Machine learning (ML)-based pedotransfer function (PTF) has become a promising alternative to the generic PTFs for predicting the saturated hydraulic conductivity of soils (K_s). This study enhanced the performance of ML-PTF for predicting K_s by utilizing the prominent extreme gradient boosting (XGB) algorithm trained with the cleaned USKSAT containing approximately 18,000 K_s data for U.S. soils. For improving the performance of the developed XGB-PTF, the outliers were detected and eliminated based on the robust Mahalanobis distance (MD). Furthermore, the cooperative game theory was used to quantify the predictor importance on predictions by XGB-PTF. High multicollinearity among most predictors in the database indicates the need for including all predictors when using PTFs for K_s and XGB-PTF with the selection of all predictors yielded a comparable performance to ML-PTFs in the literature on the identical database. In addition, the relatively narrow prediction interval reflects the reliability of the presented XGB-PTF, and the substantial improvement on the performance of XGB-PTF was obtained using the robust MD by eliminating 3.7% of the database. Notably, the developed XGB-PTF coupled with the game theory enables identifying the clay content as the most dominant factor affecting the K_s of soils, followed by bulk density (ρ_b) and 10th percentile particle diameter (d₁₀) for coarse-grained soils and d₁₀ and ρ_b for fine-grained soils. The three most dominant predictors (clay content, ρ_b, and d₁₀) found in this study consistent with the observed K_s in the literature indicate the reliable evaluation of predictor importance using the game theory.

基于机器学习 (ML) 的土壤传递函数 (PTF) 已成为预测土壤饱和导水率 ( K _s ) 的通用 PTF 的有前途的替代方案。这项研究通过利用使用包含大约 18,000 K _s的清洁 USKSAT 训练的突出的极端梯度提升 (XGB) 算法来增强 ML-PTF 预测K _s的性能美国土壤数据。为了提高开发的 XGB-PTF 的性能，基于鲁棒马氏距离 (MD) 检测和消除异常值。此外，合作博弈论被用来量化预测变量对 XGB-PTF 预测的重要性。数据库中大多数预测变量之间的高度多重共线性表明在对K _s使用 PTF 时需要包括所有预测变量和 XGB-PTF 以及所有预测变量的选择在相同数据库的文献中产生了与 ML-PTF 相当的性能。此外，相对较窄的预测区间反映了所提出的 XGB-PTF 的可靠性，并且通过消除 3.7% 的数据库，使用鲁棒 MD 获得了 XGB-PTF 性能的实质性改进。值得注意的是，开发的 XGB-PTF 与博弈论相结合，能够确定粘土含量是影响土壤K _s的最主要因素，其次是容重 ( ρ _b ) 和第 10 个百分位粒径 ( d ₁₀ )土壤和d ₁₀和ρ _b适用于细粒土壤。本研究中发现的三个最主要的预测因子（粘土含量、ρ _b和d ₁₀）与文献中观察到的K _s一致，表明使用博弈论对预测因子重要性的可靠评估。