Neural Network Analysis for Hierarchical Prediction of Soil Hydraulic Properties

Abstract

Abstract The solution of many field‐scale flow and transport problems requires estimates of unsaturated soil hydraulic properties. The objective of this study was to calibrate neural network models for prediction of water retention parameters and saturated hydraulic conductivity, K s , from basic soil properties. Twelve neural network models were developed to predict water retention parameters using a data set of 1209 samples containing sand, silt, and clay contents, bulk density, porosity, gravel content, and soil horizon as well as water retention data. A subset of 620 samples was used to develop 19 neural network models to predict K s . Prediction of water retention parameters and K s generally improved if more input data were used. In a more detailed investigation, four models with the following levels of input data were selected: (i) soil textural class, (ii) sand, silt, and clay contents, (iii) sand, silt, and clay contents and bulk density, and (iv) the previous variables and water content at a pressure head of 33 kPa. For water retention, the root mean square residuals decreased from 0.107 for the first to 0.060 m 3 m ‐3 for the fourth model while the root mean square residual K s decreased from 0.627 to 0.451 log(cm d ‐1 ). The neural network models performed better on our data set than four published pedotransfer functions for water retention (by ≈0.01–0.05 m 3 m ‐3 ) and better than six published functions for K s (by ≈0.1–0.9 order of magnitude). Use of the developed hierarchical neural network models is attractive because of improved accuracy and because it permits a considerable degree of flexibility toward available input data.