EconBase
← All papers

Feature Importance of Climate Vulnerability Indicators with Gradient Boosting across Five Global Cities

Lidia Cano Pecharroman, Melissa O. Tier, Elke U. Weber

arXiv 15 Nov 2024 · Econometrics · publishedFrontiers in Climate (2025) · 2 citations (OpenAlex)

arXiv:2411.10628 · PDF · DOI · OpenAlex · Extracted main text

Abstract

Efforts are needed to identify and measure both communities' exposure to climate hazards and the social vulnerabilities that interact with these hazards, but the science of validating hazard vulnerability indicators is still in its infancy. Progress is needed to improve: 1) the selection of variables that are used as proxies to represent hazard vulnerability; 2) the applicability and scale for which these indicators are intended, including their transnational applicability. We administered an international urban survey in Buenos Aires, Argentina; Johannesburg, South Africa; London, United Kingdom; New York City, United States; and Seoul, South Korea in order to collect data on exposure to various types of extreme weather events, socioeconomic characteristics commonly used as proxies for vulnerability (i.e., income, education level, gender, and age), and additional characteristics not often included in existing composite indices (i.e., queer identity, disability identity, non-dominant primary language, and self-perceptions of both discrimination and vulnerability to flood risk). We then use feature importance analysis with gradient-boosted decision trees to measure the importance that these variables have in predicting exposure to various types of extreme weather events. Our results show that non-traditional variables were more relevant to self-reported exposure to extreme weather events than traditionally employed variables such as income or age. Furthermore, differences in variable relevance across different types of hazards and across urban contexts suggest that vulnerability indicators need to be fit to context and should not be used in a one-size-fits-all fashion.

Citation extraction

37
references
51
in-text mentions
37
distinct cited
0
self-citations
6,575
main-text words

appendix boundary found by none_found · 100% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1B. Wilson, E. Tate, and C. T. Emrich (2021) Flood recovery outcomes and disaster assistance barriers for vulnerable populations0.81142100%
2I. Ajibade, M. Sullivan, C. Lower, L. Yarina, and A. Reilly (2022) Are managed retreat programs successful and just? a global mapping of success typologies, justice dimensions, and trade-offs0.73732100%
3T. Chen and C. Guestrin (2016) XGBoost: A scalable tree boosting system0.64422100%
4NASEM (2024) Constructing Valid Geospatial Tools for Environmental Justice0.58531100%
5A. R. Siders and L. Gerber-Chavez (2021) Floodplain buyouts: Challenges, practices, and lessons learned0.58531100%
6S. R. Foster, A. Baptista, K. H. Nguyen, J. Tchen, M. Tedesco, and R… NPCC4: Advancing climate justice in climate adaptation strategies for new york city0.51121100%
7A. Greer, S. Brokopp Binder, and E. Zavar (2022) From hazard mitigation to climate adaptation: A review of home buyout program literature0.51121100%
8K. J. Mach, C. M. Kraan, M. Hino, A. R. Siders, E. M. Johnston, and… (2019) Managed retreat through voluntary buyouts of flood-prone properties0.51121100%
9A. Weber and R. Moore (2019) Going under: Long wait times for post-flood buyouts leave homeowners underwater0.51121100%
10J. H. Friedman (2001) Greedy function approximation: A gradient boosting machine0.40511100%

Showing the top 10 of 37 scored citations.