Articles | Volume 17, issue 18
https://doi.org/10.5194/gmd-17-6949-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-17-6949-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Model description paper
| 
18 Sep 2024
Model description paper |
| 18 Sep 2024
| 18 Sep 2024
Prediction of hysteretic matric potential dynamics using artificial intelligence: application of autoencoder neural networks
Nedal Aqel
CORRESPONDING AUTHOR
Physics of Soils and Terrestrial Ecosystems, ETH Zurich, Zurich, Switzerland
Lea Reusser
Physics of Soils and Terrestrial Ecosystems, ETH Zurich, Zurich, Switzerland
Office for the Environment, Canton of Solothurn, Solothurn, Switzerland
now at: Forum Landscape, Alps, Parks (FoLAP), Swiss Academy of Sciences, Bern, Switzerland
Stephan Margreth
Office for the Environment, Canton of Solothurn, Solothurn, Switzerland
Andrea Carminati
Physics of Soils and Terrestrial Ecosystems, ETH Zurich, Zurich, Switzerland
Peter Lehmann
Physics of Soils and Terrestrial Ecosystems, ETH Zurich, Zurich, Switzerland
Related authors
Nedal Aqel, Jannis Groh, Lutz Weihermüller, Ralf Gründling, Andrea Carminati, and Peter Lehmann
EGUsphere, https://doi.org/10.5194/egusphere-2025-5141, https://doi.org/10.5194/egusphere-2025-5141, 2025
This preprint is open for discussion and under review for Hydrology and Earth System Sciences (HESS).
Short summary
Short summary
This study investigates how soils respond to major climatic disturbances, such as the extreme drought in Germany in 2018. Using long-term lysimeter observations and an artificial intelligence model, we show that persistent shifts in soil water dynamics indicate changes in hydraulic properties that may affect soil health, emphasizing the need for continuous monitoring under a changing climate.
Nedal Aqel, Jannis Groh, Lutz Weihermüller, Ralf Gründling, Andrea Carminati, and Peter Lehmann
EGUsphere, https://doi.org/10.5194/egusphere-2025-5141, https://doi.org/10.5194/egusphere-2025-5141, 2025
This preprint is open for discussion and under review for Hydrology and Earth System Sciences (HESS).
Short summary
Short summary
This study investigates how soils respond to major climatic disturbances, such as the extreme drought in Germany in 2018. Using long-term lysimeter observations and an artificial intelligence model, we show that persistent shifts in soil water dynamics indicate changes in hydraulic properties that may affect soil health, emphasizing the need for continuous monitoring under a changing climate.
Michael Lombardo, Amelie Fees, Anders Kaestner, Alec van Herwijnen, Jürg Schweizer, and Peter Lehmann
The Cryosphere, 19, 4437–4458, https://doi.org/10.5194/tc-19-4437-2025, https://doi.org/10.5194/tc-19-4437-2025, 2025
Short summary
Short summary
Water flow in snow is important for many applications including snow hydrology and avalanche forecasting. This work investigated the role of capillary forces at the soil-snow interface during capillary rise experiments using neutron radiography. The results showed that the properties of both the snow and the transitional layer below the snow affected the water flow. This work will allow for better representations of water flow across the soil–snow interface in snowpack models.
Amelie Fees, Michael Lombardo, Alec van Herwijnen, Peter Lehmann, and Jürg Schweizer
The Cryosphere, 19, 1453–1468, https://doi.org/10.5194/tc-19-1453-2025, https://doi.org/10.5194/tc-19-1453-2025, 2025
Short summary
Short summary
Glide-snow avalanches release at the soil–snow interface due to a loss of friction, which is suspected to be linked to interfacial water. The importance of the interfacial water was investigated with a spatio-temporal monitoring setup for soil and local snow on an avalanche-prone slope. Seven glide-snow avalanches were released on the monitoring grid (winter seasons 2021/22 to 2023/24) and provided insights into the source, quantity, and spatial distribution of interfacial water before avalanche release.
Amelie Fees, Alec van Herwijnen, Michael Lombardo, Jürg Schweizer, and Peter Lehmann
Nat. Hazards Earth Syst. Sci., 24, 3387–3400, https://doi.org/10.5194/nhess-24-3387-2024, https://doi.org/10.5194/nhess-24-3387-2024, 2024
Short summary
Short summary
Glide-snow avalanches release at the ground–snow interface, and their release process is poorly understood. To investigate the influence of spatial variability (snowpack and basal friction) on avalanche release, we developed a 3D, mechanical, threshold-based model that reproduces an observed release area distribution. A sensitivity analysis showed that the distribution was mostly influenced by the basal friction uniformity, while the variations in snowpack properties had little influence.
Tobias Karl David Weber, Lutz Weihermüller, Attila Nemes, Michel Bechtold, Aurore Degré, Efstathios Diamantopoulos, Simone Fatichi, Vilim Filipović, Surya Gupta, Tobias L. Hohenbrink, Daniel R. Hirmas, Conrad Jackisch, Quirijn de Jong van Lier, John Koestel, Peter Lehmann, Toby R. Marthews, Budiman Minasny, Holger Pagel, Martine van der Ploeg, Shahab Aldin Shojaeezadeh, Simon Fiil Svane, Brigitta Szabó, Harry Vereecken, Anne Verhoef, Michael Young, Yijian Zeng, Yonggen Zhang, and Sara Bonetti
Hydrol. Earth Syst. Sci., 28, 3391–3433, https://doi.org/10.5194/hess-28-3391-2024, https://doi.org/10.5194/hess-28-3391-2024, 2024
Short summary
Short summary
Pedotransfer functions (PTFs) are used to predict parameters of models describing the hydraulic properties of soils. The appropriateness of these predictions critically relies on the nature of the datasets for training the PTFs and the physical comprehensiveness of the models. This roadmap paper is addressed to PTF developers and users and critically reflects the utility and future of PTFs. To this end, we present a manifesto aiming at a paradigm shift in PTF research.
Adrian Wicki, Peter Lehmann, Christian Hauck, and Manfred Stähli
Nat. Hazards Earth Syst. Sci., 23, 1059–1077, https://doi.org/10.5194/nhess-23-1059-2023, https://doi.org/10.5194/nhess-23-1059-2023, 2023
Short summary
Short summary
Soil wetness measurements are used for shallow landslide prediction; however, existing sites are often located in flat terrain. Here, we assessed the ability of monitoring sites at flat locations to detect critically saturated conditions compared to if they were situated at a landslide-prone location. We found that differences exist but that both sites could equally well distinguish critical from non-critical conditions for shallow landslide triggering if relative changes are considered.
Adrian Wicki, Per-Erik Jansson, Peter Lehmann, Christian Hauck, and Manfred Stähli
Hydrol. Earth Syst. Sci., 25, 4585–4610, https://doi.org/10.5194/hess-25-4585-2021, https://doi.org/10.5194/hess-25-4585-2021, 2021
Short summary
Short summary
Soil moisture information was shown to be valuable for landslide prediction. Soil moisture was simulated at 133 sites in Switzerland, and the temporal variability was compared to the regional occurrence of landslides. We found that simulated soil moisture is a good predictor for landslides, and that the forecast goodness is similar to using in situ measurements. This encourages the use of models for complementing existing soil moisture monitoring networks for regional landslide early warning.
Surya Gupta, Tomislav Hengl, Peter Lehmann, Sara Bonetti, and Dani Or
Earth Syst. Sci. Data, 13, 1593–1612, https://doi.org/10.5194/essd-13-1593-2021, https://doi.org/10.5194/essd-13-1593-2021, 2021
Cited articles
Achieng, K. O.: Modelling of soil moisture retention curve using machine learning techniques: Artificial and deep neural networks vs support vector regression models, Comput. Geosci., 133, 104320, https://doi.org/10.1016/j.cageo.2019.104320, 2019.
Aqel, N.: Prediction of Hysteretic Matric Potential Dynamics Using Artificial Intelligence: Application of Autoencoder Neural Networks-Dataset, Zenodo [data set], https://doi.org/10.5281/zenodo.10600669, 2024a.
Aqel, N.: Prediction of Hysteretic Matric Potential Dynamics Using Artificial Intelligence: Application of Autoencoder Neural Networks – python codes. Zenodo [code], https://doi.org/10.5281/zenodo.10602397, 2024b.
Aqel, N.: Prediction of Hysteretic Matric Potential Dynamics Using Artificial Intelligence: Application of Autoencoder Neural Networks – Autoencoder part, Zenodo [code], https://doi.org/10.5281/zenodo.10605108, 2024c.
Basile, A., Bonfante, A., Coppola, A., De Mascellis, R., Falanga Bolognesi, S., Terribile, F., and Manna, P.: How does PTF Interpret Soil Heterogeneity? A Stochastic Approach Applied to a Case Study on Maize in Northern Italy, Water (Basel), 11, 275, https://doi.org/10.3390/w11020275, 2019.
Bertels, D. and Willems, P.: Physics-informed machine learning method for modelling transport of a conservative pollutant in surface water systems, J. Hydrol., 619, 129354, https://doi.org/10.1016/j.jhydrol.2023.129354, 2023.
Bodenmessnetz: Bodenmessnetz Schweiz, https://www.bodenmessnetz.ch/, last access: 10 September 2024.
Boyle, D. P., Gupta, H. V., and Sorooshian, S.: Toward improved calibration of hydrologic models: Combining the strengths of manual and automatic methods, Water Resour. Res., 36, 3663–3674, https://doi.org/10.1029/2000WR900207, 2000.
Bundesamt für Energiewirtschaft: Richtlinien zum Schutze des Bodens beim Bau unterirdisch verlegter Rohrleitungen, Schweiz, https://pubdb.bfe.admin.ch/de/publication/download/1386 (last access: 10 September 2024), 1997.
Capparelli, G. and Spolverino, G.: An Empirical Approach for Modeling Hysteresis Behavior of Pyroclastic Soils, Hydrology, 7, 14, https://doi.org/10.3390/hydrology7010014, 2020.
Chen, S. and Guo, W.: Auto-Encoders in Deep Learning – A Review with New Perspectives, Mathematics, 11, 1777, https://doi.org/10.3390/math11081777, 2023.
Moriasi, D. N., Arnold, J. G., Van Liew, M. W., Bingner, R. L., Harmel, R. D., and Veith, T. L.: Model Evaluation Guidelines for Systematic Quantification of Accuracy in Watershed Simulations, Trans ASABE, 50, 885–900, https://doi.org/10.13031/2013.23153, 2007.
den Ouden, H. E. M., Kok, P., and de Lange, F. P.: How Prediction Errors Shape Perception, Attention, and Motivation, Front. Psychol., 3, 548, https://doi.org/10.3389/fpsyg.2012.00548, 2012.
Fomin, D. S., Yudina, A. V., Romanenko, K. A., Abrosimov, K. N., Karsanina, M. V., and Gerke, K. M.: Soil pore structure dynamics under steady-state wetting-drying cycle, Geoderma, 432, 116401, https://doi.org/10.1016/j.geoderma.2023.116401, 2023.
Fu, Y. P., Liao, H. J., Chai, X. Q., Li, Y., and Lv, L. L.: A Hysteretic Model Considering Contact Angle Hysteresis for Fitting Soil-Water Characteristic Curves, Water Resour. Res., 57, e2019WR026889, https://doi.org/10.1029/2019WR026889, 2021.
Gallipoli, D., Gens, A., Sharma, R., and Vaunat, J.: An elasto-plastic model for unsaturated soil incorporating the effects of suction and degree of saturation on mechanical behaviour, Géotechnique, 53, 123–135, https://doi.org/10.1680/geot.2003.53.1.123, 2003.
Gholamy, A., Kreinovich, V., and Kosheleva, O.: Why
Gupta, H. V. and Kling, H.: On typical range, sensitivity, and normalization of Mean Squared Error and Nash-Sutcliffe Efficiency type metrics, Water Resour. Res., 47, W10601, https://doi.org/10.1029/2011WR010962, 2011.
Gupta, H. V., Sorooshian, S., and Yapo, P. O.: Status of Automatic Calibration for Hydrologic Models: Comparison with Multilevel Expert Calibration, J. Hydrol. Eng., 4, 135–143, https://doi.org/10.1061/(ASCE)1084-0699(1999)4:2(135), 1999.
Gupta, S., Lehmann, P., Bickel, S., Bonetti, S., and Or, D.: Global Mapping of Potential and Climatic Plant-Available Soil Water, J. Adv. Model. Earth Sy., 15, e2022MS003277, https://doi.org/10.1029/2022MS003277, 2023.
Hannes, M., Wollschläger, U., Wöhling, T., and Vogel, H.-J.: Revisiting hydraulic hysteresis based on long-term monitoring of hydraulic states in lysimeters, Water Resour. Res., 52, 3847–3865, https://doi.org/10.1002/2015WR018319, 2016.
Holthusen, D., Peth, S., and Horn, R.: Impact of potassium concentration and matric potential on soil stability derived from rheological parameters, Soil Tillage Res., 111, 75–85, https://doi.org/10.1016/j.still.2010.08.002, 2010.
Ioffe, S. and Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift, arXiv [preprint], https://doi.org/10.48550/arXiv.1502.03167, 11 February 2015.
Jain, S. K., Singh, V. P., and van Genuchten, M. Th.: Analysis of Soil Water Retention Data Using Artificial Neural Networks, J. Hydrol. Eng., 9, 415–420, https://doi.org/10.1061/(ASCE)1084-0699(2004)9:5(415), 2004.
Kingma, D. P. and Ba, J.: Adam: A method for stochastic optimization, arXiv [preprint], https://doi.org/10.48550/arXiv.1412.6980, 22 December 2014.
Lu, L.: Dying ReLU and Initialization: Theory and Numerical Examples, Commun. Comput. Phys., 28, 1671–1706, https://doi.org/10.4208/cicp.OA-2020-0165, 2020.
Lu, N., Godt, J. W., and Wu, D. T.: A closed-form equation for effective stress in unsaturated soil, Water Resour. Res., 46, W05515, https://doi.org/10.1029/2009WR008646, 2010.
Ma, Y., Liu, H., Yu, Y., Guo, L., Zhao, W., and Yetemen, O.: Revisiting Soil Water Potential: Towards a Better Understanding of Soil and Plant Interactions, Water (Basel), 14, 3721, https://doi.org/10.3390/w14223721, 2022.
Mendes, J. and Buzzi, O.: New insight into cavitation mechanisms in high-capacity tensiometers based on high-speed photography, Can. Geotech. J., 50, 550–556, https://doi.org/10.1139/cgj-2012-0393, 2013.
Menon, M., Mawodza, T., Rabbani, A., Blaud, A., Lair, G. J., Babaei, M., Kercheva, M., Rousseva, S., and Banwart, S.: Pore system characteristics of soil aggregates and their relevance to aggregate stability, Geoderma, 366, 114259, https://doi.org/10.1016/j.geoderma.2020.114259, 2020.
MeteoSwiss: IDAWEB data portal, https://gate.meteoswiss.ch/idaweb, last access: 22 July 2024.
Montesinos López, O. A., Montesinos López, A., and Crossa, J.: Fundamentals of Artificial Neural Networks and Deep Learning, in: Multivariate Statistical Machine Learning Methods for Genomic Prediction, Springer International Publishing, Cham, 379–425, https://doi.org/10.1007/978-3-030-89010-0_10, 2022.
Nash, J. E. and Sutcliffe, J. V.: River flow forecasting through conceptual models part I – A discussion of principles, J. Hydrol., 10, 282–290, https://doi.org/10.1016/0022-1694(70)90255-6, 1970.
O'Connor, R.: Introduction to Variational Autoencoders Using Keras, AssemblyAI [Blog], https://www.assemblyai.com/blog/introduction-to-variational-autoencoders-using-keras/ (last access: 13 September 2024), 2022.
Rawls, W. J., Pachepsky, Y. A., Ritchie, J. C., Sobecki, T. M., and Bloodworth, H.: Effect of soil organic carbon on soil water retention, Geoderma, 116, 61–76, https://doi.org/10.1016/S0016-7061(03)00094-6, 2003.
Reichle, R. H., Liu, Q., Koster, R. D., Crow, W. T., De Lannoy, G. J. M., Kimball, J. S., Ardizzone, J. V., Bosch, D., Colliander, A., Cosh, M., Kolassa, J., Mahanama, S. P., Prueger, J., Starks, P., and Walker, J. P.: Version 4 of the SMAP Level-4 Soil Moisture Algorithm and Data Product, J. Adv. Model. Earth Sy., 11, 3106–3130, https://doi.org/10.1029/2019MS001729, 2019.
Ritter, A. and Muñoz-Carpena, R.: Performance evaluation of hydrological models: Statistical significance for reducing subjectivity in goodness-of-fit assessments, J. Hydrol., 480, 33–45, https://doi.org/10.1016/j.jhydrol.2012.12.004, 2013.
Romero-Ruiz, A., Linde, N., Keller, T., and Or, D.: A Review of Geophysical Methods for Soil Structure Characterization, Rev. Geophys., 56, 672–697, https://doi.org/10.1029/2018RG000611, 2018.
Ross, P. J. and Smettem, K. R. J.: A Simple Treatment of Physical Nonequilibrium Water Flow in Soils, Soil Sci. Soc. Am. J., 64, 1926–1930, https://doi.org/10.2136/sssaj2000.6461926x, 2000.
Rostami, A., Habibagahi, G., Ajdari, M., and Nikooee, E.: Pore Network Investigation on Hysteresis Phenomena and Influence of Stress State on the SWRC, Int. J. Geomech., 15, 04014072, https://doi.org/10.1061/(ASCE)GM.1943-5622.0000315, 2015.
Sadeghi, H., Chiu, A. C. F., Ng, C. W. W., and Jafarzadeh, F.: A vacuum-refilled tensiometer for deep monitoring of in-situ pore water pressure, Sci. Iran., 27, 596–606, https://doi.org/10.24200/sci.2018.5052.1063, 2018.
Shwetha, P. and Varija, K.: Soil Water Retention Curve from Saturated Hydraulic Conductivity for Sandy Loam and Loamy Sand Textured Soils, Aquat. Procedia, 4, 1142–1149, https://doi.org/10.1016/j.aqpro.2015.02.145, 2015.
Smith, C. W., Johnston, M. A., and Lorentz, S. A.: The effect of soil compaction on the water retention characteristics of soils in forest plantations, South African Journal of Plant and Soil, 18, 87–97, https://doi.org/10.1080/02571862.2001.10634410, 2001.
Spreafi, M. and Weingartner, R.: The Hydrology of Switzerland Selected aspects and results, Reports of the FOWG, Water Series, Bern, https://www.bafu.admin.ch/dam/bafu/en/dokumente/hydrologie/uw-umwelt-wissen/hydrologie_der_schweizausgewaehlteaspekteundresultate.pdf.download.pdf/the_hydrology_inswitzerlandselectedaspectsandresults.pdf (last access: 10 September 2024), 2005.
Tuller, M. and Or, D.: Soil water retention and characteristic curve, in: Encyclopedia of Soils in the Environment, Elsevier, 187–202, https://doi.org/10.1016/B978-0-12-822974-3.00105-1, 2023.
Willems, P.: A time series tool to support the multi-criteria performance evaluation of rainfall-runoff models, Environ. Modell. Softw., 24, 311–321, https://doi.org/10.1016/j.envsoft.2008.09.005, 2009.
Zuo, Y. and He, K.: Evaluation and Development of Pedo-Transfer Functions for Predicting Soil Saturated Hydraulic Conductivity in the Alpine Frigid Hilly Region of Qinghai Province, Agronomy, 11, 1581, https://doi.org/10.3390/agronomy11081581, 2021.
Short summary
The soil water potential (SWP) determines various soil water processes. Since remote sensing techniques cannot measure it directly, 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 the dynamic SWP.
The soil water potential (SWP) determines various soil water processes. Since remote sensing...
