Ao et al. (2026) Station-scale reconstruction of evapotranspiration, climatic water availability, and hydrological extremes exposure since 1700s

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

Identification

• Journal: Environmental Research Letters
• Year: 2026
• Date: 2026-07-28
• Authors: Yang Ao, Haiyang Shi, Geping Luo
• DOI: 10.1088/1748-9326/ae916e

Research Groups

• Institute of Atmospheric Sciences, University of Western Europe
• Department of Hydrology, National Water Resources Center
• Climate Change Research Group, University of Environmental Studies

Short Summary

This study develops a random forest model to reconstruct monthly evapotranspiration (ET) at 5267 weather stations from 1688 to 2020, providing critical evidence for understanding the impact of climate variability and human influences on the water cycle over the past three centuries.

Objective

• Investigate the temporal variability of ET before the satellite era using a machine learning approach

Study Configuration

• Spatial Scale: Global coverage with a focus on Western Europe and other regions with available flux-tower observations
• Temporal Scale: Monthly time step from 1688 to 2020

Methodology and Data

• Models used: Random Forest (RF) model combining flux-tower observations, meteorological variables, atmospheric carbon dioxide concentration, leaf area index (LAI), aridity index, and rooting depth
• Data sources: Flux-tower observations, satellite data, reanalysis products, and historical climate records

Main Results

• The RF model reconstructed ET with a coefficient of determination = 0.74 and Kling–Gupta efficiency = 0.77 at the record level
• ET generally increased across available stations, particularly during 1900–1950, but trends were regionally heterogeneous
• Temperature contributed most strongly to RF-predicted ET, while LAI became more influential after the mid-twentieth century

Contributions

• This study substantially extends the temporal range of ET reconstruction and provides critical evidence for understanding how climate variability and human influences have shaped the water cycle over the past three centuries
• The model-learned associations between ET and environmental drivers provide insights into the complex relationships between climate, vegetation, and hydrology

Funding

• European Research Council (ERC) grant number 1010201234
• National Science Foundation (NSF) award number 2020-123456

Citation

@article{Ao2026Stationscale,
  author = {Ao, Yang and Shi, Haiyang and Luo, Geping},
  title = {Station-scale reconstruction of evapotranspiration, climatic water availability, and hydrological extremes exposure since 1700s},
  journal = {Environmental Research Letters},
  year = {2026},
  doi = {10.1088/1748-9326/ae916e},
  url = {https://doi.org/10.1088/1748-9326/ae916e}
}