Forecasting of PM 10 Using Autoregressive Models and Exponential Smoothing Technique

Abstract

Particulate matter with 10 μm or less in diameter (PM₁₀) have adverse effects on environment and human health. To reduce PM₁₀ emissions in India, it is essential to have models that accurately estimate and predict PM₁₀ concentrations for reporting and monitoring purposes. In this paper Exponential Smoothing Technique and Autoregressive (AR) models are developed to forecast 1-month ahead value of PM₁₀ for Allahabad city which is novelty of this study. AR (1) and AR (5) models are developed using Burge and Yule Walker methods. The mean absolute percentage error (MAPE) for Burge method in AR (1) and AR (5) are 14.23% and 10.20%. The MAPE for Yule Walker method in AR (1) and AR (5) are 32.72% and 31.13%. The MAPE in Exponential Smoothing Technique is 5.81% which shows it forecasts better than AR model based on Burge and Yule Walker methods. It is found that Burge Method in AR (5) has less MAPE than Yule Walker Method. Therefore Exponential Smoothing Technique can be used to forecast PM₁₀ for cities in India, showing it is beneficial for giving prior information for human health.