The relative importance of drought-related and structural economic factors in explaining regional economic performance across Europe: an explainable machine-learning approach
Environmental Data Science · 2026 · 5
DOI: 10.1017/eds.2026.10070 ↗Kurz gefasst
Fachartikel in der Zeitschrift Environmental Data Science, online erschienen am 19.11.2026. Verfasst von Kevin Bulthuis. Die Arbeit nennt 78 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The European Union (EU) exhibits spatial heterogeneity in economic structure and performance, reflecting historical development trajectories, sectoral composition, socio-economic conditions, and climatic variability. Among climatic stressors, drought challenges economic resilience, particularly in agriculture and manufacturing, which are sensitive to water availability, temperature extremes, and infrastructure constraints. In this study, we quantify the contributions of drought-related and socio-economic factors to regional gross value added (GVA) across NUTS3 regions in the EU. We integrate climatic indicators from the Copernicus European Drought Observatory with socio-economic data from Eurostat, and apply an eXtreme Gradient Boosting (XGBoost) model coupled with Shapley value–based interpretability methods to attribute sector-specific economic outcomes to individual features. Our analysis reveals spatial heterogeneity in the contributions of socio-economic and climatic factors to GVA. Variability in both agricultural and manufacturing GVA is predominantly explained by socio-economic factors. Agricultural GVA is influenced by the employment share in agriculture and regional area, reflecting the availability of labor and land resources, while manufacturing GVA is strongly associated with regional economic performance, as proxied by gross domestic product. Among climatic drivers, winter temperature—a factor for plant survival—explains the largest share of variability in agricultural GVA, with soil moisture and vegetation photosynthetic activity, used as proxies for productivity, also contributing. For manufacturing, median monthly maximum temperature emerges as the most influential climatic variable, with soil moisture and photosynthetic activity contributing as secondary predictors. However, these climatic associations likely reflect spatial covariation with regional characteristics rather than direct causal impacts of climate on production processes.
Zitieren
APA
Bulthuis, K. (2026). The relative importance of drought-related and structural economic factors in explaining regional economic performance across Europe: an explainable machine-learning approach. Environmental Data Science, 5. https://doi.org/10.1017/eds.2026.10070
Vancouver
Bulthuis K. The relative importance of drought-related and structural economic factors in explaining regional economic performance across Europe: an explainable machine-learning approach. Environmental Data Science. 2026;5. doi:10.1017/eds.2026.10070
BibTeX
@article{Bulthuis2026,
author = {Bulthuis, Kevin},
title = {The relative importance of drought-related and structural economic factors in explaining regional economic performance across Europe: an explainable machine-learning approach},
journal = {Environmental Data Science},
year = {2026},
volume = {5},
doi = {10.1017/eds.2026.10070}
}
EUVIMED