A neural network approach to the environmental Kuznets curve

We investigate the relationship between per capita gross domestic product and per capita carbon dioxide emissions using national-level panel data for the period 1960-2018. We propose a novel semiparametric panel data methodology that combines country and time fixed effects with a nonparametric neural network regression component. Globally and for the regions OECD and Asia, we find evidence of an inverse U-shaped relationship, often referred to as an environmental Kuznets curve (EKC), in production-based emissions. For OECD, the EKC-shape disappears when using consumption-based emissions data, suggesting the EKC-shape observed for OECD is driven by emissions exports. For Asia, the EKC-shape becomes even more pronounced when using consumption-based emissions data and exhibits an earlier turning point.

Automated summary

This study examines the relationship between per capita gross domestic product (GDP) and per capita carbon dioxide (CO2) emissions using national-level panel data from 1960 to 2018. The findings suggest the presence of an inverse U-shaped relationship, known as the environmental Kuznets curve (EKC), in production-based emissions globally and for the OECD and Asia regions. However, the EKC shape disappears for the OECD when consumption-based emissions data is used, indicating that the observed EKC shape for the OECD is driven by emissions exports. For Asia, the EKC shape becomes even more pronounced when consumption-based emissions data is considered, with an earlier turning point.