Preprints
https://doi.org/10.5194/egusphere-2024-407
https://doi.org/10.5194/egusphere-2024-407
04 Mar 2024
 | 04 Mar 2024

Prediction of Hysteretic Matric Potential Dynamics Using Artificial Intelligence: Application of Autoencoder Neural Networks

Nedal Aqel, Lea Reusser, Stephan Margreth, Andrea Carminati, and Peter Lehmann

Abstract. Information on soil water potential is essential to assess soil moisture state, to prevent soil compaction in weak soils, and to optimize crop management. In lack of direct measurements, the soil water potential values must be deduced from soil water content dynamics that can be monitored at plot scale or obtained at larger scale from remote sensing information. Because the relationship between water content and soil water potential in natural field soils is highly ambiguous, the prediction of soil water potential from water content data is a big challenge. The hysteretic relationship observed in nine soil profiles in the region of Solothurn (Switzerland) is not a simple function of texture or wetting and drainage cycles but depends on seasonal patterns that may be related to soil structural dynamics. Because the physical mechanisms governing seasonal hysteresis are unclear, we developed a deep neural network model that predicts water potential changes using rainfall, potential evapotranspiration, and water content time series as inputs. To adapt the model for multiple locations, we incorporated a Deep Autoencoder Neural Network as a classifier. The autoencoder compresses the water content time series into a site-specific feature that is highly representative of the underlying water content dynamics of each site and quantifies the similarity of dynamic patterns. By adding the Autoencoder's output as an additional input and training the neural network model with three stations located in three major classes founded by the autoencoder, we predict matric potential for other sites. This method has the potential to deduce the dynamics of matric potential from water content data (including satellite data) despite strong seasonal effects that cannot be captured by standard methods.

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 preprint. The responsibility to include appropriate place names lies with the authors.

Journal article(s) based on this preprint

18 Sep 2024
Prediction of hysteretic matric potential dynamics using artificial intelligence: application of autoencoder neural networks
Nedal Aqel, Lea Reusser, Stephan Margreth, Andrea Carminati, and Peter Lehmann
Geosci. Model Dev., 17, 6949–6966, https://doi.org/10.5194/gmd-17-6949-2024,https://doi.org/10.5194/gmd-17-6949-2024, 2024
Short summary
Nedal Aqel, Lea Reusser, Stephan Margreth, Andrea Carminati, and Peter Lehmann

Interactive discussion

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2024-407', Ilhan Özgen-Xian, 29 Apr 2024
  • RC2: 'Comment on egusphere-2024-407', Anonymous Referee #2, 07 Jun 2024

Interactive discussion

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2024-407', Ilhan Özgen-Xian, 29 Apr 2024
  • RC2: 'Comment on egusphere-2024-407', Anonymous Referee #2, 07 Jun 2024

Peer review completion

AR: Author's response | RR: Referee report | ED: Editor decision | EF: Editorial file upload
AR by Nedal Aqel on behalf of the Authors (01 Jul 2024)  Author's response   Author's tracked changes   Manuscript 
ED: Publish subject to minor revisions (review by editor) (19 Jul 2024) by Lele Shu
AR by Nedal Aqel on behalf of the Authors (22 Jul 2024)
EF by Sarah Buchmann (24 Jul 2024)  Manuscript   Author's response   Author's tracked changes 
ED: Publish as is (29 Jul 2024) by Lele Shu
AR by Nedal Aqel on behalf of the Authors (30 Jul 2024)

Journal article(s) based on this preprint

18 Sep 2024
Prediction of hysteretic matric potential dynamics using artificial intelligence: application of autoencoder neural networks
Nedal Aqel, Lea Reusser, Stephan Margreth, Andrea Carminati, and Peter Lehmann
Geosci. Model Dev., 17, 6949–6966, https://doi.org/10.5194/gmd-17-6949-2024,https://doi.org/10.5194/gmd-17-6949-2024, 2024
Short summary
Nedal Aqel, Lea Reusser, Stephan Margreth, Andrea Carminati, and Peter Lehmann
Nedal Aqel, Lea Reusser, Stephan Margreth, Andrea Carminati, and Peter Lehmann

Viewed

Total article views: 457 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
321 98 38 457 23 18
  • HTML: 321
  • PDF: 98
  • XML: 38
  • Total: 457
  • BibTeX: 23
  • EndNote: 18
Views and downloads (calculated since 04 Mar 2024)
Cumulative views and downloads (calculated since 04 Mar 2024)

Viewed (geographical distribution)

Total article views: 464 (including HTML, PDF, and XML) Thereof 464 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 18 Sep 2024
Download

The requested preprint has a corresponding peer-reviewed final revised paper. You are encouraged to refer to the final revised version.

Short summary
The soil water potential (SWP) determines various soil water processes. Because it cannot be measured directly by remote sensing techniques, it is often deduced from volumetric water content (VWC) information. However, under dynamic field conditions, the relationship between SWP and VWC is highly ambiguous due to different factors that cannot be modeled with the classical approach. Applying a deep neural network with an autoencoder enables the prediction of SWP.