EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Spatio‐Temporal Machine Learning for Regional to Continental Scale Terrestrial Hydrology

Andrew Bennett, Hoang Tran, Luis De la Fuente, Amanda Triplett, Yueling Ma, Peter Melchior, Reed M. Maxwell, Laura E. Condon

Journal of Advances in Modeling Earth Systems · 2024-06 · 16 (6)

DOI: 10.1029/2023ms004095 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Advances in Modeling Earth Systems, online erschienen am 12.06.2024. Verfasst von Andrew Bennett und 7 weiteren Autor:innen. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Integrated hydrologic models can simulate coupled surface and subsurface processes but are computationally expensive to run at high resolutions over large domains. Here we develop a novel deep learning model to emulate subsurface flows simulated by the integrated ParFlow‐CLM model across the contiguous US. We compare convolutional neural networks like ResNet and UNet run autoregressively against our novel architecture called the Forced SpatioTemporal RNN (FSTR). The FSTR model incorporates separate encoding of initial conditions, static parameters, and meteorological forcings, which are fused in a recurrent loop to produce spatiotemporal predictions of groundwater. We evaluate the model architectures on their ability to reproduce 4D pressure heads, water table depths, and surface soil moisture over the contiguous US at 1 km resolution and daily time steps over the course of a full water year. The FSTR model shows superior performance to the baseline models, producing stable simulations that capture both seasonal and event‐scale dynamics across a wide array of hydroclimatic regimes. The emulators provide over 1,000× speedup compared to the original physical model, which will enable new capabilities like uncertainty quantification and data assimilation for integrated hydrologic modeling that were not previously possible. Our results demonstrate the promise of using specialized deep learning architectures like FSTR for emulating complex process‐based models without sacrificing fidelity.

Förderung

  • National Science Foundation

Zitieren

APA

Bennett, A., Tran, H., Fuente, L. D. L., Triplett, A., Ma, Y., Melchior, P., Maxwell, R. M., & Condon, L. E. (2024). Spatio‐Temporal Machine Learning for Regional to Continental Scale Terrestrial Hydrology. Journal of Advances in Modeling Earth Systems, 16(6). https://doi.org/10.1029/2023ms004095

Vancouver

Bennett A, Tran H, Fuente LDL, Triplett A, Ma Y, Melchior P, et al. Spatio‐Temporal Machine Learning for Regional to Continental Scale Terrestrial Hydrology. Journal of Advances in Modeling Earth Systems. 2024;16(6). doi:10.1029/2023ms004095

BibTeX
@article{Bennett2024,
  author = {Bennett, Andrew and Tran, Hoang and Fuente, Luis De la and Triplett, Amanda and Ma, Yueling and Melchior, Peter and Maxwell, Reed M. and Condon, Laura E.},
  title = {Spatio‐Temporal Machine Learning for Regional to Continental Scale Terrestrial Hydrology},
  journal = {Journal of Advances in Modeling Earth Systems},
  year = {2024},
  volume = {16},
  number = {6},
  doi = {10.1029/2023ms004095}
}
Kostenlos starten →