Preprints
https://doi.org/10.5194/egusphere-2025-4253
https://doi.org/10.5194/egusphere-2025-4253
02 Sep 2025
 | 02 Sep 2025
Status: this preprint is open for discussion and under review for Geoscientific Model Development (GMD).

NoahPy: A differentiable Noah land surface model for simulating permafrost thermo-hydrology

Wenbiao Tian, Hu Yu, Shuping Zhao, Yuhe Cao, Wenjun Yi, Jiwei Xu, and Zhuotong Nan

Abstract. Accurately representing permafrost in Earth System Models is a grand challenge that creates major uncertainty. A promising path forward is to create hybrid models that synergize process-based physics with deep learning, but this is fundamentally hindered by the non-differentiable nature of traditional land surface models (LSMs), which are incompatible with modern AI workflows. To overcome this limitation, we present NoahPy, a fully differentiable LSM developed by reconstructing the Noah LSM’s governing partial differential equations into a process-encapsulated Recurrent Neural Network (RNN). We first demonstrate that NoahPy perfectly replicates the numerical behaviour of the modified Noah LSM, achieving Nash-Sutcliffe Efficiency (NSE) coefficients above 0.99 for both soil temperature and liquid water. We then show that at a permafrost site, the calibrated NoahPy achieves robust simulation performance for for soil temperature (NSE > 0.9) and liquid water (NSE > 0.8). Critically, the differentiable workflow, when combined with the Adam optimizer, is significantly faster, more stable, and yields simulations with lower uncertainty compared to traditional SCE-UA calibration algorithm. NoahPy thus provides a foundational, "glass-box" framework that closes a key technical gap, enabling the development of the next generation of hybrid AI-physics models needed to more reliably predict the future of the cryosphere.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this paper. While Copernicus Publications makes every effort to include appropriate place names, the final responsibility lies with the authors. Views expressed in the text are those of the authors and do not necessarily reflect the views of the publisher.
Share
Wenbiao Tian, Hu Yu, Shuping Zhao, Yuhe Cao, Wenjun Yi, Jiwei Xu, and Zhuotong Nan

Status: open (until 28 Oct 2025)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
Wenbiao Tian, Hu Yu, Shuping Zhao, Yuhe Cao, Wenjun Yi, Jiwei Xu, and Zhuotong Nan
Wenbiao Tian, Hu Yu, Shuping Zhao, Yuhe Cao, Wenjun Yi, Jiwei Xu, and Zhuotong Nan

Viewed

Total article views: 56 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
52 4 0 56 0 0
  • HTML: 52
  • PDF: 4
  • XML: 0
  • Total: 56
  • BibTeX: 0
  • EndNote: 0
Views and downloads (calculated since 02 Sep 2025)
Cumulative views and downloads (calculated since 02 Sep 2025)

Viewed (geographical distribution)

Total article views: 56 (including HTML, PDF, and XML) Thereof 56 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 03 Sep 2025
Download
Short summary
Accurately predicting how permafrost will thaw with land surface models is a grand challenge in Earth science. We created a new computer model by rebuilding a traditional physics model to work with artificial intelligence. Our results show this new approach is much faster and more reliable for tuning model parameters with data. This provides a better tool to build the next generation of climate models and improve predictions of permafrost's future.
Share