We need measurements of soil water retention (SWR) and available water capacity (AWC) to assess and model soil functions, but methods are time-consuming and expensive. Our aim here was to investigate the modelling of AWC and SWR with visible–near-infrared spectra (vis–NIR) and the machine-learning method cubist. We used soils from 54 locations across Australian agricultural regions, from three depths: 0–15 cm, 15–30 cm and 30–60 cm. The volumetric water content of the samples and their vis–NIR spectra were measured at seven matric potentials from −1 kPa to −1500 kPa. We modelled the following: (i) AWC directly with the average spectra of the samples measured at different water contents, (ii) water contents at field capacity and permanent wilting point and calculated AWC from those estimates, (iii) AWC with spectra of air-dried soils, and (iv) parameters of the Kosugi and van Genuchten SWR models, then reconstructed the SWR curves to calculate AWC. We compared the estimates with those from a local pedotransfer function (PTF) and an established Australian PTF. The accuracy of the spectroscopic approaches varied but was generally better than the PTFs. The spectroscopic methods are also more practical because they do not require additional soil properties for the modelling. The root-mean squared-error (RMSE) of the spectroscopic methods ranged from 0.033 cm³ cm⁻³ to 0.059 cm³ cm⁻³. The RMSEs of the PTFs were 0.050 cm³ cm⁻³ for the local and 0.077 cm³ cm⁻³ for the general PTF. Spectroscopy with machine learning provides a rapid and versatile method for estimating the AWC and SWR characteristics of diverse agricultural soils.

中文翻译：

---

用可见-近红外光谱和机器学习模拟土壤保水性和保水性

我们需要测量土壤保水性 (SWR) 和可用水容量 (AWC) 来评估和模拟土壤功能，但这些方法既耗时又昂贵。我们的目标是使用可见-近红外光谱 (vis-NIR) 和机器学习方法cubist研究 AWC 和 SWR 的建模. 我们使用了来自澳大利亚农业区 54 个地点的土壤，来自三个深度：0-15 厘米、15-30 厘米和 30-60 厘米。在从-1 kPa 到-1500 kPa 的七个基质电位下测量样品的体积含水量及其可见近红外光谱。我们模拟了以下内容：（i）AWC 直接使用在不同含水量下测量的样品的平均光谱，（ii）田间容量和永久萎蔫点的含水量，并根据这些估计值计算 AWC，（iii）AWC 与空气光谱-干燥的土壤，以及 (iv) Kosugi 和 van Genuchten SWR 模型的参数，然后重建 SWR 曲线以计算 AWC。我们将估计值与来自本地 pedotransfer function (PTF) 和已建立的澳大利亚 PTF 的估计值进行了比较。光谱方法的准确性各不相同，但通常优于 PTF。光谱方法也更实用，因为它们不需要额外的土壤特性进行建模。光谱方法的均方根误差 (RMSE) 范围为 0.033 cm³  cm ^-3至0.059 cm ³  cm ^-3。PTF 的 RMSE 为局部 PTF 的 0.050 cm ³  cm ^-3和一般 PTF 的 0.077 cm ³  cm ^-3。带有机器学习的光谱学为估计不同农业土壤的 AWC 和 SWR 特性提供了一种快速且通用的方法。