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

Abstract

Modeling of irrigation and agricultural drainage requires knowledge of the soil hydraulic properties. However, uncertainty in the direct measurement of the saturation moisture content (θs) 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 (θs) estimation, which relate to the proportion of sand and clay, bulk density (BD) as well as the saturated hydraulic conductivity (Ks). In addition, ANNs were developed with different combinations of input and hidden layers for the estimation of θs. The results showed R2 values from 0.9046≤R2≤0.9877 for the eight different PTFs, while with the ANNs, values of R2>0.9891 were obtained. Finally, the root-mean-square error (RMSE) was obtained for each ANN configuration, with results ranging from 0.0245≤RMSE≤0.0262. It was found that with particular soil characteristic parameters (% Clay, % Silt, % Sand, BD and Ks), accurate estimate of θs is obtained. With the development of these models (PTFs and ANNs), high R2 values were obtained for 10 of the 12 textural classes.

A soil database from Queretaro, Mexico for assessment of crop and irrigation water requirements

“…For the knowledge of some soil parameters such as saturated moisture content (θ s ) and saturated hydraulic conductivity (K s ) can be obtained by field and laboratory tests, but they are costly and time consuming, also, they can be estimated by pedotransfer functions 15 , 16 or neural networks 17 – 19 that relate more properties of the soil being analyzed. However, to achieve the above, sufficient data is required to have a representative equation of the soil being analyzed.…”

“…The integration of all soil information was performed in a dataset named NaneSoil 23 . The information contained in the dataset can be used to perform statistical analysis, to develop pedotransfer functions 19 , 24 , use of neural networks 19 , 25 , calculation of crop water requirement as a function of soil texture 26 – 28 , surface irrigation system design 29 and pressurized 30 , or any other agronomic parameter of interest. NaneSoil contains most of the agronomic parameters necessary for the study of crop water requirements in different soils, and therefore, it is an excellent tool that can be used by farmers, academics, students, and people involved in crop production and research.…”