms and implications for extreme climate events. Front Earth Sci 9:596860. https://doi.org/10.3389/feart.2021.596860
Huang HL et al (2022) Solar radiation prediction using improved soft computing models for semi-arid, slightly-arid and humid climates. Alexandria Eng J 61(12):10631–10657
Ibrahim IA, Khatib T (2017) A novel hybrid model for hourly global solar radiation prediction using random forests technique and firefly algorithm. Energy Conver Manag 138:413–425. https://doi.org/10.1016/j.enconman.2017.02.006
Islam MA, Alam MS, Sharker KK, Nandi SK (2016) Estimation of solar radiation on horizontal and tilted surface over Bangladesh. Comput Water Energy Environ Eng 5:54–69. https://doi.org/10.4236/cweee.2016.52006
Jamei M, Ahmadianfar I, Jamei M et al (2022a) Estimating daily global solar radiation in hot semi-arid climate using an efficient hybrid intelligent system. Eur Phys J Plus 137:289. https://doi.org/10.1140/epjp/s13360-022-02398-z
Jamei M, Karbasi M, Malik A et al (2022b) Computational assessment of groundwater salinity distribution within coastal multi-aquifers of Bangladesh. Sci Rep 12:11165. https://doi.org/10.1038/s41598-022-15104-x
Jiang H, Yang Y, Wang H, Bai Y, Bai Y (2020) Surface diffuse solar radiation determined by reanalysis and satellite over East Asia: evaluation and comparison. Remote Sens 12(9). https://doi.org/10.3390/RS12091387
Karbasi M, Jamei M, Ali M, Malik A, Yaseen ZM (2022) Forecasting weekly reference evapotranspiration using Auto Encoder Decoder Bidirectional LSTM model hybridized with a Boruta-CatBoost input optimizer. Comput Electro Agric 198:107121
Liu Y, Gao Z (2015) Real-time property prediction for an industrial rubber-mixing process with probabilistic ensemble Gaussian process regression models. J Appl Polymer Sci 132(6). https://doi.org/10.1002/app.41432
Ma S, Qiu H, Yang D, Wang J, Zhu Y, Tang, B.,... Cao, M. (2023) Surface multi-hazard effect of underground coal mining. Landslides 20(1):39–52. https://doi.org/10.1007/s10346-022-01961-0
Makade RG, Chakrabarti S, Jamil B (2019) Prediction of global solar radiation using a single empirical model for diversified locations across India. Urban Climate 29. https://doi.org/10.1016/j.uclim.2019.100492
Makade RG, Chakrabarti S, Jamil B (2021) Development of global solar radiation models: a comprehensive review and statistical analysis for Indian regions. J Cleaner Prod 293:126208. https://doi.org/10.1016/j.jclepro.2021.126208
Meenal R, Selvakumar AI (2018) Assessment of SVM, empirical and ANN based solar radiation prediction models with most influencing input parameters. Renewe Energy 121:324–343. https://doi.org/10.1016/j.renene.2017.12.005
Mohammadi K, Shamshirband S, Anisi MH, Alam KA, Petković D (2015) Support vector regression based prediction of global solar radiation on a horizontal surface. Energy Convers Manag 91:433–441. https://doi.org/10.1016/j.enconman.2014.12.015
Nandi SK, Rahman R, Riadh RR (2016) A comparative study on ANN techniques in predicting solar radiation for various meteorological locations of Bangladesh. 5th International Conference on Informatics, Electronics and Vision (ICIEV), pp. 850-855. https://doi.org/10.1109/ICIEV.2016.7760122
Pakalidou N, Karacosta P (2018) Study of very long-period extreme precipitation records in Thessaloniki, Greece. Atmos Res 208:106–115. https://doi.org/10.1016/j.atmosres.2017.07.029
Podder S, Islam M (2015) Solar radiation estimation from the measurement of sunshine hours over southern coastal region, Bangladesh. Int J Sustain Green Energy 4(2):47–53. https://doi.org/10.11648/j.ijrse.20150402.14
Podder S, Khan RS, Mohon SMAA, Hussain MJ, Basher E (2014) Solar radiation approximation using sunshine hour at Patenga, Bangladesh. 8th International Conference on Electrical and Computer Engineering, pp. 321-324, https://doi.org/10.1109/ICECE.2014.7026996
Puga-Gil D, Astray G, Barreiro E, Gálvez JF, Mejuto JC (2022) Global solar irradiation modelling and prediction using machine learning models for their potential use in renewable energy applications. Mathematics 10:4746. https://doi.org/10.3390/math10244746
Rasaei Z, Bogaert P (2019) Spatial filtering and Bayesian data fusion for mapping soil properties: a case study combining legacy and remotely sensed data in Iran. Geoderma 344:50–62. https://doi.org/10.1016/j.geoderma.2019.02.031
Samadianfard S, Majnooni-Heris A, Qasem SN, Kisi O, Shamshirband S, Chau KW (2019) Daily global solar radiation modeling using data-driven techniques and empirical equations in a semi-arid climate. Eng Appl Comput Fluid Mech 13(1):142–157. https://doi.org/10.1080/19942060.2018.1560364
Sarkar MNI, Sifat AI (2016) Global solar radiation estimation from commonly available meteorological data for Bangladesh. Int J Renew: Wind Water Solar Renew 3:6. https://doi.org/10.1186/s40807-016-0027-3
Sarkar MNI, Sifat AI, Paul S, Hossain MS, Rahman M (2016) Solar radiation estimation using temperature data for Dhaka, Bangladesh. 5th IEEE International Conference on Informatics, Electronics, and Vision (ICIEV), pp. 204-208. https://doi.org/10.1109/ICIEV.2016.7759996
Shamshirband S et al (2019) A survey of deep learning techniques: application in wind and solar energy resources. IEEE Access 7(1):164650–164666
Shekaramiz M, Moon TK, Gunther JH (2017) Exploration and data refinement via multiple mobile sensors based on Gaussian processes. 51st Asilomar Conference on Signals, Systems, and Computers, 885–889. https://doi.org/10.1109/ACSSC.2017.8335476
Shuvho MBA, Chowdhury MA, Ahmed S, Kashem MA (2019) Prediction of solar irradiation and performance evaluation of grid connected solar 80KWp PV plant in Bangladesh. Energy Reports 5:714–722. https://doi.org/10.1016/j.egyr.2019.06.011
Sianturi Y, Marjuki A, Sartika K (2020) Evaluation of ERA5 and MERRA2 reanalyses to estimate solar irradiance using ground observations over Indonesia region. AIP Conference Proc 2223. https://doi.org/10.1063/5.0000854
Sohag MAZ, Kumari P, Agrawal R, Gupta S, Jamwal A (2020) Renewable energy in Bangladesh: current status and future potentials (pp. 353–363). https://doi.org/10.1007/978-981-15-2647-3_32
Tahir ZUR, Azhar M, Mumtaz M, Asim M, Moeenuddin G, Sharif H, Hassan S (2020) Evaluation of the reanalysis surface solar radiation from NCEP, ECMWF, NASA, and JMA using surface observations for Balochistan, Pakistan. J Renew Sustain Energy 12(2):023703. https://doi.org/10.1063/1.5135381
Taki M, Rohani A, Yildizhan H (2021) Application of machine learning for solar radiation modeling. Theor Appl Climatol 143:1599–1613. https://doi.org/10.1007/s00704-020-03484-x
Tao H, Ewees AA, Al-Sulttani AO, Beyaztas U, Hameed MM, Salih SQ, Armanuos AM, Al-Ansari N, Voyant C, Shahid S, Yaseen ZM (2021) Global solar radiation prediction over North Dakota using air temperature: development of novel hybrid intelligence model. Energy Reports 7:136–157. https://doi.org/10.1016/j.egyr.2020.11.033
Taylor KE (2001) Summarizing multiple aspects of model performance in a single diagram. J Geophys Res 106:7183–7192. https://doi.org/10.1029/2000JD900719
Vapnik V (1998) Statistical learning theory, vol 1. Wiley, New York
Vapnik VN (2000) The nature of statistical learning theory. Springer, New York. https://doi.org/10.1007/978-1-4757-3264-1
Venu K, Indhu Prakash KV, Jayaram S, Karan NS, Raja MM, Renu K (2023) Solar radiation prediction using machine learning model, 2023 International Conference on Sustainable Computing and Data Communication Systems (ICSCDS). Erode, India, pp 52–57. https://doi.org/10.1109/ICSCDS56580.2023.10104904
Voyant C, Muselli M, Paoli C, Nivet M-L (2012) Numerical weather prediction (NWP) and hybrid ARMA/ANN model to predict global radiation. Energy 39(1):341–355. https://doi.org/10.1016/j.energy.2012.01.006
Voyant C, Notton G, Kalogirou S, Nivet M-L, Paoli C, Motte F, Fouilloy A (2017) Machine learning methods for solar radiation forecasting: a review. Renew Energy 105:569–582. https://doi.org/10.1016/j.renene.2016.12.095
Wang L, Lu Y, Zou L, Feng L, Wei J, Qin W, Niu Z (2019) Prediction of diffuse solar radiation based on multiple variables in China. Renew Sustain Energy Rev 103:151–216. https://doi.org/10.1016/j.rser.2018.12.029
Yadav AK, Malik H, Chandel SS (2015) Application of rapid miner in ANN based prediction of solar radiation for assessment of solar energy resource potential of 76 sites in Northwestern India. In Renewable and Sustainable Energy Reviews (Vol. 52, pp. 1093–1106). Elsevier Ltd. https://doi.org/10.1016/j.rser.2015.07.156
Yang H, Huang K, King I, Lyu MR (2009) Localized support vector regression for time series prediction. Neurocomputing 72(10–12):2659–2669. https://doi.org/10.1016/j.neucom.2008.09.014
Yin Z, Liu Z, Liu X, Zheng W, Yin L (2023) Urban heat islands and their effects on thermal comfort in the US: New York and New Jersey. Ecol Indicators 154:110765. https://doi.org/10.1016/j.ecolind.2023.110765
Zhou Y, Liu Y, Wang D, De G, Li Y, Liu X, Wang Y, 2021. A novel combined multi-task learning and Gaussian process regression model for the prediction of multi-timescale and multi-component of solar radiation. J Cleaner Prod 284. https://doi.org/10.1016/j.jclepro.2020.124710
Acknowledgements
We are grateful to the Department of Disaster Management, Begum Rokeya University, Rangpur, for all sorts of assistance provided during this study. Furthermore, we would like to thank the Bangladesh Meteorological Department (BMD), ECMWF, and NASA POWER Project for providing the required data for this research.
Funding
Authors received administrative and financial support from the Deanship of Scientific Research. Funding for this research was given under award numbers RGP2/363/44 by the Deanship of Scientific Research; King Khalid University, Ministry of Education, Kingdom of Saudi Arabia.
Author information
Authors and Affiliations
Contributions
MAKA designed, conceptualized, data collection and extraction, and drafted the original manuscript; KA planned the documents and literature review; MH involved in the software, mapping, statistical analysis, interpretation of the analysis and discussion; MAKA contributed to instrumental setup, data analysis, validation; JM edited the manuscript, ARMTI had done the internal review and proofreading during the manuscript drafting stage. All authors reviewed the manuscript.
Corresponding author
Ethics declarations
Ethical approval
Not applicable.
Consent to participate
Not applicable.
Consent for publication
Not applicable.
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary information
ESM 1
(DOCX 450 kb)
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Azad, M.A.K., Mallick, J., Islam, A.R.M.T. et al. Estimation of solar radiation in data-scarce subtropical region using ensemble learning models based on a novel CART-based feature selection. Theor Appl Climatol 155, 349–369 (2024). https://doi.org/10.1007/s00704-023-04638-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00704-023-04638-3