Design and synthesis of Time series forecasting and Deep Learning prediction model for Air Quality Index prediction in Indian Cities

Abstract

Modeling air quality by considering the complexities of randomness in pollutant concentrations and meteorological parameters to forecast real-time Air Quality Index to mitigate public health risks. Uncertainty of prediction exists due to high dimensional nature of predictor variables which results in designing an early warning system highly critical and challenging [10]. With the aim of ensuring accurate AQI forecasts, a statistical time series forecasting model namely Vector Auto Regression (VAR) and artificial neural network based Long Short-Term Memory (LSTM) are integrated together to form the Fusion Forecasting Model (FFM) referred to as PrediCasting. The proposed PrediCasting FFM (PCFFM) is tested with the air pollutant and meteorological data collected from the Central Pollution Control Board website for three major Indian cities namely Noida, Hyderabad and Vishakhapatnam. This work provides detailed analysis of forecasting Air Quality Index by considering the correlation between all factors of air pollutants and meteorological parameters. Results demonstrated that on an average, the proposed PCFFM model has reduced the Root Mean Square Error value by 13.18% and 29.07% for 7-days-a-head and 14-days-a-head forecast respectively. Compared to existing models, 7-days-a-head and 14-days-a-head forecast reduce Mean absolute Percentage Error (MaPE) on an average by 0.187 and 0.222, respectively.