Accurate Quantitative Analysis of LIBS With Image Form Spectra by Using a Hybrid Deep Learning Model of a Convolutional Block Attention Module-Convolutional Neural Network-Long Short-Term Memory

With the development of miniaturized laser-induced breakdown spectroscopy (LIBS) instruments, the desire for accuracy and stability of quantitative analysis of portable LIBS systems is growing. In this research, a hybrid deep learning model of a convolutional block attention module combined with a convolutional neural network and a long short-term memory (CBAM-CNN-LSTM) was for the first time used for quantitative analysis in a LIBS system with a portable spectrometer. Among them, the spectra collected by LIBS were in the form of the image, the convolutional neural network (CNN) module was responsible for feature extraction of image spectra and mining deep features through the CBAM, and the simultaneous accurate quantitative analysis of Ca, Mg, Na, and Ba was realized by the long short-term memory (LSTM) module. Meanwhile, a linear regression (LR), a CNN, and a CNN-LSTM model were compared to the CBAM-CNN-LSTM model. The results showed that the performance of this model was much better than the LR model. More importantly, compared to CNN and CNN-LSTM, the average relative error (RE) of CBAM-CNN-LSTM was reduced by 80.5% and 68.1%, the average root mean square error (RMSE) was reduced by 56.7% and 53.4%, and the average stability was increased by 62.3% and 58.8%, respectively. In addition, the feature visualization results of CNN-LSTM and CBAM-CNN-LSTM displayed that CBAM can more effectively extract the features of characteristic peaks of corresponding elements and suppress the irrelative features. It indicated that the model can achieve an accurate and stable quantitative analysis of LIBS, which has the potential to be applied in the in- site analysis.