Modeling and forecasting relative humidity using multilayer perceptron, radial basis function, and linear regression approaches

• Autorzy: Kadiri Imad , Yahia Abdellah Ben , Abdallaoui Abdelaziz , El Hmaidi Abdellah

Identyfikatory

DOI

10.12913/22998624/203394

• Języki publikacji: EN

Abstrakty

EN

Forecasting relative humidity is a critical for addressing the challenges of climate change. It facilitates comprehension of climatic mechanisms and the anticipation of extreme weather events, while also contributing to strengthening societal resilience and protection. Indeed, elevated levels of humidity have been demonstrated to exacerbate heat waves, leading to a marked increase in both the perceived temperature and the associated health risks. Conversely, low humidity promotes conditions conducive to droughts and wildfires. Moreover, relative humidity plays a key role in the water cycle, influencing precipitation, evaporation, and cloud formation. Understanding these mechanisms is essential for anticipating floods, droughts, and water shortages. In this study, mathematical models were developed to predict relative humidity in the Fez, Morocco, using multilayer perceptron (MLP) neural networks, radial basis function (RBF) neural networks, and multiple linear regression (MLR). The dataset used in this study includes daily values of eight meteorological parameters, including temperature at 2m, shortwave Radiation, diffuse shortwave radiation, precipitation total, evapotranspiration, vapor pressure deficit and wind speed and relative humidity as the output. The data spans 38 years, from January 1985 to December 2022, and includes 13879 observation days.. To evaluate the predictive performance of these models, we analyzed their architectures, learning algorithms, correlation coefficients, and mean squared errors. The results indicate that the MLP model attains the highest predictive accuracy, with a correlation coefficient of 0.9809 and a mean squared error MSE of 0.0099, outperforming the RBF model (correlation of 0.9603) and the MLR model (correlation of 0.9023), the best performing model used a Tansig activation function in the hidden layer, a Purelin function in the output layer and the Levenberg-Marquardt learning algorithm with a MLP configuration [7-15-1]. The findings of this study offer a valuable contribution to the field of water resource management in the region. They demonstrate the efficacy of artificial neural network models in enhancing moisture forecasting, thereby providing a solid foundation for future research in climate modelling.

Słowa kluczowe

EN

modeling; MLP; multilayer perceptron; RBF; radial basis function; MLR; multiple linear regression; climate change; correlation coefficient; mean square error; relative humidity; Fez

• Wydawca: Lublin University of Technology ; Polish Society of Ecological Engineering (PTIE), Branch of PTIE in Lublin
• Czasopismo: Advances in Science and Technology. Research Journal
• Rocznik: 2025
• Tom: Vol. 19, no. 6
• Strony: 414--425
• Opis fizyczny: Bibliogr. 28 poz., fig., tab.

Twórcy

autor

Kadiri Imad

• Department of Chemistry, Laboratory of Analytical Chemistry and Electrochemistry, Processes and Environment, Moulay Ismail University, Faculty of Sciences, Meknes, Morocco

• https://orcid.org/0009-0007-8310-2107

autor

Yahia Abdellah Ben

• Department of Chemistry, Laboratory of Analytical Chemistry and Electrochemistry, Processes and Environment, Moulay Ismail University, Faculty of Sciences, Meknes, Morocco

• https://orcid.org/0000-0002-5585-1481

autor

Abdallaoui Abdelaziz

• Department of Chemistry, Laboratory of Analytical Chemistry and Electrochemistry, Processes and Environment, Moulay Ismail University, Faculty of Sciences, Meknes, Morocco

• https://orcid.org/0000-0002-3778-7973

autor

El Hmaidi Abdellah

• Department of Geology, Laboratory of Water Sciences and Environmental Engineering, Moulay Ismail University, Faculty of Sciences, Meknes, Morocco

• https://orcid.org/0000-0002-3311-9492

Bibliografia

• 1. Xie B., Zhang Q., and Ying Y. Trends in precipitable water and relative humidity in China: 1979–2005. Journal of Applied Meteorology and Climatology. 2011; 50(10): 1985–1994. https://doi.org/10.1175/2011JAMC2446.1.
• 2. Lowen A. C., Mubareka S., Steel J., and Palese P. Influenza virus transmission is dependent on relative humidity and temperature. PLoS Pathogens. 2007; 3(10): 1470–1476. https://doi.org/10.1371/journal.ppat.0030151.
• 3. Park J.-E., Son W\.-S., Ryu Y., Choi S. B., Kwon O., and Ahn I. Effects of temperature, humidity, and diurnal temperature range on influenza incidence in a temperate region. Influenza and Other Respiratory Viruses. 2020; 14(1): 11–18. https://doi.org/10.1111/irv.12682.
• 4. Ma Y. et al. Effects of temperature variation and humidity on the death of COVID-19 in Wuhan, China. The Science of the Total Environment. 2020; 724: 138226. https://doi.org/10.1016/j.scitotenv.2020.138226.
• 5. Mecenas P., Bastos R. T. da R. M., Vallinoto A. C. R., and Normando D. Effects of temperature and humidity on the spread of COVID-19: A systematic review. PloS One. 2020; 15(9): e0238339. https://doi.org/10.1371/journal.pone.0238339.
• 6. Bennedsen M. Designing a statistical procedure for monitoring global carbon dioxide emissions. Climatic Change. 2021; 166(3): 32. https://doi.org/10.1007/s10584-021-03123-y.
• 7. Sisco M. R., Bosetti V., and Weber E. U. When do extreme weather events generate attention to climate change. Climatic Change. 2017; 143(1): 227–241. https://doi.org/10.1007/s10584-017-1984-2.
• 8. Kuzugudenli E. Relative humidity modeling with artificial neural networks. Applied Ecology Environmental Research. 2018; 16(4): 5227–5235. https://doi.org/10.15666/aeer/1604_52275235.
• 9. Liaw A. and Wiener M. Classification and regression by random forest. R News. 2007; 2(3): 18–22.
• 10. Hanoon M. S. et al. Developing machine learning algorithms for meteorological temperature and humidity forecasting at Terengganu state in Malaysia. Scientific Reports. 2021; 11(1): 18935.https://doi.org/10.1038/s41598-021-96872-w.
• 11. Yahia B. A., Abdallaoui A., and Kadir I. Development of a stochastic model of RBF neural network for forecasting relative humidity rates. International Conference on Circuit, Systems and Communication (ICCSC). 2024; 1–7. https://doi.org/10.1109/iccsc62074.2024.10617431.
• 12. Khatibi R., Naghipour L., Ghorbani M. A., and Aalami M. T. Predictability of relative humidity by two artificial intelligence techniques using noisy data from two Californian gauging stations. Neural Computing and Applications. 2013; 23(7): 2241–2252. https://doi.org/10.1007/s00521-012-1175-z.
• 13. El Badaoui H., Abdallaoui A., & Chabaa S. Using MLP neural networks for predicting global solar radiation. The International Journal of Engineering and Science (IJES). 2013; 2: 48–56.
• 14. Touzet C. Artificial neural networks, introduction to connectionism. EC2 (in French). doi: [https://doi.org/10/document](https://doi.org/10/document).
• 15. Heidari E., Sobati M. A., and Movahedirad S. Accurate prediction of nanofluid viscosity using a multilayer perceptron artificial neural network (MLP-ANN). Chemometrics and Intelligent Laboratory Systems. 2016; 155: 73–85. https://doi.org/10.1016/j.chemolab.2016.03.031.
• 16. Derras B., Bekkouche A., and Zendagui D. Neuronal Approach and the Use of KIK-NET N Response Spectrum on the Surfaceetwork to Generate. Jordan Journal of Civil Engineering. 2010; 4(1).
• 17. Manssouri I., Manssouri M., and Kihel B. Fault detection by K-NN algorithm and MLP neural networks in a distillation column: Comparative study. Knowledge Management and Communication in the Information. 2013; 201–215.
• 18. Bélanger M., El-Jabi N., Caissie D., Ashkar F., and Ribi J. Estimation de la température de l’eau de rivière en utilisant les réseaux de neurones et la régression linéaire multiple. Revue Science de l’eau / Journal of Water Science. 2005; 18(3): 403–421.https://doi.org/10.7202/705565ar.
• 19. Ghorbani M. A., Zadeh H. A., Isazadeh M., and Terzi O. A comparative study of artificial neural network (MLP, RBF) and support vector machine models for river flow prediction. Environmental Earth Sciences. 2016; 75(6): 476. https://doi.org/10.1007/s12665-015-5096-x.
• 20. Broomhead D. S. and Lowe D. Multivariable functional interpolation and adaptive networks. Complex Syst. 1988; 2(3).
• 21. Moody J. and Darken C. J. Fast learning in networks of locally-tuned processing units. Neural Computation. 1989; 1(2): 281–294. https://doi.org/10.1162/neco.1989.1.2.281.
• 22. Boudebbouz B., Manssouri I., Mouchtachi A., Manssouri T., and Kihel B. E. Use of RBF artificial neural networks to model the normal regime with variable operating point of an industrial plant. European Scientific Journal, ESJ. 2015; 11(18) (in French).
• 23. Chen K. T., Chou C. H., Chang S. H., and Liu Y. H. Intelligent active vibration control in an isolation platform. Applied Acoustics. 2008; 69(11): 1063–1084. https://doi.org/10.1016/j.apacoust.2007.06.008.
• 24. El Azhari K., Abdallaoui B., Dehbi A., Abdallaoui A., and Zineddine H. Development of a neural statistical model for the relative humidity levels prediction in the Region of Rabat-Kenitra (Morocco). Research Square. 2021. https://doi.org/10.21203/rs.3.rs-385467/v1.
• 25. El Badaoui H., Abdallaoui A., & Chabaa S. Multilayer Perceptron and Radial Basis Function network to predict the moisture. International Journal of Innovation and Scientific Research. 2014; 5(1).
• 26. Hinton G. E. and Salakhutdinov R. R. Reducing the dimensionality of data with neural networks. Science. 2006; 313(5786): 504–507. https://doi.org/10.1126/science.1127647.
• 27. El Badaoui H., Abdallaoui A., & Chabaa S. Optimization numerical the neural architectures by performance indicator with LM learning algorithms. Journal of Materials and Environmental Science. 2017; 8: 169–179.
• 28. Wilamowski B. M., Iplikci S., Kaynak O., and Efe M. O. An algorithm for fast convergence in training neural networks. International Joint Conference on Neural Networks (IJCNN’01). 2001; 3: 1778–1782. https://doi.org/10.1109/ijcnn.2001.938431.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).