Built Environment and Travel: Tackling Non-Linear Residential Self-Selection with Double Machine Learning

51 Pages Posted: 1 Aug 2024

See all articles by Florian Nachtigall

Florian Nachtigall

affiliation not provided to SSRN

Felix Wagner

affiliation not provided to SSRN

Peter Berrill

Leiden University

Felix Creutzig

Mercator Research Institute on Global Commons and Climate Change (MCC); Technical University Berlin Campus El Gouna

Abstract

Understanding how the built environment influences travel is key to low-carbon urban planning. However, previous cross-sectional studies lack a realistic operationalization of residential self-selection that accounts for its non-linear nature, limiting its applicability to urban planning. We propose a double machine learning (DML) approach that accounts for nonlinearities in residential self-selection and captures non-linear moderating effects.Using travel diaries of 32,201 Berlin residents, we estimate the built environment's impact on per capita travel-related CO2 emissions. Our results indicate that neglecting nonlinearities overestimates this impact by 13-18%, inflating the built environment proportion by 13%pt. Age, income, and car ownership also nonlinearly moderate the built environment's effect, with the effect being largest for middle-aged, high-income, car-owning households, a novel finding.Applying the method to urban planning reveals a 43%pt emissions reduction potential for 64,000 planned Berlin housing units, highlighting the need for informed urban planning to effectively mitigate CO2 emissions in cities.

Keywords: urban form, compact development, travel behavior, travel-related CO2 emissions, moderating effects, causal machine learning

Suggested Citation

Nachtigall, Florian and Wagner, Felix and Berrill, Peter and Creutzig, Felix, Built Environment and Travel: Tackling Non-Linear Residential Self-Selection with Double Machine Learning. Available at SSRN: https://ssrn.com/abstract=4912576 or http://dx.doi.org/10.2139/ssrn.4912576

Florian Nachtigall (Contact Author)

affiliation not provided to SSRN ( email )

No Address Available

Felix Wagner

affiliation not provided to SSRN ( email )

No Address Available

Peter Berrill

Leiden University ( email )

Postbus 9500
Leiden, 2300 RA
Netherlands

Felix Creutzig

Mercator Research Institute on Global Commons and Climate Change (MCC) ( email )

Torgauer Straße 12-15
Berlin, 10829
Germany

Technical University Berlin Campus El Gouna ( email )

Mohamed Ibrahim Kamel St.
Qesm Hurghada, Red Sea Governate 84513
Egypt

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
32
Abstract Views
164
PlumX Metrics