Spatiotemporal Dynamics of Active Root Zone Storage Revealed From Hybrid Machine Learning
Water Resources Research · 2026-10 · 62 (10)
DOI: 10.1029/2025wr042803 ↗Kurz gefasst
Fachartikel in der Zeitschrift Water Resources Research, online erschienen am 10.10.2026. Verfasst von Georgios Blougouras und 9 weiteren Autor:innen. Die Arbeit nennt 110 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Carl-Zeiss-Stiftung.
Abstract (Originalsprache)
Water within the root zone regulates water, energy, and carbon exchanges at the land‐atmosphere interface, yet the dynamically active portion of subsurface water that ecosystems mobilize for evapotranspiration (ET) remains unclear, because it represents only part of the total subsurface storage. To address this gap, we develop a catchment‐scale, ecosystem‐oriented hybrid machine learning model that integrates a parsimonious ecohydrological structure with data‐driven flexibility to infer time‐varying active root zone storage (a S rz ) as a latent state variable. Without prescribing rooting depth or soil layers, the model learns adaptive water partitioning from multi‐source observations of ET, runoff, snow, and terrestrial water storage, enabling diagnosis of both dynamic a S rz and its realized capacity. Applied across hundreds of U.S. catchments over the period 2001–2020, the framework reveals coherent spatial and hydroclimatic patterns, with a S rz peaking in transitional regions where atmospheric demand and water supply are balanced. The realized capacity reflects how belowground water access varies with long‐term hydroclimatic and substrate constraints. We further show that defining storage as a realized quantity through system dynamics improves stability and interpretability under varying observational and structural conditions. Overall, this study demonstrates how hybrid modeling can be used to diagnose ecosystem‐accessible water storage as a latent state, providing a physically consistent and observation‐informed pathway to quantify belowground processes that remain inaccessible to direct measurement and control key land‐atmosphere interactions.
Förderung
- Carl-Zeiss-Stiftung
Zitieren
APA
Blougouras, G., Jiang, S., Brenning, A., Migliavacca, M., Slater, L., Zhou, J., Kumar, R., Tian, L., Wang, C., & Reichstein, M. (2026). Spatiotemporal Dynamics of Active Root Zone Storage Revealed From Hybrid Machine Learning. Water Resources Research, 62(10). https://doi.org/10.1029/2025wr042803
Vancouver
Blougouras G, Jiang S, Brenning A, Migliavacca M, Slater L, Zhou J, et al. Spatiotemporal Dynamics of Active Root Zone Storage Revealed From Hybrid Machine Learning. Water Resources Research. 2026;62(10). doi:10.1029/2025wr042803
BibTeX
@article{Blougouras2026,
author = {Blougouras, Georgios and Jiang, Shijie and Brenning, Alexander and Migliavacca, Mirco and Slater, Louise and Zhou, Jialiang and Kumar, Rohini and Tian, Lu and Wang, Chao and Reichstein, Markus},
title = {Spatiotemporal Dynamics of Active Root Zone Storage Revealed From Hybrid Machine Learning},
journal = {Water Resources Research},
year = {2026},
volume = {62},
number = {10},
doi = {10.1029/2025wr042803}
}
EUVIMED