Global Mapping of Potential and Climatic Plant‐Available Soil Water

Gupta, Surya; Lehmann, Peter; Bickel, Samuel; Bonetti, Sara; Or, Dani

doi:10.1029/2022ms003277

Cited by 3 publications

(1 citation statement)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, matric potential thresholds are defined in various regions of Switzerland to prevent mechanical damage and regulate the maximum load linked to factors like soil type, texture, and vehicle impact (Bundesamt für Energiewirtschaft, 1997). Other important potential thresholds are the wilting point and the field capacity, characterizing the plant available water (Gupta, et al, 2023).…”

Section: Introductionmentioning

confidence: 99%

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

Aqel,

Reusser,

Margreth

et al. 2024

Preprint

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%

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

Aqel,

Reusser,

Margreth

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Relationship between Plant-Available Water and Soil Compaction in Brazilian Soils

Gubiani,

do Santos,

Mulazzani

et al. 2024

Sustainability

View full text Add to dashboard Cite

The capacity of soil to retain water and make it available to plants is an essential soil functions for the sustainability of terrestrial ecosystems. A lot of progress has been made in estimating water retention and availability as a function of soil texture. On the other hand, a lower effort has been dedicated to seeking correlations between plant-available water (AW) and soil compaction. In this study, we compiled a dataset with 2479 records from experiments conducted in Brazilian soils to evaluate the relationship between AW and bulk density (BD). The dataset was split into sub-datasets defined by soil textural classes to reduce the effect of texture on AW–BD relationships. In each sub-dataset, AW–BD relationships were described by linear regression. In general, there was a weak association between AW and BD. The strongest correlations were found in the Silty Loam (R2 = 0.26) and Loam (R2 = 0.13) classes. However, the partitioning of the overall dataset by textural classes was not effective to eliminate the effect of texture on AW–BD relationships. Still, the data showed that soil compaction may increase or reduce AW. Nevertheless, more experimental research is needed to bring a better understanding of how AW is affected by changes in BD.

show abstract

Prediction of hysteretic matric potential dynamics using artificial intelligence: application of autoencoder neural networks

Aqel,

Reusser,

Margreth

et al. 2024

Geosci. Model Dev.

View full text Add to dashboard Cite

Abstract. Information on soil water potential is essential to assessing the soil moisture state, to prevent soil compaction in weak soils, and to optimize crop management. When there is a lack of direct measurements, the soil water potential values must be deduced from soil water content dynamics that can be monitored at the plot scale or obtained at a 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–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 established 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.

show abstract

Global Mapping of Potential and Climatic Plant‐Available Soil Water

Cited by 3 publications

References 55 publications

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

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

Relationship between Plant-Available Water and Soil Compaction in Brazilian Soils

Prediction of hysteretic matric potential dynamics using artificial intelligence: application of autoencoder neural networks

Contact Info

Product

Resources

About