LIBS Info: Element Analysis

Title Authors Material Detector Spectrometer Software
Machine Learning Allows Calibration Models to Predict Trace Element Concentration in Soils with Generalized LIBS Spectra J. Yu, Nicole Delepine-Gilon, Zengqi Yue, Yuqing Zhang, Hua Li, Tianlong Zhang, Yishuai Niu, Liang Gao, Ye Tian, Chen Sun Soil ICCD Mechelle 5000
Laser: Nd:YAG
1064.0000nm
60.0000mJ
NoneHz
Gate Delay: 1.000us
Gate Width: 2.000us
A very thorough paper where the Authors utilise both Standard Univariate analysis, and a Neural Network [Back Propagation Neural Network BPNN] to analyse Ag spiked soil samples. Significant improvement is obtained using the BPNN.
Element Detection Limit (ppm) Wavelength (nm) Other Wavelengths (nm) Calibration Method Calibration Range (ppm) Notes
Ag 4.9620 (Calibration Curve Slope) -10.0000 N/A Univariate 20.0000-800.0000 Authors use an Artificial Neural Network to improve the performance of calibration using Ag spiked soil samples
Ag 0.7100 (Calibration Curve Slope) -10.0000 N/A Univariate 20.0000-800.0000 Method utilises an Artificial Neural Network to improve performance on a single (Ag spiked) soil sample
Ag 23.8300 (Calibration Curve Slope) 328.1000 N/A Univariate 20.0000-800.0000 LOD for calibration curve based on combination of Ag spiked soil samples - this provides worse performance than the calibration curves based on a single (spiked) soil sample.
Ag 18.4700 (Calibration Curve Slope) 328.1000 N/A Univariate 20.0000-800.0000 Best result for a calibration curve utilising additions to the one soil sample.


Element RMSE (ppm) Wavelength (nm) Calibration Method Notes