A machine learning process for examining the linkage among disaggregated energy consumption, economic growth, and environmental degradation. (December 2022)

• Record Type: Journal Article
• Authors: Kahia, Montassar; Moulahi, Tarek; Mahfoudhi, Sami; Boubaker, Sabri; Omri, Anis
• Is Part Of: Resources policy. Volume 79(2022)
• Publication Date: 2022-12
• Subjects: Machine learning -- (non)-renewable consumption -- Environmental quality -- Economic growth; Mines and mineral resources -- Periodicals; Ressources minérales -- Périodiques; Ressources naturelles -- Gestion -- Périodiques; Environnement -- Politique gouvernementale -- Périodiques; 333.8
• DOI: 10.1016/j.resourpol.2022.103104
• Languages: English
• ISSNs: 0301-4207

Abstract

Abstract: Improving environmental quality is at the heart of the Saudi Vision 2030. Within this context, this study seeks to extend previous environmental economics literature by examining the relationship between disaggregated energy use, economic growth, and environmental quality in Saudi Arabia using machine learning (ML) techniques. Using data from 1980 to 2020, we found that reducing CO2 emissions cannot be done in Saudi Arabia without a complete transition from fossil to renewable resources and a more viable road to sustainability. ML-based regression and prediction shows that CO2 emissions will continue to grow until 2024. Beginning in 2025 and beyond, the emissions decrease (i.e., reducing CO2 emissions) must be accompanied by an increment use of renewable energies to guarantee stable economic growth. Highlights: We examine the linkage between disaggregated energy consumption, economic growth, and CO2 emissions (CO). We apply Machine Learning (ML) techniques to predict the causal links between variables. Reducing CO cannot be done without a complete shift from fossil to renewable energy (RE). Reducing CO in the next upcoming years must be accompanied by an increment use of RE to guarantee a stable GDP.