Summary
This observation-driven study used artificial neural networks and random forest models informed by ground observations and atmospheric boundary layer theory to retrieve consistent global long-term evapotranspiration data. The analysis demonstrates that recent global land evapotranspiration has increased significantly, with increasing temperature as the primary driver, particularly in humid regions including the tropics. The findings provide empirical constraints on evapotranspiration responses to climate warming and have implications for understanding terrestrial water cycles under changing environmental conditions.
Regional applicability
The global nature of this study provides context for understanding how climate warming affects hydrological cycles relevant to United Kingdom water resources and agricultural systems. However, the study highlights that ET increases are concentrated in humid tropical regions, so direct applicability to United Kingdom temperate grassland and arable systems may be limited; regional modelling would be needed to assess local implications.
Key measures
Latent heat flux (ET in energy units), sensible heat flux, global land evapotranspiration trends over recent decades
Outcomes reported
The study quantified global land evapotranspiration (ET) changes over recent decades using machine learning models informed by ground observations. It found that recent global land ET has increased significantly, with increasing temperature as the primary driver, particularly in humid tropical regions.
Topic tags
Dig deeper with Pulse AI.
Pulse AI has read the whole catalogue. Ask about this record, its theme, or how the findings apply to UK farming and policy — every answer cites the underlying studies.