Comparison of classical statistical models for forecasting CO₂ emissions, GDP, and TBL cancer indicators: A comparative analysis of East and West Asia

Read full text
Authors: Seyed Mohieddin Moezzi, Mohammadali Allahrabbi Shirazi, Alireza Rajabi Zadeh Monfared, Hossein Yousefi
Cited by: 7
References: 59

Abstract

This study analyzes and forecasts economic, environmental, and health indicators in West Asian and East Asian countries. The innovation of this study is the combination of health parameters related to respiratory diseases (cancer) with economic parameters and air pollution, and the use of artificial intelligence models for long-term forecasting of these indicators. The main objective of this study was to develop and compare four AI-based models for forecasting GDP, CO 2 emissions, and TBL cancer in selected countries from West and East Asia until 2040. After comparing the models using error measures such as RMSE, MAE, and MAPE, the ARIMA model was selected as the best model. The results of the forecast for one of the West Asian countries until 2040 show that the ARIMA model with RMSE errors of 0.1236 in CO 2 emissions, 747.26 in GDP, and 1140.81 in TBL cancer was selected as the best model. The forecast results show that East Asian countries, especially China, have had significant growth in all indicators, especially in CO 2 emissions and GDP, so that in CO 2 emissions, the growth in East Asia has reached 245.5%, while this value in West Asia has been 96.65%. Also, the growth of TBL cancer and GDP in East Asian countries has been faster than that in West Asia. China has experienced significant growth in all three indicators. This study can help researchers and decision-makers adopt better policies in the fields of public health and sustainable development by increasing awareness of future trends.

Fields of Study & Subjects

COVID-19 impact on air quality Energy Environment Economic Growth Innovation Diffusion and Forecasting

Publication details

Journal / source
Energy Nexus
Publisher
Elsevier BV
Volume
21
Pages
100682–100682
Publication date
10 February 2026
Language
EN