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

Abstract Saturated hydraulic conductivity ( K s ) is a fundamental soil property that regulates the fate of water in soils. Its measurement, however, is cumbersome and instead pedotransfer functions (PTFs) are routinely used to estimate it. Despite much progress over the years, the performance of current generic PTFs estimating K s remains poor. Using machine learning, high‐performance computing, and a large database of over 18,000 soils, we developed new PTFs to predict K s . We compared the performances of four machine learning algorithms and different predictor sets. We evaluated the relative importance of soil properties in explaining K s . PTF models based on boosted regression tree algorithm produced the best models with root‐mean‐squared log‐transformed error in ranges of 0.4 to 0.3 ( log 10 (cm/day) ). The 10th percentile particle diameter ( d 10 ) was found to be the most important predictor followed by clay content, bulk density ( ρ b ), and organic carbon content ( C ). The sensitivity of K s to soil structure was investigated using ρ b and C as proxies for soil structure. An inverse relationship was observed between ρ b and K s , with the highest sensitivity at around 1.8 g/cm 3 for most textural classes. Soil C showed a complex relationship with K s with an overall positive relation for fine‐textured and midtextured soils but an inverse relation for coarse‐textured soils. This study sought to maximize the extraction of information from a large database to develop generic machine learning‐based PTFs for estimating K s . Models developed here have been made publicly available and can be readily used to predict K s .