A neural network approach to the environmental Kuznets curve

Mikkel Bennedsen; Eric Hillebrand; Sebastian Jensen

doi:10.1016/j.eneco.2023.106985

A neural network approach to the environmental Kuznets curve

Mikkel Bennedsen, Eric Hillebrand, Sebastian Jensen^*

^*Corresponding author af dette arbejde

Institut for Økonomi

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avis › Tidsskriftartikel › Forskning › peer review

6 Citationer (Scopus)

17 Downloads (Pure)

Abstract

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.

Originalsprog	Engelsk
Artikelnummer	106985
Tidsskrift	Energy Economics
Vol/bind	126
ISSN	0140-9883
DOI	https://doi.org/10.1016/j.eneco.2023.106985
Status	Udgivet - okt. 2023

Adgang til dokumentet

10.1016/j.eneco.2023.106985Licens: CC BY

1-s2.0-S0140988323004838-mainForlagets udgivne version, 4,46 MBLicens: CC BY

Citationsformater

@article{e7fbaa2b59384a4ca7098f7c66314ecb,

title = "A neural network approach to the environmental Kuznets curve",

abstract = "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.",

keywords = "Climate econometrics, Consumption-based carbon dioxide emissions, Environmental Kuznets curve, Machine learning, Neural networks, Panel data, Production-based carbon dioxide emissions",

author = "Mikkel Bennedsen and Eric Hillebrand and Sebastian Jensen",

note = "Publisher Copyright: {\textcopyright} 2023 The Author(s)",

year = "2023",

month = oct,

doi = "10.1016/j.eneco.2023.106985",

language = "English",

volume = "126",

journal = "Energy Economics",

issn = "0140-9883",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - A neural network approach to the environmental Kuznets curve

AU - Bennedsen, Mikkel

AU - Hillebrand, Eric

AU - Jensen, Sebastian

PY - 2023/10

Y1 - 2023/10

N2 - 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.

AB - 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.

KW - Climate econometrics

KW - Consumption-based carbon dioxide emissions

KW - Environmental Kuznets curve

KW - Machine learning

KW - Neural networks

KW - Panel data

KW - Production-based carbon dioxide emissions

U2 - 10.1016/j.eneco.2023.106985

DO - 10.1016/j.eneco.2023.106985

M3 - Journal article

AN - SCOPUS:85171622446

SN - 0140-9883

VL - 126

JO - Energy Economics

JF - Energy Economics

M1 - 106985

ER -

A neural network approach to the environmental Kuznets curve

Abstract

Adgang til dokumentet

Fingeraftryk

Citationsformater