EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Physics‐Informed Neural Network for Retrieving the Continuous Soil Particle Size Distribution From Vis– NIR Spectra

Sarem Norouzi, Mogens H. Greve, Per Moldrup, Budiman Minasny, Marzieh Zaresourmanabad, Charles Pesch, Lucas Gomes, Emmanuel Arthur, Trine Norgaard, Maria Knadel, Mette B. Greve, Lis W. de Jonge

European Journal of Soil Science · 2026-01 · 77 (1)

DOI: 10.1111/ejss.70264 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Journal of Soil Science, online erschienen am 18.01.2026. Verfasst von Sarem Norouzi und 11 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 65 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)

Estimating the soil particle size distribution (PSD) from visible–near infrared (vis–NIR) reflectance spectra is conventionally limited to predicting discrete soil fractions (e.g., sand, silt, and clay). This approach presents significant challenges: it requires the harmonization of data from different classification systems and, by reducing the PSD to a few values, fails to reflect the entire variation in soil texture. To address these gaps, we present a novel physics‐informed neural network (PINN) for the direct estimation of the continuous PSD from vis–NIR reflectance measurements. The PINN learns a continuous, differentiable, and non‐parametric representation of the cumulative PSD by integrating both measurements and physical constraints imposed during training. This approach eliminates the need for harmonization and interpolation of measurements originating from different soil texture classification systems and allows the model to be trained on datasets with varying numbers of measurements per sample. Performance evaluation on 30% of the 2777 studied samples showed that the PINN achieved an RMSE of 6.77% and an R 2 of 0.97 in predicting the cumulative PSD fraction. For the texture fractions, the model achieved RMSE values of 4.72%, 3.06%, and 2.75% for sand, silt, and clay, respectively. A comparison with a physics‐agnostic (i.e., physics‐uninformed) version of the model revealed that both approaches performed similarly in terms of RMSE and R 2 . However, the physics‐agnostic model violated physical constraints even in data‐rich scenarios. In contrast, the PSD obtained from the PINN maintained its physical integrity even under data sparsity conditions and consistently produced non‐negative, monotonically increasing predictions that sum to 100% at the largest particle size.

Förderung

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

Zitieren

APA

Norouzi, S., Greve, M. H., Moldrup, P., Minasny, B., Zaresourmanabad, M., Pesch, C., Gomes, L., Arthur, E., Norgaard, T., Knadel, M., Greve, M. B., & Jonge, L. W. D. (2026). A Physics‐Informed Neural Network for Retrieving the Continuous Soil Particle Size Distribution From Vis– NIR Spectra. European Journal of Soil Science, 77(1). https://doi.org/10.1111/ejss.70264

Vancouver

Norouzi S, Greve MH, Moldrup P, Minasny B, Zaresourmanabad M, Pesch C, et al. A Physics‐Informed Neural Network for Retrieving the Continuous Soil Particle Size Distribution From Vis– NIR Spectra. European Journal of Soil Science. 2026;77(1). doi:10.1111/ejss.70264

BibTeX
@article{Norouzi2026,
  author = {Norouzi, Sarem and Greve, Mogens H. and Moldrup, Per and Minasny, Budiman and Zaresourmanabad, Marzieh and Pesch, Charles and Gomes, Lucas and Arthur, Emmanuel and Norgaard, Trine and Knadel, Maria and Greve, Mette B. and Jonge, Lis W. de},
  title = {A Physics‐Informed Neural Network for Retrieving the Continuous Soil Particle Size Distribution From Vis– NIR Spectra},
  journal = {European Journal of Soil Science},
  year = {2026},
  volume = {77},
  number = {1},
  doi = {10.1111/ejss.70264}
}
Kostenlos starten →