Comparative analysis of Elman and Jordan Recurrent Neural Networks for Solar Radiation and Air Temperature Prediction Using Backpropagation Variants
Abstract
This study compares the effectiveness of Elman Recurrent Neural Networks (ERNN) and Jordan Recurrent Neural Networks (JRNN) for predicting solar radiation and ambient temperature in Ouarzazate, Morocco. Data collected at 10-minute intervals from three meteorological stations (OUA_001, OUA_002, and OUA_003) over a 3–4-year period (2018-2022) were analyzed. The dataset was split into training (75%) and validation (25%) subsets to develop and test the models. The research systematically explored different network architectures with 1-2 hidden layers containing 4-12 neurons, applying three learning algorithms: BackPropagation (BP), BackPropagation with Momentum (BPM), and Resilient Backpropagation (Rprop). Key hyperparameters were optimized within specific ranges, including learning rates (0.00001-0.4) for BP/BPM and weight decay exponents (0.00001-4) for Rprop. Input variables included date, temperature, solar radiation, wind speed, relative humidity, precipitation, and atmospheric pressure in various combinations. Performance evaluation using Nash-Sutcliffe Efficiency (NSE) and Index of Agreement (d) revealed high prediction accuracy for both model types, with values exceeding 0.9 during validation. JRNN with BPM performed best at station OUA_001 (NSE: 0.909 for radiation, 0.971 for temperature), while ERNN with BPM demonstrated superior performance at station OUA_002 (NSE: 0.978 for radiation, 0.976 for temperature). At station OUA_003, both models showed comparable results when using BP. Despite the high overall accuracy, both models exhibited limitations in predicting extreme solar radiation values, particularly during nighttime hours. The study concludes that ERNN and JRNN are effective tools for short-term prediction of solar radiation and temperature in arid regions like Ouarzazate, though further refinement is needed to better capture extreme values and improve prediction accuracy during transitional periods.
Full Text:
PDFReferences
Sudharshan, K., Naveen, C., Vishnuram, P., Krishna Rao Kasagani, D.V.S., & Nastasi, B. 2022. Systematic review on impact of different irradiance forecasting techniques for solar energy prediction. Energies, 15(17), 6267. https://doi.org/10.3390/en15176267
Bosak, A., Matushkin, D., Davydenko, L., Kulakovskyi, L., & Bronytskyi, V. 2022. Short-term forecasting of photovoltaic solar power generation based on time series: Application for ensuring the efficient operation of the integrated energy system of Ukraine. In Power Systems Research and Operation: Selected Problems II (pp. 159-179). Cham: Springer International Publishing. https://doi.org/10.1007/978-3-030-78909-7_9
Prema, V., & Rao, K. U. 2015. Development of statistical time series models for solar power prediction. Renewable energy, 83, 100-109. https://doi.org/10.1016/j.renene.2015.03.038
Atique, S., Noureen, S., Roy, V., Bayne, S., & Macfie, J. (2020, April). Time series forecasting of total daily solar energy generation: A comparative analysis between ARIMA and machine learning techniques. In 2020 IEEE green technologies conference (GreenTech) (pp. 175-180). IEEE. https://doi.org/10.1109/GreenTech46478.2020.9289796
Pang, Z., Niu, F., & O’Neill, Z. 2020. Solar radiation prediction using recurrent neural network and artificial neural network: A case study with comparisons. Renewable Energy, 156, 279-289. https://doi.org/10.1016/j.renene.2020.04.042
Kumari, S., Aravindakshan, S., & Srinivasa Chakravarthy, V. 2021. Elman and jordan recurrence in convolutional neural networks using attention window. In International Conference on Innovative Computing and Communications: Proceedings of ICICC 2020, Volume 1 (pp. 983-993). Springer Singapore.
KROGH, Anders. What are artificial neural networks?. Nature biotechnology, 2008, vol. 26, no 2, p. 195-197.
Kaur, M., & Mohta, A. 2019. A review of deep learning with recurrent neural network. In 2019 International Conference on Smart Systems and Inventive Technology (ICSSIT) (pp. 460-465). IEEE.https://doi.org/10.1109/ICSSIT46314.2019.8987837
Gao, Y., Hu, Z., Shi, S., Chen, W. A., & Liu, M. 2024. Adversarial discriminative domain adaptation for solar radiation prediction: A cross-regional study for zero-label transfer learning in Japan. Applied Energy, 359, 122685. https://doi.org/10.1016/j.apenergy.2024.122685
[Sevas, M. S., Sharmin, N., Santona, C. F. T., & Sagor, S. R. 2024. Advanced ensemble machine-learning and explainable ai with hybridized clustering for solar irradiation prediction in Bangladesh. Theoretical and Applied Climatology, 155(7), 5695-5725.
Tercha, W., Tadjer, S. A., Chekired, F., & Canale, L. 2024. Machine learning-based forecasting of temperature and solar irradiance for photovoltaic systems. Energies, 17(5), 1124. https://doi.org/10.3390/en17051124
[Fan, C., Zou, B., Li, J., Wang, M., Liao, Y., & Zhou, X. 2024. Exploring the relationship between air temperature and urban morphology factors using machine learning under local climate zones. Case Studies in Thermal Engineering, 55, 104151. https://doi.org/10.1016/j.csite.2024.104151
Didi, F., Bibi-Triki, N., Mohamed, B., & Abène, A. 2017. Optimization, Modeling and Simulation of Microclimate and Eenergy Management of the Greenhouse by Modeling the Associated Heating and Cooling Systems and Implemented by a Fuzzy Logic Controller using Artificial Intelligence. Informatica, 41(3).
Gaafar, A. S., Dahr, J. M., & Hamoud, A. K. 2025. Optimizing Fuzzy Logic Control-Based Weather Forecasting through Optimal Antecedent Selection Using the Fuzzy Analytical Hierarchy Process Model. Informatica, 49(12).
Bengio, Y., Goodfellow, I., & Courville, A. 2017. Deep learning (Vol. 1). Cambridge, MA, USA: MIT press
Krenker, A., Bešter, J., & Kos, A. 2011. Introduction to the artificial neural networks. Artificial Neural Networks: Methodological Advances and Biomedical Applications. InTech, 1-18.
Tufail, S., Riggs, H., Tariq, M., & Sarwat, A.I. 2023. Advancements and challenges in machine learning: A comprehensive review of models, libraries, applications, and algorithms. Electronics, 12(8), 1789. https://doi.org/10.3390/electronics12081789
Krauss, P. 2024. Recurrent neural networks. In Artificial Intelligence and Brain Research: Neural Networks, Deep Learning and the Future of Cognition (pp. 131-137). Berlin, Heidelberg: Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-030-91234-0_15
Putro, S.S., Syakur, M.A., Rochman, E.M.S., & Rachmad, A. 2022. Comparison of backpropagation and ERNN methods in predicting corn production. Communications in Mathematical Biology and Neuroscience, 2022, Article-ID. https://doi.org/10.28919/cmbn/7562
Zaras, A., Passalis, N., & Tefas, A. 2022. Neural networks and backpropagation. In Deep Learning for Robot Perception and Cognition (pp. 17-34). Academic Press. https://doi.org/10.1016/B978-0-12-823600-6.00002-1
Şen, Z., Şişman, E., & Kızılöz, B. 2022. A new innovative method for model efficiency performance. Water Supply, 22(1), 589-601. https://doi.org/10.2166/ws.2021.368
Pereira, H.R., Meschiatti, M.C., Pires, R.C.D.M., & Blain, G.C. 2018. On the performance of three indices of agreement: An easy-to-use R-code for calculating the Willmott indices. Bragantia, 77(2), 394-403. https://doi.org/10.1590/1678-4499.201
DOI: https://doi.org/10.31449/inf.v49i18.8163
This work is licensed under a Creative Commons Attribution 3.0 License.