Work

A systematic map of machine learning for urban climate change mitigation

Year: 2025

Type: article

Abstract: To tackle the climate crisis, cities must reduce greenhouse gas (GHG) emissions rapidly. To aid these efforts, many cities are interested in leveraging artificial intelligence and machine learning (ML). Researchers and practitioners, however, only begin to understand how ML can contribute to achieving climate targets in urban contexts. To provide an overview of application areas, and the potential leverage of ML to reduce GHG emissions, we systematically map research conducted over the past three decades. We identify 1,206 relevant peer-reviewed records, and discover that research involving ML is expanding more rapidly than the literature on urban climate mitigation more broadly. The research focus largely aligns with urban mitigation options that the Intergovernmental Panel on Climate Change assessed as having high impact. We also find that research concentrates on the ML-strong regions Eastern Asia, Europe, and Northern America. This regional focus can influence research agendas, and we observed signs that this can lead to bias regarding which ML applications are pursued in urban climate action.

Source: Nature Cities

DOI: 10.1038/s44284-025-00328-5

Authors: Marie Josefine Hintz, Nikola Milojevic-Dupont, Felix Creutzig, Tim Repke, Lynn H. Kaack

Institutions: Hertie School, Technische Universität Berlin, Potsdam Institute for Climate Impact Research

Language: English

Topic: Urban Heat Island Mitigation

Subfield: Environmental Engineering

Field: Environmental Science

Domain: Physical Sciences

SDGs: Climate action, Sustainable cities and communities

Open Access status: hybrid

Estimated APC paid: $12,690