Factors affecting per capita ecological footprint in OECD countries: Evidence from machine learning techniques a

Görüş M. Ş., Karagol E. T.

Energy and Environment, vol.34, no.7, pp.2601-2618, 2023 (SSCI) identifier identifier

  • Publication Type: Article / Article
  • Volume: 34 Issue: 7
  • Publication Date: 2023
  • Doi Number: 10.1177/0958305x221112913
  • Journal Name: Energy and Environment
  • Journal Indexes: Social Sciences Citation Index (SSCI), Scopus, PASCAL, Aerospace Database, Communication Abstracts, Compendex, Environment Index, Geobase, Greenfile, INSPEC, Metadex, Pollution Abstracts, Civil Engineering Abstracts
  • Page Numbers: pp.2601-2618
  • Keywords: OECD countries, random forest algorithm, partial dependence plots, globalization, disaggregated energy consumption, ecological footprint
  • Ankara Yıldırım Beyazıt University Affiliated: Yes

Abstract

For a few decades, factors affecting environmental deterioration have been at the center of much interest This paper examines the impact of income level, disaggregated energy consumption, types of globalization level, and urbanization on per capita ecological footprint by utilizing novel machine learning techniques (tree regression, boosting, bagging, and random forest) for 27 OECD countries during 1971–2016. It is found that the random forest algorithms best fit the dataset. The empirical results exhibit that oil product consumption, electricity consumption, and gross domestic product are the most significant variables for our model. Besides, the partial dependence plots results show that economic growth and especially fossil fuel energy consumption damage the environment. These findings have important implications for both developed and developing countries for designing proper energy and environmental policies. Especially, policymakers should focus on sustainable development instead of plain economic growth.