Forecasting CO2 Emissions in Saudi Arabia Using Artificial Neural Network, Holt-Winters Exponential Smoothing, and Autoregressive Integrated Moving Average Models

Abstract

Forecasting models are critical tools for achieving economic development and policy-making in a country. The main goal of this study is to forecast CO2 emissions in the kingdom of Saudi Arabia. In this study, Saudi Arabia’s CO2 emissions are predicted using models of the Artificial Neural Network (ANN), Holt-Winters Exponential Smoothing (H-W), and Autoregressive Integrated Moving Average (ARIMA). This research uses statistical software to forecast time series data using ANN, H-W, and ARIMA models on the Kingdom of Saudi Arabia’s CO2 emissions from 1960 to 2014. In addition, this study shows the forecast model accuracy using various accuracy measures. The ARIMA (2,1,2) model is found to be suitable for predicting the CO2 emissions of the Kingdom of Saudi Arabia. This study also aims to clarify the current state of CO2 emissions. This study will assist the researcher in better understanding CO2 emission forecasts. In addition, government entities can use the findings of this study to establish strategic plans.