Hybrid modeling of evapotranspiration
Inferring stomatal and aerodynamic resistances using combined physics-based and machine learning
Bibliographic Data
| ID | 15544645 |
|---|---|
| Authors | Reda ElGhawi (0000-0003-2930-4537, Technical University of Munich, corresponding author), Basil Kraft (0000-0002-8491-2730, Max Planck Institute for Biogeochemistry), Christian Reimers (0000-0003-1127-136X, Max Planck Institute for Biogeochemistry), Markus Reichstein (0000-0001-5736-1112, Max Planck Institute for Biogeochemistry), Mirjam Körner (0000-0002-9186-4175, Technical University of Munich), Pierre Gentine (0000-0002-0845-8345, Columbia University), Alexander J Winkler (0000-0001-6574-4471, Max Planck Institute for Biogeochemistry, corresponding author) |
| Year | 2023 |
| Volume | 18 |
| Issue | 3 |
| Pages | 034039-034039 |
| Publication date | 2023-03-01 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Environmental Research Letters (JOURNAL) |
| Journal identifiers | ISSN: 1748-9326 • E-ISSN: 1748-9326 |
| Publisher | IOP Publishing (PUBLISHER • GB) |
| DOI | 10.1088/1748-9326/acbbe0 |
| OpenAlex | W4323364979 |
| Language | EN |
| Citations received | 1 |
| References cited | 62 |
The process of evapotranspiration transfers liquid water from vegetation and soil surfaces to the atmosphere, the so-called latent heat flux ( Q LE ), and modulates the Earth’s energy, water, and carbon cycle. Vegetation controls Q LE by regulating leaf stomata opening (surface resistance r s in the Big Leaf approach) and by altering surface roughness (aerodynamic resistance r a ). Estimating r s and r a across different vegetation types is a key challenge in predicting Q LE . We propose a hybrid approach that combines mechanistic modeling and machine learning for modeling Q LE . The hybrid model combines a feed-forward neural network which estimates the resistances from observations as intermediate variables and a mechanistic model in an end-to-end setting. In the hybrid modeling setup, we make use of the Penman–Monteith equation in conjunction with multi-year flux measurements across different forest and grassland sites from the FLUXNET database. This hybrid model setup is successful in predicting Q LE , however, this approach leads to equifinal solutions in terms of estimated physical parameters. We follow two different strategies to constrain the hybrid model and therefore control for the equifinality that arises when the two resistances are estimated simultaneously. One strategy is to impose an a priori constraint on r a based on mechanistic assumptions (theory-driven strategy), while the other strategy makes use of more observational data and adds a constraint in predicting r a through multi-task learning of both latent and sensible heat flux ( <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" ov
Algorithm · Machine learning · Computer Science · Greenhouse Technology and Climate Control · Meteorological Phenomena and Simulations · Plant Water Relations and Carbon Dynamics · Artificial Intelligence
Recent decline in the global land evapotranspiration trend due to limited moisture supply
Deep learning and process understanding for data-driven Earth system science
Natural evaporation from open water, bare soil and grass
Land-surface evapotranspiration derived from a first-principles primary production model
Evaluation and machine learning improvement of global hydrological model-based flood simulations
| Unique citing works | 1 |
|---|---|
| Citations per year | 0,5 |
| Citation span | 2024 - 2024 (1) |
| Citation velocity | recent |
| Highly cited | No |
| Citation types | Neutral: 1 |