Evaluation of hybrid deep learning approaches for air pollution forecasting

This paper aims at applying different architectures of hybrid deep learning methods and an RBF (Radial Basis Functions)-based approach, with a comparison to traditional deep learning models, for air pollution forecasting which is the key of the air quality control management. The hybrid deep learning models are based on the combination between 1D convolutional neural network which prove during the research literature its excellent ability for features extraction, with recurrent neural network (RNN) which is appropriated for prediction tasks. The RBF-based approach is another way of approximating a nonlinear autoregressive model, using that RBF are powerful interpolation tool. The traditional deep learning methods used for comparison in this work are the simple RNN and the NARMAX model (Non-Linear AutoRegressive Moving Average with eXogenous inputs). The prediction methods are based on a real data base of pollutant concentrations and other influencing environmental air quality parameters (temperature, humidity, pressure, wind speed and wind direction) tested for different locations. All available data values are hourly recorded. As a result of this research work, it was proven that the hybrid deep learning architectures succeeded to provide the best forecasting results based on different errors measurements used as comparison criteria between all the proposed methods.