The relative importance of drought-related and structural economic factors in explaining regional economic performance across Europe: an explainable machine-learning approach

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.

Authors

Publication Details

Journal
Environmental Data Science
Published
2026-11-19
DOI
https://doi.org/10.1017/eds.2026.10070
Primary Topic
Climate change impacts on agriculture
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

The relative importance of drought-related and structural economic factors in explaining regional economic performance across Europe: an explainable machine-learning approach

Kevin Bulthuis
1 links
Environmental Data Science
Climate change impacts on agriculture
article

The relative importance of drought-related and structural economic factors in explaining regional economic performance across Europe: an explainable machine-learning approach

Kevin Bulthuis
article en

Abstract

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.

Environmental Data ScienceVol. 5
Decent work and economic growth, Industry, innovation and infrastructure, Zero hunger, Climate action
Climate change impacts on agriculture
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon