Part of #Ozone Level Forecasting: Time Series Analysis Using Multi-Layer Perceptron (MLP) Artificial Neural Networks Trained with Bayesian Regulation Back-propagation# :
Publishing year : 2016
Conference : The 2nd International Conference on New Findings in Chemistry and Chemical Engineering
Number of pages : 8
Abstract: Concerns of tropospheric ozone effects on human life motivate decision makers to predict ozone concentration especially in metropolitan and tropic regions. Due to the nonlinearity of ozone variations, using neural networks methods is considered a proper tool for predicting air quality. This paper proposes a multi-layer perceptron (MLP) model trained with a Bayesian Regulation Back-Propagation (BRP) algorithm for predicting maximum daily ozone concentrations in Tucson city. The performance of the proposed model trained with BRP algorithm shows better results than other training algorithms in Which is a reason of our claim for the R = 0.9627 (Pearson correlation coefficient) for measured and predicted data and the coordination between their errors and the standard normal distribution curve. The results obtained confirm that the proposed model has a fair ozone concentration time series forecasting.