Zhao et al. (2026) Meteorological Triggers of Regionally Extreme Atmospheric Evaporative Demand Across Global Land: Attribution With Adversarial Random Forests

⚠️ Warning: This summary was generated from the abstract only, as the full text was not available.

Identification

• Journal: Earth s Future
• Year: 2026
• Date: 2026-09-01
• Authors: Bingjie Zhao, Abrielle Mannino, Christopher Horvat
• DOI: 10.1029/2026ef009156

Research Groups

[Information not available in the provided abstract.]

Short Summary

This study develops a physically constrained counterfactual attribution framework combining the FAO56 Penman–Monteith equation with adversarial random forests to quantify the meteorological drivers of regionally extreme atmospheric evaporative demand (AED) globally, revealing that dominant trigger mechanisms vary systematically across hydroclimatic regimes.

Objective

• To quantify the relative contributions of main meteorological drivers to regionally extreme atmospheric evaporative demand (AED) across global land regions, while preserving the dependence among correlated drivers.

Study Configuration

• Spatial Scale: Global land regions, analyzed on equal-area grids.
• Temporal Scale: 40 years (1986–2025) of daily data.

Methodology and Data

• Models used: FAO56 Penman–Monteith equation, adversarial random forests (ARF) for counterfactual attribution, complementary Shapley-value attribution for long-term trends.
• Data sources: ERA5‐Land daily reanalysis data.

Main Results

• Dominant meteorological trigger mechanisms for extreme AED vary systematically across hydroclimatic regimes.
• In humid tropical regions, extreme AED is primarily triggered by enhanced shortwave radiation under anomalously clear-sky conditions.
• In many arid and semi-arid regions, wind speed dominates as a trigger, amplified by large background vapor pressure deficits.
• Long-term trends in mean AED are dominated by rising air temperature across most regions, as shown by Shapley-value attribution.
• The slow warming-driven background "push" on mean AED often differs from the more regionally diverse meteorological "triggers" that drive AED beyond its extreme threshold.

Contributions

• Development of a novel physically constrained counterfactual attribution framework using adversarial random forests that reduces bias in contribution estimates by preserving dependence among correlated meteorological drivers.
• Global-scale quantification and systematic mapping of the regionally varying meteorological triggers of extreme AED.
• Differentiation between the meteorological triggers of extreme AED events and the drivers of long-term trends in mean AED.
• Demonstration of the ARF-based framework as a generalizable approach for quantifying variable contributions to extreme events.

Funding

[Information not available in the provided abstract.]

Citation

@article{Zhao2026Meteorological,
  author = {Zhao, Bingjie and Mannino, Abrielle and Horvat, Christopher},
  title = {Meteorological Triggers of Regionally Extreme Atmospheric Evaporative Demand Across Global Land: Attribution With Adversarial Random Forests},
  journal = {Earth s Future},
  year = {2026},
  doi = {10.1029/2026ef009156},
  url = {https://doi.org/10.1029/2026ef009156}
}