Using Machine Learning for Prediction of Saturated Hydraulic Conductivity and Its Sensitivity to Soil Structural Perturbations

Araya, Samuel N.; Ghezzehei, Teamrat A.

doi:10.1029/2018wr024357

Cited by 132 publications

(88 citation statements)

References 97 publications

(113 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When the methods are homogeneous, the RMSE value is usually around 0.6-0.7 log 10 (cm day -1 ) (Zhang and Schaap, 2017). Araya and Ghezzehei (2019) report that the PTF with the highest accuracy in the literature has and RMSE of 0.3-0.4 log 10 (cm day -1 ). In Lilly et al (2008), the performance of the KS predictions and findings were similar to this study.…”

Section: Saturated Hydraulic Conductivitymentioning

confidence: 97%

“…Machine learning methods can be more robust to construct PTFs in comparison to previous approaches such as linear regression or simple decision trees if relationship between the predictors and response is highly non-linear (Araya and Ghezzehei, 2019). The random forest algorithm (Breiman, 2001) is able to outperform other machine learning methods (Olson et al, 2018), which was also shown for predicting soil properties (Hengl et al, 2018;Nussbaum et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Updated European hydraulic pedotransfer functions with communicated uncertainties in the predicted variables (euptfv2)

Szabó¹,

Weynants²,

Weber³

2020

Preprint

View full text Add to dashboard Cite

Abstract. Soil hydraulic properties are often derived indirectly, i.e. computed from easily available soil properties with pedotransfer functions (PTFs), when those are needed for catchment, regional or continental scale applications. When predicted soil hydraulic parameters are used for the modelling of the state and flux of water in soils, uncertainty of the computed values can provide more detailed information when drawing conclusions. The aim of this study was to update the previously published European PTFs (Tóth et al., 2015, euptf v1.4.0) by providing prediction uncertainty calculation built into the transfer functions. The new set of algorithms was derived for point predictions of soil water content at saturation (0 cm matric potential head), field capacity (both −100 and −330 cm matric potential head), wilting point (−15.000 cm matric potential head), plant available water, and saturated hydraulic conductivity, as well as the Mualem-van Genuchten model parameters of the moisture retention and hydraulic conductivity curve. The minimum set of input properties for the prediction is soil depth and sand, silt and clay content. The effect of including additional information like soil organic carbon content, bulk density, calcium carbonate content, pH and cation exchange capacity were extensively analysed. The PTFs were derived adopting the random forest method. The advantage of the new PTFs is that they i) provide information about prediction uncertainty, ii) are significantly more accurate than the euptfv1, iii) can be applied for more predictor variable combinations than the euptfv1, 32 instead of 5, and iv) are now also derived for the prediction of water content at −100 cm matric potential head and plant available water content.

show abstract

Section: Saturated Hydraulic Conductivitymentioning

confidence: 97%

Section: Introductionmentioning

confidence: 99%

Updated European hydraulic pedotransfer functions with communicated uncertainties in the predicted variables (euptfv2)

Szabó¹,

Weynants²,

Weber³

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…When the methods are homogeneous, the RMSE value is usually around 0.6-0.7 log10 (cm day -1 ) (Zhang and Schaap, 2017). Araya and Ghezzehei (2019) report that the PTF with the highest accuracy in the literature has and RMSE of 0.3-0.4 log10 (cm day -1 ). In Lilly et al (2008), the performance of the KS predictions and findings were similar to this study.…”

Section: Saturated Hydraulic Conductivitymentioning

confidence: 97%

Updated European Hydraulic Pedotransfer Functions with Communicated Uncertainties in the Predicted Variables (euptfv2)

Szabó

Weynants

Weber

2020

Preprint

View full text Add to dashboard Cite

Soil hydraulic properties are often derived indirectly, i.e. computed from easily available soil properties with pedotransfer functions (PTFs), when those are needed for catchment, regional or continental scale applications. When predicted soil hydraulic parameters are used for the modelling of the state and flux of water in soils, uncertainty of the computed values can provide more detailed information when drawing conclusions. The aim of this study was to update the previously published European PTFs (Tóth et al., 2015, euptf v1.4.0) by providing prediction uncertainty calculation built into the transfer functions. The new set of algorithms was derived for point predictions of soil water content at saturation (0 cm matric potential head), field capacity (both -100 and -330 cm matric potential head), wilting point (-15.000 cm matric potential head), plant available water, and saturated hydraulic conductivity, as well as the Mualem-van Genuchten model parameters of the moisture retention and hydraulic conductivity curve. The minimum set of input properties for the prediction is soil depth and sand, silt and clay content. The effect of including additional information like soil organic carbon content, bulk density, calcium carbonate content, pH and cation exchange capacity were extensively analysed. The PTFs were derived adopting the random forest method. The advantage of the new PTFs is that they i) provide information about prediction uncertainty, ii) are significantly more accurate than the euptfv1, iii) can be applied for more predictor variable combinations than the euptfv1, 32 instead of 5, and iv) are now also derived for the prediction of water content at -100 cm matric potential head and plant available water content.

show abstract

“…The global dataset in SWIG may allow for such a wide variety of soil conditions for the same land use category that the value of land use alone as a predictor becomes less significant. The infiltration rate should be affected by the initial water content in the soil, the water content of which was an important variable for predicting hydraulic conductivity (Araya and Ghezzehei, 2019). Since the initial soil water content is only available in 31% of the infiltration data in the SWIG database, initial soil water content was not included in this study.…”

Section: Equationmentioning

confidence: 99%

Estimating parameters of empirical infiltration models from the global dataset using machine learning

Kim¹,

Karahan²,

Шарма³

et al. 2021

Int. Agrophys.

View full text Add to dashboard Cite

It is beneficial to develop pedotransfer relationships to estimate infiltration equation coefficients in site-specific conditions from readily available data. No systematic studies have been published concerning the relationships between the accuracy of the infiltration equation and the accuracy of the predicted coefficients in this equation. The objective of this work was to test the hypothesis that, for the same infiltration data, the accuracy of pedotransfer predictions for coefficients in an infiltration equation is greater for the infiltration equation that performs better. The hypothesis was tested using the commonly employed Horton and Mezencev (modified Kostiakov) infiltration equations with data from the Soil Water Infiltration Global database. The random forest machine learning algorithm was used to develop the pedotransfer model. The Horton and the Mezencev models performed better with 928 and 758 datasets, respectively. The accuracy of the estimates of the infiltration equation coefficients did not differ substantially between the estimates obtained from all data and from the data where the infiltration equation had lower root-mean-squared error values. The root-mean-squared error values of the pedotransfer estimates decreased by 2 to 25% when only datasets with the same infiltration measurement method were considered. The development of predictive pedotransfer equations with the data obtained from the same infiltration measurement method is recommended.

show abstract

Using Machine Learning for Prediction of Saturated Hydraulic Conductivity and Its Sensitivity to Soil Structural Perturbations

Cited by 132 publications

References 97 publications

Updated European hydraulic pedotransfer functions with communicated uncertainties in the predicted variables (euptfv2)

Updated European hydraulic pedotransfer functions with communicated uncertainties in the predicted variables (euptfv2)

Updated European Hydraulic Pedotransfer Functions with Communicated Uncertainties in the Predicted Variables (euptfv2)

Estimating parameters of empirical infiltration models from the global dataset using machine learning

Contact Info

Product

Resources

About