EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Advancing environmental and food system monitoring with machine-learning-enhanced X-ray fluorescence analytics

Yicong Li, Wanqi Jia, Wilfred Angie Abia, Simon A Haughey, Manus Carey, Coalain McCreanor, Mark Mooney, Maame Croffie, Karen Daly, Britt Marianna Maestroni, Caroline Meharg, Andrew A Meharg und 2 weitere

Environment International · 2026-06 · 212 · 110294

DOI: 10.1016/j.envint.2026.110294 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Environment International, 2026-06. Verfasst von Yicong Li und 13 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Global Food Security, The Queen's University of Belfast, Belfast BT9 5DL, Northern Ireland, UK. Hauptthemen laut MEDLINE: Machine Learning, Spectrometry, X-Ray Emission, Environmental Monitoring, Food Analysis. Die Arbeit nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: UK Research and Innovation, International Atomic Energy Agency, Department of Agriculture, Environment and Rural Affairs, UK Government.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deficiencies of essential and excesses of toxic elements contribute to substantial, yet frequently under‑recognized, global disease burden. Energy Dispersive (ED) X-ray fluorescence (XRF) spectroscopy is widely used for rapid, multi-elemental analysis. However, different instruments and XRF-system configurations vary in performance, constrained by sensitivity, matrix effects and spectral interferences. Presented here is a novel analytics solution. Integrating across common XRF platforms, sequences of systematic model building, and validation were performed with diverse machine-learning algorithms. A total of 85 certified reference materials, including 20 soils and 65 food and biological samples, were used to provide a comparable validation framework. Matrix-specific limits of detection were calculated, and platform performance was assessed. Hybrid calibration strategies using linear, partial least squares, and random forest enhanced XRF models, were developed to correct systematic biases. Unlike approaches based on direct prediction from high-dimensional spectra, this framework uses XRF-derived concentrations as inputs and corrects residual deviations. Machine learning-assisted calibration improved measurement accuracy, particularly for handheld XRF. However, no single correction model was universally applicable. Performance varied by element, matrix, and instrument. These results show that hybrid calibration improves the reliability of multi-elemental XRF analysis and supports its application in environmental and food system monitoring.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningSpectrometry, X-Ray EmissionEnvironmental MonitoringFood AnalysisCalibrationRandom Forest

Stichwörter der Autor:innen

AccuracyCertified reference materialsHybrid calibration frameworkMachine learningMulti-elemental measurementX-ray fluorescence

Autor:innen und Institutionen

  • Institute for Global Food Security, The Queen's University of Belfast, Belfast BT9 5DL, Northern Ireland, UK.
  • Institute for Global Food Security, The Queen's University of Belfast, Belfast BT9 5DL, Northern Ireland, UK; Department of Biochemistry, Faculty of Science, University of Yaounde 1, BP 812 Yaounde, Cameroon.
  • Institute for Global Food Security, The Queen's University of Belfast, Belfast BT9 5DL, Northern Ireland, UK; Co-Centre for Sustainable Food Systems, School of Biological Sciences, The Queen's University of Belfast, Bel…
  • Environment Soils and Land Use Department, Teagasc Johnstown Castle Research Centre, Wexford Y35 TC97, Ireland.
  • Food Safety and Control Laboratory, Joint FAO/IAEA Centre of Nuclear Techniques in Food and Agriculture, Department of Nuclear Sciences and Applications, International Atomic Energy Agency, Wagramerstrasse 5, A-1400 Vie…
  • Institute for Global Food Security, The Queen's University of Belfast, Belfast BT9 5DL, Northern Ireland, UK; Thammasat University Center of Excellence in Global Food Security, Mhu 18, Khong Luang, Pathum Thani 12120, T…

Förderung

  • UK Research and Innovation
  • International Atomic Energy Agency
  • Department of Agriculture, Environment and Rural Affairs, UK Government

Zitieren

APA

Li, Y., Jia, W., Abia, W. A., Haughey, S. A., Carey, M., McCreanor, C., Mooney, M., Croffie, M., Daly, K., Maestroni, B. M., Meharg, C., Meharg, A. A., Elliott, C. T., & Williams, P. N. (2026). Advancing environmental and food system monitoring with machine-learning-enhanced X-ray fluorescence analytics. Environment International, 212, 110294. https://doi.org/10.1016/j.envint.2026.110294

Vancouver

Li Y, Jia W, Abia WA, Haughey SA, Carey M, McCreanor C, et al. Advancing environmental and food system monitoring with machine-learning-enhanced X-ray fluorescence analytics. Environment International. 2026;212:110294. doi:10.1016/j.envint.2026.110294

BibTeX
@article{Li2026,
  author = {Li, Yicong and Jia, Wanqi and Abia, Wilfred Angie and Haughey, Simon A and Carey, Manus and McCreanor, Coalain and Mooney, Mark and Croffie, Maame and Daly, Karen and Maestroni, Britt Marianna and Meharg, Caroline and Meharg, Andrew A and Elliott, Christopher T and Williams, Paul N},
  title = {Advancing environmental and food system monitoring with machine-learning-enhanced X-ray fluorescence analytics},
  journal = {Environment International},
  year = {2026},
  volume = {212},
  pages = {110294},
  doi = {10.1016/j.envint.2026.110294}
}
Kostenlos starten →