Context: USEPA 3051a is a standard analytical methodology for the extraction of inorganic substances in soils. However, these analyses are expensive, time-consuming and produce chemical residues. Conversely, proximal sensors such as portable X-ray fluorescence (pXRF) spectrometry reduce analysis time, costs and consequently offer a valuable alternative to laboratory analyses.

Aim: We aimed to investigate the feasibility to predict the results of the USEPA 3051a method for 28 chemical elements from pXRF data.

Methods: Samples (n = 179) representing a large area from Brazil were analysed for elemental composition using the USEPA 3051a method and pXRF scanning (Al, Ca, Cr, Cu, Fe, K, Mn, Ni, P, Pb, Sr, Ti, V, Zn and Zr). Linear regressions (simple linear regression – SLR and stepwise multiple linear regressions – SMLR) and machine learning algorithms (support vector machine – SVM and random forest – RF) were tested and compared. Modelling was developed with 70% of the data, while the remaining 30% were used for validation.

Key results: Results demonstrated that SVM and RF performed better than SLR and SMLR for the prediction of Al, Ba, Bi, Ca, Cd, Ce, Co, Cr, Cu, Fe, Mg, Mn, Mo, P, Pb, Sn, Sr, Ti, Tl, V, Zn and Zr; R² and RPD values ranged from 0.52 to 0.94 and 1.43 to 3.62, respectively, as well as the lowest values of RMSE and NRMSE values (0.28 to 0.70 mg kg⁻¹).

Conclusions and implications: Most USEPA 3051a results can be accurately predicted from pXRF data saving cost, time, and ensuring large-scale routine geochemical characterisation of tropical soils in an environmentally friendly way.

背景： USEPA 3051a 是一种用于提取土壤中无机物质的标准分析方法。然而，这些分析昂贵、耗时并且会产生化学残留物。相反，便携式 X 射线荧光 (pXRF) 光谱仪等近端传感器可减少分析时间和成本，从而为实验室分析提供有价值的替代方案。

目的：我们旨在研究从 pXRF 数据预测 28 种化学元素的 USEPA 3051a 方法结果的可行性。

方法： 使用 USEPA 3051a 方法和 pXRF 扫描（Al、Ca、Cr、Cu、Fe、K、Mn、Ni、P、Pb、Sr 、钛、钒、锌和锆）。测试和比较了线性回归（简单线性回归 – SLR 和逐步多元线性回归 – SMLR）和机器学习算法（支持向量机 – SVM 和随机森林 – RF）。建模是使用 70% 的数据开发的，而剩余的 30% 用于验证。

主要结果：结果表明，SVM 和 RF 在预测 Al、B​​a、Bi、Ca、Cd、Ce、Co、Cr、Cu、Fe、Mg、Mn、Mo、P、Pb、Sn 方面表现优于 SLR 和 SMLR 、Sr、Ti、Tl、V、Zn和Zr；R ²和 RPD 值的范围分别为 0.52 至 0.94 和 1.43 至 3.62，以及 RMSE 和 NRMSE 值的最低值（0.28 至 0.70 mg kg ^-1）。

结论和影响：大多数 USEPA 3051a 结果可以根据 pXRF 数据准确预测，从而节省成本和时间，并确保以环保方式对热带土壤进行大规模常规地球化学表征。