Faculty of Agriculture, Department of Soil Science and Engineering, Shiraz University, Shiraz, IR Iran.
Faculty of Agriculture, Department of Biosystems Engineering, Shiraz University, Shiraz, IR Iran.
PLoS One. 2024 Nov 14;19(11):e0310622. doi: 10.1371/journal.pone.0310622. eCollection 2024.
Characterization of near (field) saturated hydraulic conductivity (Kfs) of the soil environment is among the crucial components of hydrological modeling frameworks. Since the associated laboratory/field experiments are time-consuming and labor-intensive, pedotransfer functions (PTFs) that rely on statistical predictors are usually integrated with the existing measurements to predict Kfs in other areas of the field. In this study some of the most appropriate machine learning approaches, including variants of artificial neural networks (ANNs) were used for predicting Kfs by some easily measurable soil attributes. The analyses were performed using 100 measurements in Bajgah Agricultural Experimental Station. First, physico-chemical inputs as bulk density (BD), initial water content (Wi), saturated water content (Ws), mean weight diameter (MWD), and geometric mean diameter (GMD) of aggregates, pH, electrical conductivity (EC), and calcium carbonate equivalent (CCE) were measured. Then, radial basis functions (RBFNNs), multilayer perceptron (MLPNNs), hybrid genetic algorithm (GA-NNs), and particle swarm optimization (PSO-NNs) neural networks were utilized to develop PTFs and compared their accuracy with the traditional regression model (MLR) using statistical indices. The statistical assessment indicated that PSO-NNs with the lowest RMSE and MAPE as well as the highest correlation coefficient (R) value provided the most accurate and robust prediction of Kfs. The prediction models ranked as PSO-NNs (R = 0.958; RMSE = 0.343; MAPE = 9.47), GA-NNs (R = 0.949; RMSE = 0.404; MAPE = 11.83), MLPNNs (R = 0.933; RMSE = 0.426; MAPE = 12.13), RBFNNs (R = 0.926; RMSE = 0.452; MAPE = 14.30), and MLR (R = 0.675; RMSE = 0.685; MAPE = 22.54) in terms of their performances for the test data set. Results revealed that all NN models particularly PSO-NNs were efficient in prediction of Kfs. However, further evaluations may be recommended for other soil conditions and input variables to quantify their potential uncertainties and wider potential and versatility before they are used in other geographical locations/soil conditions.
土壤环境近（场）饱和导水率（Kfs）的特征化是水文模型框架的关键组成部分之一。由于相关的实验室/现场实验既耗时又费力，因此通常会将依赖于统计预测因子的转移函数（PTFs）与现有测量结果结合起来，以预测田间其他区域的 Kfs。在这项研究中，使用了一些最适合的机器学习方法，包括人工神经网络（ANNs）的变体，通过一些易于测量的土壤属性来预测 Kfs。该分析使用了巴加农业实验站的 100 个测量值。首先，测量了土壤的物理化学特性，包括土壤容重（BD）、初始含水量（Wi）、饱和含水量（Ws）、平均重量直径（MWD）和几何平均直径（GMD）、pH 值、电导率（EC）和碳酸钙当量（CCE）。然后，利用径向基函数（RBFNNs）、多层感知器（MLPNNs）、混合遗传算法（GA-NNs）和粒子群优化（PSO-NNs）神经网络建立了转移函数，并使用统计指标与传统回归模型（MLR）比较了它们的准确性。统计评估表明，PSO-NNs 具有最低的 RMSE 和 MAPE 以及最高的相关系数（R）值，能够提供最准确和稳健的 Kfs 预测。预测模型的排名依次为 PSO-NNs（R = 0.958；RMSE = 0.343；MAPE = 9.47）、GA-NNs（R = 0.949；RMSE = 0.404；MAPE = 11.83）、MLPNNs（R = 0.933；RMSE = 0.426；MAPE = 12.13）、RBFNNs（R = 0.926；RMSE = 0.452；MAPE = 14.30）和 MLR（R = 0.675；RMSE = 0.685；MAPE = 22.54），用于测试数据集的性能。结果表明，所有的神经网络模型，特别是 PSO-NNs，在 Kfs 的预测方面都非常有效。然而，在将它们应用于其他地理位置/土壤条件之前，可能需要对其他土壤条件和输入变量进行进一步评估，以量化其潜在的不确定性和更广泛的潜力和多功能性。
