Comparison of Different Artificial Neural Networks Techniques and Autoregressive Models for Forecasting of PM₁₀

Article type: Research Article

Authors: Yadav, Vibha^{; *} | Nath, Satyendra

Affiliations: Department of Environmental Sciences and NRM, College of Forestry, Sam Higginbottom University of Agriculture, Technology and Sciences, Allahabad – 211007, Uttar Pradesh, India

Correspondence: [*] Corresponding Author. [email protected]

Abstract: Atmospheric particulate matter (PM10) is one of the pollutant affecting human health significantly and has become a global issue. Data collected during three years in an urban area of Allahabad, Uttar Pradesh, India, are analysed and compared for 1-month ahead forecasting of PM10 using four models: Levenberg algorithm (LM) based artificial neural network (ANN), radial basis function neural network (RBFNN), generalized regression neural network (GRNN) and autoregressive (AR) model. Measured PM10 concentration are used as input to forecast the monthly averaged concentration of PM10 for one month ahead. The mean absolute percentage error (MAPE) for AR models varies from 10.20% to 32.78% whereas MAPE for ANN, RBFNN and GRNN are found 4.75%, 13.40% and 11.43% respectively, showing ANN model with LM algorithm forecast PM10 at one month ahead better than RBFNN, GRNN and AR models. In addition GRNN forecast is better than RBFNN with good accuracy. The average values of PM10 for Bharat Yantra Nigam Allahabad and Ardali Bazar Varanasi are found to be 182.16 and 262 respectively, showing Varanasi has high value of PM10. This study is useful for researcher working in forecasting of PM10.

Keywords: Artificial neural network, forecasting, PM₁₀, radial basis function neural network, generalized regression neural network and autoregressive model

DOI: 10.3233/AJW-180006

Journal: Asian Journal of Water, Environment and Pollution, vol. 15, no. 1, pp. 57-65, 2018