Details zur Publikation |
| Kategorie | Textpublikation |
| Referenztyp | Zeitschriften |
| DOI | 10.1029/2025GL121483 |
Lizenz  |
|
| Titel (primär) | Understanding the influence of soil moisture on machine learning predictions of photosynthesis and evapotranspiration |
| Autor | Power, D.; Rico-Ramirez, M.A.; Gentine, P.; McJannet, D.; Schrön, M.; Rebmann, C.; da Rocha, H.; Rosolem, R. |
| Quelle | Geophysical Research Letters |
| Erscheinungsjahr | 2026 |
| Department | MET |
| Band/Volume | 53 |
| Heft | 9 |
| Seite von | e2025GL121483 |
| Sprache | englisch |
| Topic | T5 Future Landscapes |
| Daten-/Softwarelinks | https://doi.org/10.1594/PANGAEA.940759 https://doi.org/10.17190/AMF/1245971 https://doi.org/10.17190/AMF/1246027 https://doi.org/10.17190/AMF/1246076 https://doi.org/10.17190/AMF/1246080 https://doi.org/10.17190/AMF/1246081 https://doi.org/10.17190/AMF/1246086 https://doi.org/10.17190/AMF/1246112 https://doi.org/10.17190/AMF/1246113 https://doi.org/10.17190/AMF/1246127 https://doi.org/10.17190/AMF/1419501 https://doi.org/10.17190/AMF/1419504 https://doi.org/10.34731/x9s3-kr48 https://doi.org/10.5281/zenodo.11147410 https://doi.org/10.5281/zenodo.6828595 https://doi.org/10.5523/bris.qb8ujazzda0s2aykkv0oq0ctp |
| Supplements | Supplement 1 |
| Keywords | soil moisture; land atmosphere processes; machine learning; evapotranspiration |
| Abstract | Evapotranspiration (ET) and photosynthesis are key processes in ecosystem functioning on which soil moisture (SM) has an important influence. Eddy covariance measurements and machine learning (ML) increasingly enable flux prediction in ungauged regions. With numerous SM estimation methods available, each representing different spatiotemporal scales, understanding how data choice influences ML predictions is important. Our study examines how different SM data affect ML predictions of ET and photosynthesis. At semi-arid to arid sites, we found that in situ near-surface SM enhances ML predictions of ET. For photosynthesis, SM memory, indicative of deeper SM control, shows the highest predictive power, improving predictions by up to 30% at the driest sites. These contrasting responses reveal that ET and Gross Primary Productivity (GPP) are likely governed by distinct SM mechanisms: spatial scale matching for ET and temporal depth for GPP. Our study demonstrates that process-guided feature engineering can improve ML predictions where root-zone SM observations are often unavailable. |
| Power, D., Rico-Ramirez, M.A., Gentine, P., McJannet, D., Schrön, M., Rebmann, C., da Rocha, H., Rosolem, R. (2026): Understanding the influence of soil moisture on machine learning predictions of photosynthesis and evapotranspiration Geophys. Res. Lett. 53 (9), e2025GL121483 10.1029/2025GL121483 |
|