Estimation of Stratospheric Ozone Concentration over Southern Nigeria using Neural Network: Case Study of Lagos and Port Harcourt
DOI:
https://doi.org/10.37591/.v8i1.1704Keywords:
Stratospheric ozone, Artificial Neural Network, Meteorological factors, Regression, Mean square error.Abstract
The neural network model was developed to estimate the stratospheric ozone concentrations along with some meteorological parameters. The neural network was trained using monthly maximum data provided by Nigerian Meteorological Agency (NIMET) and National Aeronautics and Space Administration (NASA) over a period of 43year (1970-2012) in the towns of Lagos and Port Harcourt Ozone concentration from the two stations was estimated using a surface meteorological variable as predictors for the ANN. Based on the results, it was confirmed that Lagos station has the highest coefficient of correction of r = 0.85747 in comparison with Port Harcourt station. The sensitivity of the results indicated that Lagos station had the greatest maximum effect on the prediction of stratospheric ozone concentrations.
Keywords: Artificial neural network, mean square error, meteorological factors, regression, stratospheric ozone
Cite this Article
C.C. Ekechukwu, J.A. Obu, E. Okoro, D.I. Okoh. Estimation of Stratospheric Ozone Concentration over Southern Nigeria using Neural Network: Case Study of Lagos and Port Harcourt. Research & Reviews: Journal of Space Science & Technology. 2019; 8(1): 4–9p.
References
Ignacio, G., Jose, G.R., Yenisse, M.T. Artificial neural network models for prediction of ozone concentration in Guadalajara Mexico. Air quality model and applications. 2011; ISBN: 978-953-307-1.
Akinyemi, M.L. and Oladiran, E.O. Temporal and Spatial Variability of Ozone Concentration over Four African Stations. Journal of Applied Sciences. 2007; 7: 913 – 917p.
García, L. A. and Shigidi, A. Using neural networks for parameter estimation in ground water, Journal of Hydrology. 2006; 318: 215–231p.
Jacobson, M. Z. Fundamental of Atmospheric Modeling. Cambridge University Press, Cambridge; 2000.
World Meteorological Organization. Scientific Assessment of ozone depletion: 2002, Global Ozone Research and Monitoring project. 47th ed. Geneva: World Health Organization; 2003. 498p.
Acharaya, U.R., Bhatt, P.S., Ienger, S.S., Rao, A. and Dua, S. Classification of heart rate data using neural networks and fuzzy equivalence relation. Pattern Recognition. 2003; 36: 61-68p.
Wang, W., Lu, W., Wang, X., Leung, A.Y.T. Prediction of maximum daily ozone level using combined neural network and statistical characteristics. Environment International. 2003; 29: 555-562p
.
Yetilmezsoy, K. and Demirel, S. Artificial neural networks (ANN) approach for modeling of Pb (II) adsorption from aqueous solution by Antep pistachio (PistaciaVeral.) Shells.Journal of Hazardous Materials. 2008; 153: 1288–1300p.
