MLP based predictive model for surface ozone concentration over an urban area in the Gangetic West Bengal during pre-monsoon season

Abstract The present paper reports a comparative study among two neurocomputing models in the form of Multilayer Perceptron (MLP) models and non-linear regression for the prediction of surface ozone (O3) during pre-monsoon season over Gangetic West Bengal (GWB), India considering NOx, SO2, PM10 and temperature as predictors. Learning the MLPs through gradient descent (GD) with tanhyperbolic and sigmoid nonlinearities, we found that all the models under consideration have almost the same degrees of prediction efficiency for O3 over GWB during pre-monsoon season with the said predictors. However, the MLP model with tanhyperbolic activation function is found to produce a significantly higher correlation and Willmott's index of agreement between actual and predicted O3 than the other models. Finally, MLP with GD learning characterized by tanhyperbolic nonlinearity is identified to have significant efficiency in surface ozone prediction over the region as mentioned above.

[1]  K. Mohanakumar.  Stratosphere Troposphere Interactions: An Introduction , 2008 .

[2]  Elena Paoletti,et al.  Ozone levels in European and USA cities are increasing more than at rural sites, while peak values are decreasing. , 2014, Environmental pollution.

[3]  David G. Streets,et al.  Linking ozone pollution and climate change: The case for controlling methane , 2002 .

[4]  K. Clemitshaw,et al.  Ozone and other secondary photochemical pollutants: chemical processes governing their formation in the planetary boundary layer , 2000 .

[5]  D. Rosenfeld,et al.  A possible new molecular mechanism of thundercloud electrification , 2005 .

[6]  B. Yegnanarayana,et al.  Artificial Neural Networks , 2004 .

[7]  P Wolkoff,et al.  Chemical and biological evaluation of a reaction mixture of R-(+)-limonene/ozone: formation of strong airway irritants. , 2001, Environment international.

[8]  R. Harrison,et al.  Ozone-secondary aerosol-visibility relationships in North-West England , 1984 .

[9]  Soteris A. Kalogirou,et al.  Artificial neural networks in renewable energy systems applications: a review , 2001 .

[10]  Surajit Chattopadhyay,et al.  Conjugate gradient descent learned ANN for Indian summer monsoon rainfall and efficiency assessment through Shannon-Fano coding , 2018, Journal of Atmospheric and Solar-Terrestrial Physics.

[11]  Raúl Rojas,et al.  Neural Networks - A Systematic Introduction , 1996 .

[12]  Baoning Zhang,et al.  Photochemical smog pollution in the Bangkok Metropolitan Region of Thailand in relation to O3 precursor concentrations and meteorological conditions , 2002 .

[13]  M. W Gardner,et al.  Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences , 1998 .

[14]  I. K. Larissi,et al.  Development and Application of Artificial Neural Network Modeling in Forecasting PM10 Levels in a Mediterranean City , 2013, Water, Air, & Soil Pollution.

[15]  F. Palmgren,et al.  To be presented at Trafikdage på AUC Aalborg, August 21-22 1995 URBAN AIR POLLUTION OF NITROGEN OXIDES FROM TRAFFIC , 1996 .

[16]  Surajit Chattopadhyay,et al.  Comparative study among different neural net learning algorithms applied to rainfall time series , 2008 .

[17]  J. Murphy,et al.  Long term changes in nitrogen oxides and volatile organic compounds in Toronto and the challenges facing local ozone control , 2009 .

[18]  A. Sheta,et al.  Forecasting ozone concentrations in the east of Croatia using nonparametric Neural Network Models , 2016, Journal of Earth System Science.

[19]  Kamal Ahmed,et al.  Multilayer perceptron neural network for downscaling rainfall in arid region: A case study of Baluchistan, Pakistan , 2015, Journal of Earth System Science.

[20]  Georgios Grivas,et al.  Artificial neural network models for prediction of PM10 hourly concentrations, in the Greater Area of Athens, Greece , 2006 .

[21]  Paolo Bonasoni,et al.  Aerosol-ozone correlations during dust transport episodes , 2004 .

[22]  Effect of cloud occurrences on tropospheric ozone over, Alipore (22.52°N, 88.33°E), India , 2012, Journal of Earth System Science.

[23]  A. V. Olgac,et al.  Performance Analysis of Various Activation Functions in Generalized MLP Architectures of Neural Networks , 2011 .

[24]  C. Varotsos,et al.  Global total ozone dynamics , 1996, Environmental science and pollution research international.

[25]  A. Ravishankara,et al.  Nitrous Oxide (N2O): The Dominant Ozone-Depleting Substance Emitted in the 21st Century , 2009, Science.

[26]  Costas Varotsos,et al.  The southern hemisphere ozone hole split in 2002 , 2002, Environmental science and pollution research international.

[27]  C. Willmott.  Some Comments on the Evaluation of Model Performance , 1982 .

[28]  J. Seinfeld,et al.  Atmospheric Chemistry and Physics: From Air Pollution to Climate Change , 1997 .

[29]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[30]  V. Rakov,et al.  Lightning: Physics and Effects , 2007 .