Abstract
The present study attempts to model ambient ozone (O3) concentrations using the Feed-forward backpropagation neural network model as a function of meteorological conditions and to draw a map of ozone concentrations over the Agadir City and its neighboring regions. The data, used to train the network, was collected during a period of 30 days in Agadir City using a mobile monitoring station. The data was divided into two sets: 85% for the training and 15% for the testing. Different neural network architectures were tested during the training process. A network of two hidden layers with a [7-16-16-1] structure, Levenberg-Marquardt as a training algorithm and log-sigmoid as a transfer function was found to give the best predictions for both the training and testing data. Statistical agreement between predicted and observed values is evaluated by coefficient of correlation (CC), root mean square error (RMSE) and mean absolute error (MAE). Results show that artificial neural network modelling appears to be a promising method for modelling air-pollution. IDW Inverse distance method was used in order to interpolate the ozone concentrations over the city of Agadir and its neighboring areas.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Abdallah, C., Afif, C., El Masri, N., Öztürk, F., Keles, M., & Sartelet, K.: A first annual assessment of air quality modeling over Lebanon using WRF/Polyphemus. Atmos. Pollut. Res., March 2017 (2018). https://doi.org/10.1016/j.apr.2018.01.003
Abdul-Wahab, S.A., Al-Alawi, S.M.: Assessment and prediction of tropospheric ozone concentration levels using artificial neural networks. Environ. Model. Softw. 17, 219–228 (2002)
Adnane, A., Leghrib, R., Chaoufi, J.: The use of a recurrent neural network for forecasting ozone concentrations in the city of Agadir (Morocco). J. Atomic Mol. Condens. Matter Nano Phys. 7(3), 197–206 (2020). https://doi.org/10.26713/jamcnp.v7i3.1545
Ajdour, A., Leghrib, R., Chaoufi, J., Chirmata, A., Menut, L., Mailler, S.: Towards air quality modeling in Agadir City (Morocco). Mater. Today Proc. 24, 17–23 (2020). https://doi.org/10.1016/j.matpr.2019.07.438
ANSES: Sélection des polluants à prendre en compte dans les évaluations des risques sanitaires réalisées dans le cadre des études d’impact des infrastructures routières (2012)
Bai, Y., Li, Y., Wang, X., Xie, J., Li, C.: Air pollutants concentrations forecasting using back propagation neural network based on wavelet decomposition with meteorological conditions. Atmos. Pollut. Res. 7(3), 557–566 (2016). https://doi.org/10.1016/j.apr.2016.01.004
Bai, Y., Zeng, B., Li, C., Zhang, J.: Chemosphere an ensemble long short-term memory neural network for hourly PM 2. 5 concentration forecasting. Chemosphere 222, 286–294 (2019). https://doi.org/10.1016/j.chemosphere.2019.01.121
Chirmata, A., Leghrib, R., Ichou, I.A.: Implementation of the air quality monitoring network at Agadir City in Morocco. J. Environ. Prot. 8, 540–567 (2017). https://doi.org/10.4236/jep.2017.84037
Comrie, A.C.: Comparing neural networks and regression models for ozone forecasting. J. Air Waste Manag. Assoc. 47(6), 653–663 (1997). https://doi.org/10.1080/10473289.1997.10463925
Elkamel, A., Abdul-Wahab, S., Bouhamra, W., Alper, E.: Measurement and prediction of ozone levels around a heavily industrialized area: a neural network approach. Adv. Environ. Res. 5(1), 47–59 (2001). https://doi.org/10.1016/S1093-0191(00)00042-3
Garson, G.: Interpreting neural network connection weights. Artif. Intell. Expert 6, 47–51 (1991)
Kuenzli, N.: Une longue route pour comprendre les effets à long terme de la pollution atmosphérique, pp. 5–8 (2006)
Schmitt, A., Le Blanc, B., Corsini, M., Lafond, C., Bruzek, J.: Artificial neural network : A relevant data processing tool for anthropology. Bulletins et Mémoires de La Société d’Anthropologie de Paris 13 (2001)
Tertre, A.L., et al.: Short-term effects of air pollution on mortality in nine French cities: a quantitative summary. Arch. Environ. Health 57(4), 311–319 (2002). https://doi.org/10.1080/00039890209601414
Olden, J., Jackson, D.: Illuminating the ‘black box’: a randomization approach for understanding variable contribution in artifical neural networks. Ecol. Model. 154, 135–150 (2002). https://doi.org/10.1016/S03033800(02)00064-9
Ruiz-Suarez, J., Mayora-Ibarra, O., Torres-Jimenez, J.: Short-term ozone forecasting by artificial neural networks. Adv. Eng. Softw. 23, 143–149 (1995). https://doi.org/10.1016/0965-9978(95)00076-3
Trigo, R.M., Palutikof, J.P.: Simulation of daily temperatures for climate change scenarios over Portugal: a neural network model approach. Climate Res. 13(1), 45–59 (1999). https://doi.org/10.3354/cr013045
World Health Organization, WHO (2016). http://www.who.int/airpollution
Zhang, J., Ding, W.: Prediction of air pollutants concentration based on an extreme learning machine: the case of Hong Kong. Int. J. Environ. Res. Public Health 14(2), 1–19 (2017). https://doi.org/10.3390/ijerph14020114
Acknowledgements
We acknowledge the Wilaya and the Region of the Souss Massa for their collaboration and supporting the Research, under the leadership of the Wali and the president of the region of Souss Massa, to whom we present our great and special thanks.
A special acknowledge is dedicated also to AGROTECH association and the “Institut Agronomique et Vétérinaire Hassan II. Complexe Horticole Agadir”.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Adnane, A., Leghrib, R., Chaoufi, J., Chirmata, A. (2023). Ambient Ozone Concentrations Modelling Using Feedforward Backpropagation Neural Networks: Spatial Modeling over the Agadir City (Morocco). In: Melliani, S., Castillo, O. (eds) Recent Advances in Fuzzy Sets Theory, Fractional Calculus, Dynamic Systems and Optimization. ICPAMS 2021. Lecture Notes in Networks and Systems, vol 476. Springer, Cham. https://doi.org/10.1007/978-3-031-12416-7_6
Download citation
DOI: https://doi.org/10.1007/978-3-031-12416-7_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-12415-0
Online ISBN: 978-3-031-12416-7
eBook Packages: EngineeringEngineering (R0)