A computational approach to analyzing climate strategies of cities pledging net zero

Abstract

Cities have become primary actors on climate change and are increasingly setting goals aimed at net-zero emissions, which warrants closer examination to understand how they intend to meet these goals. The incomplete and heterogeneous nature of city climate policy documents, however, has made systemic analysis challenging. We analyze 318 climate action documents from cities with net-zero targets using machine learning-based natural language processing (NLP) techniques. We aim to accomplish two goals: (1) determine text patterns that predict ‘ambitious’ net-zero targets; and (2) perform a sectoral analysis to identify patterns and trade-offs in climate action themes. We find that cities with ambitious climate actions tend to emphasize quantitative metrics and specific high-emitting sectors in their plans. Cities predominantly emphasize energy-related actions in their plans, but often at the expense of other sectors, including land-use and climate impacts. The method presented in this paper provides a replicable, scalable approach to analyzing climate action plans and a first step towards facilitating cross-city learning.

Unveiling urban governance diversity: Clustering cities based on mitigation actions

“…Critiques by scholars like Hughes et al ( 2019 ) and Gordon ( 2016 ) question the privileging of specific types of knowledge, such as energy use or emissions, accessible primarily to resourceful cities (Hughes et al 2019 ). Despite these limitations, previous studies have successfully employed CDP (Mokhles and Acuto 2024 ; Hsu and Rauber 2021 ; Sachdeva et al 2022 ).…”

“…Secondly, very few studies, such as that by Sachdeva et al ( 2022 ), have utilised cities’ climate actions, case studies, or action plans for meaningful city comparisons. Case studies or cities’ climate actions reflect cities’ socio-cultural contexts, and they can be used for city comparison and finding city typologies (Lamb et al 2019 ; Creutzig et al 2020 ).…”

“…Case studies or cities’ climate actions reflect cities’ socio-cultural contexts, and they can be used for city comparison and finding city typologies (Lamb et al 2019 ; Creutzig et al 2020 ). Sachdeva et al ( 2022 ) analysed 318 climate strategies or action plans of 315 cities with net-zero targets using NLP. While they presented an insight into the pattern of cities’ strategies based on the two constructed themes of ecology and infrastructure, their endeavour lacks a nuanced understanding of sectors and governance aspects of climate actions such as finance and implementation.…”