Using machine learning to understand causal relationships between urban form and travel CO2 emissions across continents

• Published in: arXiv.org
• Main Authors: Wagner, Felix, Nachtigall, Florian, Franken, Lukas, Milojevic-Dupont, Nikola, Pereira, Rafael H M, Koch, Nicolas, Runge, Jakob, Gonzalez, Marta, Creutzig, Felix
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 15.12.2023
• Subjects: Carbon content; Cities; City centres; Continents; Demographics; High resolution; Infrastructure; Machine learning; Spatial resolution; Transportation systems; Urban development; Urban transportation

Climate change mitigation in urban mobility requires policies reconfiguring urban form to increase accessibility and facilitate low-carbon modes of transport. However, current policy research has insufficiently assessed urban form effects on car travel at three levels: (1) Causality -- Can causality be established beyond theoretical and correlation-based analyses? (2) Generalizability -- Do relationships hold across different cities and world regions? (3) Context specificity -- How do relationships vary across neighborhoods of a city? Here, we address all three gaps via causal graph discovery and explainable machine learning to detect urban form effects on intra-city car travel, based on mobility data of six cities across three continents. We find significant causal effects of urban form on trip emissions and inter-feature effects, which had been neglected in previous work. Our results demonstrate that destination accessibility matters most overall, while low density and low connectivity also sharply increase CO\(_2\) emissions. These general trends are similar across cities but we find idiosyncratic effects that can lead to substantially different recommendations. In more monocentric cities, we identify spatial corridors -- about 10--50 km from the city center -- where subcenter-oriented development is more relevant than increased access to the main center. Our work demonstrates a novel application of machine learning that enables new research addressing the needs of causality, generalizability, and contextual specificity for scaling evidence-based urban climate solutions.