Summary
This study validates portable spectroscopy techniques (pXRF and DRIFT-MIR) combined with machine learning as a rapid, non-destructive method for comprehensive nutrient and contaminant quantification in organic soil amendments. The authors demonstrate that both spectrometric approaches, when paired with forest regression or extreme gradient boosting algorithms, provide similar broad analytical capabilities. The findings position portable spectrometry with machine learning as a scalable, cost-effective quality assessment tool for organic amendments, particularly valuable in resource-limited settings.
UK applicability
The methodology could support UK organic certification bodies and amendment producers seeking rapid, non-destructive quality assurance systems for compost and other organic materials. However, applicability depends on whether the training datasets and model generalisation extend to amendments commonly used in UK farming systems.
Key measures
Estimated concentrations of total carbon, nitrogen, and total elemental composition across multiple elements in organic amendments using pXRF and DRIFT-MIR spectroscopy paired with machine learning models; model generalisation assessed through cross-validation trials
Outcomes reported
The study evaluated portable X-ray fluorescence (pXRF) and Diffuse Reflectance Fourier Transformed Mid-Infrared (DRIFT-MIR) spectroscopy combined with machine learning algorithms to estimate macro- and micronutrient concentrations in organic amendments. Both forest regression and extreme gradient boosting methods demonstrated similar capabilities, with pXRF particularly suitable for nutrient and contaminant analysis.
Topic tags
Dig deeper with Pulse AI.
Pulse AI has read the whole catalogue. Ask about this record, its theme, or how the findings apply to UK farming and policy — every answer cites the underlying studies.