The accuracy of determining arsenic and lead using the optical technique Slurry–Total Reflection X-ray Fluorescence (Slurry-TXRF) was significantly enhanced through the application of a machine learning method, aimed at improving the ecological risk assessment of agricultural soils. The overlapping of the arsenic Kα signal at 10.55 keV with the lead Lα signal at 10.54 keV due to the relatively low resolution of TXRF could compromise the determination of lead. However, by applying a Partial Least Squares (PLS) machine learning algorithm, we mitigated interference variations, resulting in improved selectivity and accuracy. Specifically, the average percentage error was reduced from 15.6% to 9.4% for arsenic (RMSEP improved from 5.6 mg kg⁻¹ to 3.3 mg kg⁻¹) and from 18.9% to 6.8% for lead (RMSEP improved from 12.3 mg kg⁻¹ to 5.03 mg kg⁻¹) compared to the previous univariable model. This enhanced predictive accuracy, within the set of samples concentration range, is attributable to the efficiency of the multivariate calibration first-order advantage in quantifying the presence of interferents. The evaluation of X-ray fluorescence emission signals for 26 different synthetic calibration mixtures confirmed these improvements, overcoming spectral interferences. Additionally, the application of these models enabled the quantification of arsenic and lead in soils from a viticultural subregion of Chile, facilitating the estimation of ecological risk indices in a fast and reliable manner. The results indicate that the contamination level of these soils with arsenic and lead ranges from moderate to considerable.

A machine learning method was applied to improve the accuracy of the determination of Arsenic and Lead by Slurry - Total Reflection X-ray fluorescence (Slurry-TXRF) with the idea of being applied to the ecological assessment of agricultural soils. Due to TXRF's relatively low resolution, a particular and well-known overlapping of arsenic signal Kα at 10.55 keV with Lαsignal at 10.54 keV of the lead can compromise its determination. Applying a multivariate calibration method based on a machine learning algorithm, for example, Partial Least Squares, could reduce variations due to interference and, consequently, improve the selectivity and accuracy in arsenic and lead determination. In this work the X-Ray fluorescence emission signals was evaluated for a set of 26 different synthetic calibration mixtures and a significant accuracy improvement for arsenic and lead determination was observed, overcoming the problems associated with spectral interferences. Furthermore, with these models, arsenic and lead were quantified from soils of a viticultural subregion of Chile, allowing the estimation of ecological indices in a fast and reliable way. The results report that the level of contamination of these soils concerning arsenic and lead is moderate to considerable.