EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Physics‐Informed Neural Networks for Estimating a Continuous Form of the Soil Water Retention Curve From Basic Soil Properties

Sarem Norouzi, Charles Pesch, Emmanuel Arthur, Trine Norgaard, Per Moldrup, Mogens H. Greve, Amélie M. Beucher, Morteza Sadeghi, Marzieh Zaresourmanabad, Markus Tuller, Bo V. Iversen, Lis W. de Jonge

Water Resources Research · 2025-03 · 61 (3)

DOI: 10.1029/2024wr038149 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Water Resources Research, online erschienen am 14.03.2025. Verfasst von Sarem Norouzi und 11 weiteren Autor:innen. Die Arbeit wurde bisher 37-mal zitiert (Crossref) und nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: HORIZON EUROPE Food, Bioeconomy, Natural Resources, Agriculture and Environment.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents a novel physics‐informed neural network (PINN) approach for developing pedotransfer functions (PTFs) to predict continuous soil water retention curves (SWRCs) based on soil textural fractions, organic carbon content, and bulk density. In contrast to conventional parametric PTFs developed for specific SWRC models, the PINN learns a non‐specific form of the SWRC from both measurements and physical constraints imposed during the training process. This approach allows the estimated SWRC to maintain its physical integrity from saturation to oven‐dry conditions, even in scenarios with sparse data. The new approach is particularly effective for tackling the challenges encountered in developing PTFs on large SWRC data sets, which often have an imbalance toward the wet‐end () and include numerous samples with limited and unevenly distributed measurements, many of which do not meet the requirements to fit traditional SWRC models. We compared the performance of the PINN with that of a conventional physics‐agnostic neural network using a data set of 4,200 soil samples. While both networks performed similarly at the wet‐end where data are abundant, with RMSE values of around 0.041 m 3 m −3 , the PINN excelled at the dry‐end () where data are sparse and unevenly distributed, achieving a normalized RMSE of 0.172 (RMSE = 0.0045 m 3 m −3 ) compared to a normalized RMSE of 0.522 (RMSE = 0.0136 m 3 m −3 ) for the conventional neural network. The SWRC derived from the PINN is differentiable with respect to matric potential, making it well‐suited for integration into models of water flow in the unsaturated zone.

Förderung

  • HORIZON EUROPE Food, Bioeconomy, Natural Resources, Agriculture and Environment

Zitieren

APA

Norouzi, S., Pesch, C., Arthur, E., Norgaard, T., Moldrup, P., Greve, M. H., Beucher, A. M., Sadeghi, M., Zaresourmanabad, M., Tuller, M., Iversen, B. V., & Jonge, L. W. D. (2025). Physics‐Informed Neural Networks for Estimating a Continuous Form of the Soil Water Retention Curve From Basic Soil Properties. Water Resources Research, 61(3). https://doi.org/10.1029/2024wr038149

Vancouver

Norouzi S, Pesch C, Arthur E, Norgaard T, Moldrup P, Greve MH, et al. Physics‐Informed Neural Networks for Estimating a Continuous Form of the Soil Water Retention Curve From Basic Soil Properties. Water Resources Research. 2025;61(3). doi:10.1029/2024wr038149

BibTeX
@article{Norouzi2025,
  author = {Norouzi, Sarem and Pesch, Charles and Arthur, Emmanuel and Norgaard, Trine and Moldrup, Per and Greve, Mogens H. and Beucher, Amélie M. and Sadeghi, Morteza and Zaresourmanabad, Marzieh and Tuller, Markus and Iversen, Bo V. and Jonge, Lis W. de},
  title = {Physics‐Informed Neural Networks for Estimating a Continuous Form of the Soil Water Retention Curve From Basic Soil Properties},
  journal = {Water Resources Research},
  year = {2025},
  volume = {61},
  number = {3},
  doi = {10.1029/2024wr038149}
}
Kostenlos starten →