Journal of Aerosol Science · 2022 · 12 citations · 34 references
Natural SciencesMaterials EngineeringMaterials ScienceMachine LearningNanomaterialsSpectroscopyAerosol ScienceEmission SpectroscopyFluorescence SpectroscopyNanomaterial CharacterizationNanoparticle CharacterizationOptical SpectroscopyAerosol Measurement TechniquesAerosol Optical PropertiesAerosol PropertiesCompositional TuningEmission SpectraOptical Emission SpectraOptical Emission SpectroscopyX-ray Fluorescence Spectroscopy
Spark ablation is an established technique for generating aerosol nanoparticles. Recent demonstrations of compositional tuning of bimetallic aerosols have led to a demand for on-line stoichiometry measurements. In this work, we present a simple, non-intrusive method to determine the composition of a binary AuAg nanoparticle aerosol on-line using the optical emission from the electrical discharges. Machine learning models based on the least absolute shrinkage and selection operator (LASSO) were trained on optical spectra datasets collected during aerosol generation and labelled with X-ray fluorescence spectroscopy (XRF) compositional measurements. Models trained for varying discharge energies demonstrated good predictability of nanoparticle stoichiometry with mean absolute errors <10 at. %. While the models utilized the emission spectra at different wavelengths in the predictions, a combined model using spectra from all discharge energies made accurate predictions of the AuAg nanoparticle composition, showing the method's robustness under variable synthesis conditions.
34
Scikit-learn: Machine Learning in Python
Fabián Pedregosa, Gaël Varoquaux, Alexandre Gramfort et al. · arXiv (Cornell University) · 2012 · 63.7K citations · Full text
Generation of nanoparticles by spark discharge
Nooshin Salman Tabrizi, Marc Ullmann, V.A. Vons et al. · Journal of Nanoparticle Research · 2008 · 291 citations