LIBS Info: Element Analysis
| Title | Authors | Material | Detector | Spectrometer | Software |
|---|---|---|---|---|---|
| Rapid Nuclear Forensics Analysis via Machine-Learning-Enabled Laser-Induced Breakdown Spectroscopy (LIBS) | Kalambuka Hudson Angeyo, Alix Dehayem-Kamadjeu, Bobby Bhatt | Actinides | Ocean Optics HR2000 | Ocean Optics HR2000 | MATLAB |
| Laser: | Nd:YAG 1064.0000nm 50.0000mJ 10.000Hz |
||||
| Gate Delay: | Noneus | ||||
| Gate Width: | Noneus | ||||
| Pellets of UO3 mixed with cellulose were analysed to understand the applicability of LIBS for the rapid quantification of Nuclear Materials [Nuclear Forensics]. Machine Learning Techniques (PCA and ANN) when then used to improve the performance/detection | |||||
| Element | Detection Limit (ppm) | Wavelength (nm) | Other Wavelengths (nm) | Calibration Method | Calibration Range (ppm) | Notes |
|---|---|---|---|---|---|---|
| U | 34.0000 (None) | -10.0000 | N/A | Machnine Learning | 54.0000-677.0000 | The Machine learning model utilised Uranium peaks from several parts of the spectrum ((1) uranium lines (348 nm to 455 nm), (2) uranium lines (380 nm to 388 nm), and (3) subtle uranium peaks (UV range).) to aid detection. Relative Errors of 6-10% were achieved on validation samples |
| Element | RMSE (ppm) | Wavelength (nm) | Calibration Method | Notes |
|---|