journal article·2025-04-01Open access

Enhanced hourly temperature prediction using advanced ensemble neural networks for energy system efficiency optimization in hyper-arid regions

Abdennasser Dahmani, Ikram Kouidri, Nadjem Bailek, Lotfi Mouni, Shabana Urooj, Jihad A. Younis, Bilel Zerouali, El-Sayed M El-Kenawy, Celso Augusto Guimarães Santos, Abdel-Nasser Sharkawy

AIP Advances· Volume 15· Issue 4

Abstract

This paper presents advanced techniques for air temperature forecasting based on the relationship between meteorological variables and feedforward neural network models aimed at improving prediction accuracy. An optimal single neural network model was developed, and optimization through dataset partitioning resulted in high predictive preformance, with all correlation coefficients exceeding 0.97 in the test phase and a root mean square error (RMSE) of 1.5587. Additionally, a bootstrap-aggregated neural network (BANN) model comprising 30 networks in a stacked ensemble was implemented, yielding robust results; both validation and testing correlation coefficients were close to the ideal value. Sensitivity analysis further revealed that true solar time, extraterrestrial radiation, and wind speed were the most influential predictors—an outcome that is consistent with their physical relevance to temperature variation. Moreover, the model’s validity was confirmed through applicability domain analysis using the Williams plot, which showed that over 97% of the predictions fell within acceptable error limits. A comparative evaluation against other existing models demonstrated the superior predictive performance of the proposed approach, reinforcing the potential of the BANN model for accurate air temperature forecasting under diverse meteorological conditions.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Energy Load and Power Forecasting · Solar Radiation and Photovoltaics · Hydrological Forecasting Using AI

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Department of Mechanical Engineering, Faculty of Applied Sciences, University of Bouira 1 , Bouira 10000,

Laboratory of Biomaterials and Transport Phenomena (LBMPT), University of Medea 2 , Urban Pole, 26000 Medea,

Department of Mechanical Engineering, Faculty of Science and Technology, GIDD Industrial Engineering and Sustainable Development Laboratory, University of Relizane 3 , Bourmadia, 48000 Relizane,

Laboratory of Mathematics Modeling and Applications, Department of Mathematics and Computer Science, Faculty of Sciences and Technology, Ahmed Draia University of Adrar 4 , Adrar,

5 Jadara Research Center, Jadara University, Irbid 21110, Jordan

Laboratoire de Gestion et Valorisation des Ressources Naturelles et Assurance Qualité, Faculté SNVST, Université de Bouira 6 , 10000 Bouira,

Department of Electrical Engineering, College of Engineering, Princess Nourah Bint Abdulrahman University 7 , P.O. Box 84428, Riyadh 11671,

Department of Mathematics, Aden University 8 , Aden,

Laboratory of Architecture, Cities and Environment, Faculty of Civil Engineering and Architecture, Department of Hydraulic, Hassiba Benbouali, University of Chlef 9 , B.P. 78C, Ouled Fares, Chlef 02180,

Vegetal Chemistry-Water-Energy Laboratory, Faculty of Civil Engineering and Architecture, Depart-ment of Hydraulic, Hassiba Benbouali, University of Chlef 10 , B.P. 78C, Ouled Fares, Chlef 02180,

School of ICT, Faculty of Engineering, Design and Information & Communications Technology (EDICT), Bahrain Polytechnic 11 , P.O. Box 33349, Isa Town,

Applied Science Research Center, Applied Science Private University 12 , Amman,

Department of Civil and Environmental Engineering, Federal University of Paraíba 13 , João Pessoa 58051-900,

Mechanical Engineering Department, Faculty of Engineering, South Valley University 14 , Qena 83523,

Funding

Princess Nourah Bint Abdulrahman University

References (35)

Show source-provided references
1. R. K. Pachauri , M. R.Allen, V. R.Barros, J.Broome, W.Cramer, Climate Change 2014: Synthesis Report. Contribution of Working Groups I, II and III to the Fifth Assessment Report of the Intergovernmental Panel on Climate Change (IPCC, 2014).
2. Long-term trend in ground-based air temperature and its responses to atmospheric circulation and anthropogenic activity in the Yangtze river delta, China10.1016/j.atmosres.2017.05.013 ↗
3. Hourly temperature forecasting using abductive networks10.1016/j.engappai.2004.04.002 ↗
4. An ensemble approach for short-term load forecasting by extreme learning machine10.1016/j.apenergy.2016.02.114 ↗
5. A novel non-linear model based on bootstrapped aggregated support vector machine for the prediction of hourly global solar radiation10.1007/s40866-023-00179-w ↗
6. Prediction of building's temperature using neural networks models10.1016/j.enbuild.2005.09.007 ↗
7. Estimation of photovoltaic module yearly temperature and performance based on nominal operation cell temperature calculations10.1016/j.renene.2004.03.010 ↗
8. Daily means ambient temperature prediction using artificial neural network method: A case study of Turkey10.1016/j.renene.2008.07.007 ↗
9. Meteorological fire danger indices and remote sensing10.1007/978-3-642-60164-4 ↗
10. Cooling load prediction for buildings using general regression neural networks10.1016/j.enconman.2003.10.009 ↗
11. On the energy consumption in residential buildings10.1016/s0378-7788(01)00137-2 ↗
12. Improved surface temperature prediction for the coming decade from a global climate model10.1126/science.1139540 ↗
13. Application of neural networks for the prediction of hourly mean surface temperatures in Saudi Arabia10.1016/S0960-1481(01)00082-9 ↗
14. Improving air temperature prediction with artificial neural networks10.5281/zenodo.1075076 ↗
15. Artificial neural networks for automated year-round temperature prediction10.1016/j.compag.2009.04.003 ↗
16. Air temperature forecasting using artificial neural networks with delayed exogenous input
17. Prediction of hourly air temperature based on CNN–LSTM10.1080/19475705.2022.2102942 ↗
18. Prediction of outdoor air temperature using neural networks: Application in 4 European cities10.1016/j.enbuild.2015.06.054 ↗
19. The use of artificial neural network (ANN) for modeling of COD removal from antibiotic aqueous solution by the Fenton process10.1016/j.jhazmat.2010.02.068 ↗
20. Prediction of hourly global solar radiation: Comparison of neural networks/bootstrap aggregating10.15255/KUI.2022.065 ↗
21. A model based on bootstrapped neural networks for modeling the removal of organic compounds by nanofiltration and reverse osmosis membranes10.1007/s13369-018-3484-8 ↗
22. Modeling the retention of organic compounds by nanofiltration and reverse osmosis membranes using bootstrap aggregated neural networks10.1007/s13369-016-2320-2 ↗
23. Bootstrap based artificial neural network (BANN) analysis for hierarchical prediction of monthly runoff in vpper damodar valley catchment10.1016/j.jhydrol.2009.06.003 ↗
24. Reliable optimisation control of a reactive polymer composite moulding process using ant colony optimisation and bootstrap aggregated neural networks10.1007/s00521-012-1273-y ↗
25. Inferential estimation of polymer melt index using sequentially trained bootstrap aggregated neural networks10.1002/ceat.200500352 ↗
26. Optimal control of batch processes using particle swam optimisation with stacked neural network models10.1016/j.compchemeng.2009.01.009 ↗
27. A new empirical model for forecasting the diffuse solar radiation over Sahara in the Algerian big south10.1016/j.renene.2017.10.081 ↗
28. Neural network for prediction solar radiation in Relizane region (Algeria)-Analysis study
29. Interpreting neural-network connection weights
30. Back-propagation neural networks for modeling complex systems10.1016/0954-1810(94)00011-s ↗
31. QSAR modeling in ecotoxicological risk assessment: Application to the prediction of acute contact toxicity of pesticides on bees (Apis mellifera L.)10.1007/s11356-017-0498-9 ↗
32. Accurate local very short-term temperature prediction based on synoptic situation support vector regression banks10.1016/j.atmosres.2011.10.013 ↗
33. Neural network modelling for the analysis of forcings/temperatures relationships at different scales in the climate system10.1016/j.ecolmodel.2005.08.012 ↗
34. Forecast of daily mean, maximum and minimum temperature time series by three artificial neural network methods10.1002/met.83 ↗
35. Establishment of dynamic evolving neural-fuzzy inference system model for natural air temperature prediction10.1155/2022/1047309 ↗