Evaluation and Development of Pedotransfer Functions and Artificial Neural Networks to Saturation Moisture Content Estimation: Fid-Bau Portal

Fachinformationsdienst BAUdigital

A platform for research: civil engineering, architecture and urbanism

Evaluation and Development of Pedotransfer Functions and Artificial Neural Networks to Saturation Moisture Content Estimation

Josué Trejo-Alonso / Sebastián Fuentes / Nami Morales-Durán / Carlos Chávez

Modeling of irrigation and agricultural drainage requires knowledge of the soil hydraulic properties. However, uncertainty in the direct measurement of the saturation moisture content ( $θ_{s}$ ) has been generated in several methodologies for its estimation, such as Pedotransfer Functions (PTFs) and Artificial Neuronal Networks (ANNs). In this work, eight different PTFs were developed for the ( $θ_{s}$ ) estimation, which relate to the proportion of sand and clay, bulk density (BD) as well as the saturated hydraulic conductivity ( $K_{s}$ ). In addition, ANNs were developed with different combinations of input and hidden layers for the estimation of $θ_{s}$ . The results showed R $^{2}$ values from $0.9046 \leq R^{2} \leq 0.9877$ for the eight different PTFs, while with the ANNs, values of R $^{2} > 0.9891$ were obtained. Finally, the root-mean-square error (RMSE) was obtained for each ANN configuration, with results ranging from $0.0245 \leq RMSE \leq 0.0262$ . It was found that with particular soil characteristic parameters (% Clay, % Silt, % Sand, BD and $K_{s}$ ), accurate estimate of $θ_{s}$ is obtained. With the development of these models (PTFs and ANNs), high R $^{2}$ values were obtained for 10 of the 12 textural classes.

Access

Page navigation

Document information

Export, share and cite

Evaluation and Development of Pedotransfer Functions and Artificial Neural Networks to Saturation Moisture Content Estimation

Josué Trejo-Alonso / Sebastián Fuentes / Nami Morales-Durán / Carlos Chávez

Modeling of irrigation and agricultural drainage requires knowledge of the soil hydraulic properties. However, uncertainty in the direct measurement of the saturation moisture content ( $θ_{s}$ ) has been generated in several methodologies for its estimation, such as Pedotransfer Functions (PTFs) and Artificial Neuronal Networks (ANNs). In this work, eight different PTFs were developed for the ( $θ_{s}$ ) estimation, which relate to the proportion of sand and clay, bulk density (BD) as well as the saturated hydraulic conductivity ( $K_{s}$ ). In addition, ANNs were developed with different combinations of input and hidden layers for the estimation of $θ_{s}$ . The results showed R $^{2}$ values from $0.9046 \leq R^{2} \leq 0.9877$ for the eight different PTFs, while with the ANNs, values of R $^{2} > 0.9891$ were obtained. Finally, the root-mean-square error (RMSE) was obtained for each ANN configuration, with results ranging from $0.0245 \leq RMSE \leq 0.0262$ . It was found that with particular soil characteristic parameters (% Clay, % Silt, % Sand, BD and $K_{s}$ ), accurate estimate of $θ_{s}$ is obtained. With the development of these models (PTFs and ANNs), high R $^{2}$ values were obtained for 10 of the 12 textural classes.

Evaluation and Development of Pedotransfer Functions and Artificial Neural Networks to Saturation Moisture Content Estimation

Josué Trejo-Alonso / Sebastián Fuentes / Nami Morales-Durán / Carlos Chávez

Modeling of irrigation and agricultural drainage requires knowledge of the soil hydraulic properties. However, uncertainty in the direct measurement of the saturation moisture content ( $θ_{s}$ ) has been generated in several methodologies for its estimation, such as Pedotransfer Functions (PTFs) and Artificial Neuronal Networks (ANNs). In this work, eight different PTFs were developed for the ( $θ_{s}$ ) estimation, which relate to the proportion of sand and clay, bulk density (BD) as well as the saturated hydraulic conductivity ( $K_{s}$ ). In addition, ANNs were developed with different combinations of input and hidden layers for the estimation of $θ_{s}$ . The results showed R $^{2}$ values from $0.9046 \leq R^{2} \leq 0.9877$ for the eight different PTFs, while with the ANNs, values of R $^{2} > 0.9891$ were obtained. Finally, the root-mean-square error (RMSE) was obtained for each ANN configuration, with results ranging from $0.0245 \leq RMSE \leq 0.0262$ . It was found that with particular soil characteristic parameters (% Clay, % Silt, % Sand, BD and $K_{s}$ ), accurate estimate of $θ_{s}$ is obtained. With the development of these models (PTFs and ANNs), high R $^{2}$ values were obtained for 10 of the 12 textural classes.

Access

Page navigation

Document information

Export, share and cite

Document information

Title:

Evaluation and Development of Pedotransfer Functions and Artificial Neural Networks to Saturation Moisture Content Estimation

Contributors:

Josué Trejo-Alonso (author) / Sebastián Fuentes (author) / Nami Morales-Durán (author) / Carlos Chávez (author)

Published in:

Water, Vol 15, Iss 2, p 220 (2023)

Publication date:

2023

ISSN:

DOI:

https://doi.org/10.3390/w15020220

Type of media:

Article (Journal)

Type of material:

Electronic Resource

Language:

Unknown

Keywords:

soil hydraulic properties , artificial intelligence , soil water content , deficit irrigation , Hydraulic engineering , TC1-978 , Water supply for domestic and industrial purposes , TD201-500

Metadata by DOAJ is licensed under CC BY-SA 1.0

Similar titles

Development and Evaluation of Pedotransfer Functions to Estimate Soil Moisture Content at Field Capacity and Permanent Wilting Point for South African Soils

Lindumusa Myeni / Thandile Mdlambuzi / David Garry Paterson et al. | DOAJ | 2021

Free access

Pedotransfer Functions with Interdependency of Hydraulic Parameters

Tietje, O. | British Library Conference Proceedings | 1999

Review on Pedotransfer Functions for Predicting Unsaturated Hydraulic Conductivity

Wang, M. X. / Chang, B. / Wang, D. K. et al. | British Library Conference Proceedings | 2015

Enhanced Soil Moisture Retrieval through Integrating Satellite Data with Pedotransfer Functions in a Complex Landscape of Ethiopia

Ermias Teferi / Greg O’Donnell / Tibebu Kassawmar et al. | DOAJ | 2023

Free access

Practical pedotransfer functions for estimating the saturated hydraulic conductivity

Mbonimpa, M. / Aubertin, M. / Chapuis, R. P. et al. | Online Contents | 2002