Laser-induced Breakdown Spectroscopy Quantitative Analysis Research Articles

Analysis of an Al-Sn-Cu alloy by calibration-free laser-induced breakdown spectroscopy under varying sample temperature conditions

This study investigates the impact of sample temperature Ts on Laser-Induced Breakdown Spectroscopy (LIBS) emission characteristics and Calibration-Free LIBS (CF-LIBS) quantitative analysis in vacuum and air. Using an aluminum‑tin‑copper alloy, we analyze spectral lines within a 20 °C to 170 °C temperature range. Evaluation encompasses emission line intensities, plasma parameters, expansion imagery, and laser ablation crater morphologies. CF-LIBS analysis underlines that elevated Ts maintains quantitative accuracy even for minor elements with weak lines. In atmospheric conditions, tin segregation occurs, yet CF-LIBS remains robust. These results highlight CF-LIBS's potential for varied applications by mitigating Ts-induced effects.

Multi-component quantitative analysis of LIBS using adaptively optimized multi-branch CNN

Multi-component quantitative analysis of laser-induced breakdown spectroscopy (LIBS) is very important for industrial process control, food safety and space exploration. Due to the strong background interference and complex matrix effect, traditional quantitative analysis methods are difficult to realize accurate multi-component regression. Deep learning has the advantages of automatically extracting full-spectrum features and strong nonlinear modeling capabilities, which provides new opportunities for advancing the progress of LIBS quantitative analysis. However, due to the large difference of spectral line intensity and spectral cross-interference, existing deep learning models have limited performance for simultaneous multi-component regression. To this end, a novel adaptively optimized multi-branch convolution neural network (AOMB-CNN) framework is proposed for multi-component quantitative analysis of LIBS. Multi-branch structure is adopted to ensure the accuracy of multi-component content simultaneously. Dynamic weighted loss function and Bayesian optimization algorithm are used to adaptively optimize the deep learning model. The results demonstrate that the AOMB-CNN can effectively improve the performance of multi-component regression on 2 LIBS datasets compared with the traditional quantitative analysis methods. The root mean square error (RMSE) of 8 components of the ChemCam test set are 2.4465, 0.3486, 1.2481, 1.3909, 0.9010, 0.8892, 0.6700, and 0.5498 respectively, and the RMSE of 4 components of the steel test sets are 1.9787, 0.3455, 0.6025 and 1.6631 respectively. The proposed method provides an end-to-end, adaptively optimized, full-spectrum deep learning solution for LIBS multi-component content measurement without human intervention.

Multielement simultaneous quantitative analysis of trace elements in stainless steel via full spectrum laser-induced breakdown spectroscopy

Laser-Induced Breakdown Spectroscopy (LIBS) instruments are increasingly recognized as valuable tools for detecting trace metal elements due to their simplicity, rapid detection, and ability to perform simultaneous multi-element analysis. Traditional LIBS modeling often relies on empirical or machine learning-based feature band selection to establish quantitative models. In this study, we introduce a novel approach—simultaneous multi-element quantitative analysis based on the entire spectrum, which enhances model establishment efficiency and leverages the advantages of LIBS. By logarithmically processing the spectra and quantifying the cognitive uncertainty of the model, we achieved remarkable predictive performance (R2) for trace elements Mn, Mo, Cr, and Cu (0.9876, 0.9879, 0.9891, and 0.9841, respectively) in stainless steel. Our multi-element model shares features and parameters during the learning process, effectively mitigating the impact of matrix effects and self-absorption. Additionally, we introduce a cognitive error term to quantify the cognitive uncertainty of the model. The results suggest that our approach has significant potential in the quantitative analysis of trace elements, providing a reliable data processing method for efficient and accurate multi-task analysis in LIBS. This methodology holds promising applications in the field of LIBS quantitative analysis.

Substrate-Assisted Laser-Induced Breakdown Spectroscopy Combined with Variable Selection and Extreme Learning Machine for Quantitative Determination of Fenthion in Soybean Oil

The quality and safety of edible vegetable oils are closely related to human life and health, meaning it is of great significance to explore the rapid detection methods of pesticide residues in edible vegetable oils. This study explored the applicability potential of substrate-assisted laser-induced breakdown spectroscopy (LIBS) for quantitatively determining fenthion in soybean oils. First, we explored the impact of laser energy, delay time, and average oil film thickness on the spectral signals to identify the best experimental parameters. Afterward, we quantitatively analyzed soybean oil samples using these optimized conditions and developed a full-spectrum extreme learning machine (ELM) model. The model achieved a prediction correlation coefficient (RP2) of 0.8417, a root mean square error of prediction (RMSEP) of 167.2986, and a mean absolute percentage error of prediction (MAPEP) of 26.46%. In order to enhance the prediction performance of the model, a modeling method using the Boruta algorithm combined with the ELM was proposed. The Boruta algorithm was employed to identify the feature variables that exhibit a strong correlation with the fenthion content. These selected variables were utilized as inputs for the ELM model, with the RP2, RMSEP, and MAPEP of Boruta-ELM being 0.9631, 71.4423, and 10.06%, respectively. Then, the genetic algorithm (GA) was used to optimize the parameters of the Boruta-ELM model, with the RP2, RMSEP, and MAPEP of GA-Boruta-ELM being 0.9962, 11.005, and 1.66%, respectively. The findings demonstrate that the GA-Boruta-ELM model exhibits excellent prediction capability and effectively predicts the fenthion contents in soybean oil samples. It will be valuable for the LIBS quantitative detection and analysis of pesticide residues in edible vegetable oils.

Application of S-transform-based nonlinear processing for accurate LIBS quantitative analysis of iron ore slurry.

Real-time Fe content monitoring in iron ore slurry is crucial for evaluating concentrate quality and enhancing mineral processing efficiency. Laser-induced breakdown spectroscopy (LIBS) is a promising technique for the online monitoring of elemental content at industrial sites. However, LIBS measurements are hampered by the matrix effect and the self-absorption effect, limiting the precision of linear analytical processes. To overcome this, we propose to introduce a nonlinear processing unit based on the S-transform to incorporate nonlinearity into the data analysis process. This approach integrates a feature selection unit based on the spectral distance variable selection method (SDVS), a nonlinear processing unit based on the S-transform (ST), and a partial least squares regression model (PLS). To demonstrate the improvement in accuracy achieved through nonlinear processing, a comparative analysis involving five models, Raw-PLS, SDVS-PLS, ST-PLS, SDVS-ANN, and SDVS-ST-PLS, is conducted. The results reveal a significant improvement in the performance of the SDVS-ST-PLS model, effectively facilitating the successful application of the LIBSlurry analyzer to the mineral flotation process.

An approach for measurement of the magnetic field near the surface of plasma-facing components in tokamak by laser induced breakdown spectroscopy based on Zeeman effect

Laser-induced breakdown spectroscopy (LIBS) has been demonstrated to diagnose the surface element distribution of plasma-facing components (PFCS) in fusion devices. However, the magnetic field intensity and polarity near the wall surface change frequently and cannot be measured in real time, which will affect the analytical accuracy of LIBS results. The determination of the strength and polarity direction of the magnetic field near the surface will be conducive to the quantitative analysis of LIBS and provide valuable information for the distribution of the magnetic field near the surface of PFCs. In this work, the effects of magnetic fields on the characteristics of laser-induced Mo plasma, such as the ablation depth and mass, the spatio-temporal evolution behavior of spectrum and the plasma parameters, were first systematically investigated. The different phenomenon of continuum radiation, Mo I line and Mo II line under the magnetic field were mutually verified by optical emission spectroscopy and fast plasma imaging methods. Meanwhile, an approach for measurement of the magnetic field intensity and polarity near the surface of PFCS by LIBS method has been proposed and investigated. When the magnetic field polarity is changed, the spatial distribution profile of Mo spectrum will drift in the opposite direction affected by of the Lorentz force, which realizes the measurement of magnetic field polarity. Moreover, the splitting distance of Mo I line caused by Zeeman effect with the variable magnetic fields were preliminarily calculated. The experimental values of splitting distance agree well with the theoretical values that calculated by the known magnetic field strength. These results confirm the feasibility of measuring the magnetic field intensity and polarity of PFCs surface by LIBS approach.

Deep learning regression for quantitative LIBS analysis

One of the most promising innovation strategies for sorting and recycling post-consumer aluminium scrap is using quantitative Laser-Induced Breakdown Spectroscopy (LIBS) analysis. However, existing methods to estimate alloying element concentrations based on LIBS spectra, such as linear univariate regression and Machine Learning models, are still too limited in their performance to achieve the accuracy demanded by the industry. Therefore, this study presents novel Deep Learning approaches and compares their performance to those of traditional univariate regression and Machine Learning methods in terms of RMSE, MAE, and R2 value. For this evaluation, two sample sets of aluminium pieces are used: one containing 27 certified aluminium reference samples and the second containing 733 post-consumer scrap pieces for which the ground truth concentrations are determined by X-Ray Fluorescence (XRF).Adopting multiple loss functions, one for each element, has proven its significant value for the regression performance. It improves the results for all performance metrics in the Scrap Sample set, and the same is true for the Reference Sample set, except for the coefficient of determination of Fe, Mn and Mg. In addition, the proposed methodology considers the learning prioritisation problem to prevent that learning the concentration of the base element is prioritised over the alloying elements. Although the effect of excluding the base alloy aluminium from the learning is small and not always positive for the performance, demonstrating this effect is also considered valuable. Since the average RMSE on the prediction is just 0.02 wt% for Al and Si, and not more than 0.01 wt% for Fe, Cu, Mn, Mg, and Zn, the best-performing Deep Learning model shows promise for the future of LIBS in metal sorting applications.

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 CNN module was responsible for feature extraction of image spectra, mining deep features through the CBAM, and the simultaneous accurate quantitative analysis of Ca, Mg, Na and Ba was realized by the 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 of CBAM-CNN-LSTM was reduced by 80.5% and 68.1%, the average root mean square error 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.

Application of elastic net in quantitative analysis of major elements using Martian laser-induced breakdown spectroscopy datasets

Multiple sets of laser-induced breakdown spectroscopy (LIBS) instruments, including ChemCam (Curiosity), SuperCam (Perseverance), and the Mars Surface Composition Detector (MarSCoDe, Zhurong), are working currently on the surface of Mars, a booming scene of LIBS technology application to planetary exploration. One of the primary challenges faced by those LIBS instruments is accurate and quantitative chemical composition determination of unexplored geological targets. Elastic net is a linear regression model that combines ridge regression and lasso model, which inherits the sparseness of lasso and the stability of ridge. In this work, we investigated the spectral features selected by elastic net model, the model performance and application to over 23,000 LIBS points. Selected features exhibit significant emission lines that are attributed to a certain single element and a few lines attributed to other related elements. These features enhance the interpretability of the model and weaken the matrix effect in LIBS quantitative analysis. In comparison, the results of elastic net are comparable and may be slightly better in some cases than other common linear regression models. For igneous calibration targets (norite, picrite, and shergottite), the predictions of elastic net are closer to the values measured in Earth laboratory than the final multivariate oxide composition values predicted by ChemCam team. Finally, we predicted the oxide abundances of 8 major elements from Mars LIBS spectra of over 23,000 points using elastic net. The predicted values of the elastic net models are highly correlated with those from the ChemCam team model. These results indicate that elastic net is viable for quantitative analysis Mars LIBS spectra. We propose that elastic net is an important candidate model for the quantitative analysis of the Zhurong MarSCoDe LIBS spectra.

Comparison on Quantitative Analysis of Olivine Using MarSCoDe Laser-Induced Breakdown Spectroscopy in a Simulated Martian Atmosphere

A Mars Surface Composition Detector (MarSCoDe) instrument mounted on Zhurong rover of Tianwen-1, adopts Laser-Induced Breakdown Spectroscopy (LIBS), with no sample preparation or dust and coatings ablation required, to conduct rapid multi-elemental analysis and characterization of minerals, rocks and soils on the surface of Mars. To test the capability of MarSCoDe LIBS measurement and quantitative analysis, some methods of multivariate analysis on olivine samples with gradient concentrations were inspected based on the spectra acquired in a Mars-simulated environment before the rover launch in 2020. Firstly, LIBS spectra need preprocessing, including background subtraction, random signal denoising, continuum baseline removal, spectral drift correction and wavelength calibration, radiation calibration, and multi-channel spectra subset merging. Then, the quantitative analysis with univariate linear regression (ULR) and multivariate linear regression (MLR) are performed on the characteristic lines, while principal component regression (PCR), partial least square regression (PLSR), ridge, least-absolute-shrinkage-and-selection-operator (LASSO) and elastic net, and nonlinear analysis with back-propagation (BP) are conducted on the entire spectral information. Finally, the performance on the quantitative olivine analyzed by MarSCoDe LIBS is compared with the mean spectrum and all spectra for each sample and evaluated by some statistical indicators. The results show that: (1) the calibration curve of ULR constructed by the characteristic line of magnesium and iron indicates the linear relationship between the spectral signal and the element concentration, and the limits of detection of forsterite and fayalite is 0.9943 and 2.0536 (c%) analyzed by mean spectra, and 2.3354 and 3.8883 (c%) analyzed by all spectra; (2) the R2 value on the calibration and validation of all the methods is close to 1, and the predicted concentration estimated by these calibration models is close to the true concentration; (3) the shrinkage or regularization technique of ridge, LASSO and elastic net perform better than the ULR and MLR, except for ridge overfitting on the testing sample; the best results can be obtained by the dimension reduction technique of PCR and PLSR, especially with PLSR; and BP is more applicable for the sample measured with larger spectral dataset.

Exploiting Data Uncertainty for Improving the Performance of a Quantitative Analysis Model for Laser-Induced Breakdown Spectroscopy.

The accuracy and precision of laser-induced breakdown spectroscopy (LIBS) quantitative analysis are significantly limited by the spectral noise. Normalization and ensemble averaging of multiple spectra were often used to preprocess spectra. However, these methods cannot completely remove the spectral noise. Data uncertainty due to the irremovable spectral noise will affect LIBS quantitative analysis. Therefore, this paper proposes a method using data uncertainty to improve the performance of LIBS quantitative analysis. The proposed method uses several spectra to characterize each sample to preserve some data uncertainty in the calibration data matrix. Thus, the data uncertainty is used to optimize the calibration model for improving the toleration to the spectral signal variation. As a result, the optimized calibration model had better accuracy and robustness than the calibration model trained by conventional method. The best root mean square error of prediction (RMSEP) of the ash content of coal was 1.152% for the optimized calibration model, while that for the conventional calibration model was 1.718%. The optimized calibration model also showed a lower relative standard deviation (RSD) value of repeated predictions. Moreover, the calibration model for predicting the ash content in biomass was also optimized by the proposed method. The optimized calibration model outperformed the conventional calibration model again, which demonstrated the extensive applicability of the proposed method.

Comparison of Convolutional and Conventional Artificial Neural Networks for Laser-Induced Breakdown Spectroscopy Quantitative Analysis.

The introduction of "deep learning" algorithms for feature identification in digital imaging has paved the way for artificial intelligence applications that up to a decade ago were considered technologically impossible to achieve, from the development of driverless vehicles to the fully automated diagnostics of cancer and other diseases from histological images. The success of deep learning applications has, in turn, attracted the attention of several researchers for the possible use of these methods in chemometrics, applied to the analysis of complex phenomena as, for example, the optical emission of laser-induced plasmas. In this paper, we will discuss the advantages and disadvantages of convolutional neural networks, one of the most diffused deep learning techniques, in laser-induced breakdown spectroscopy (LIBS) applications (classification and quantitative analysis), to understand the real potential of "deep LIBS" in practical everyday use. In particular, the comparison with the results obtained using "shallow" artificial neural networks will be presented and discussed, taking as a case study the analysis of six bronze samples of known composition.

Spectral knowledge-based regression for laser-induced breakdown spectroscopy quantitative analysis

Laser-induced breakdown spectroscopy (LIBS) is a promising atomic emission spectroscopic technique for multi-elemental analysis and has the advantages of real-time multi-element measurement, minimal sample preparation and remote detection. However, the quality of LIBS data can be low due to matrix effects and signal uncertainty which hinders the wide application of LIBS. Recent studies attempt to improve the performance of LIBS quantitative analysis using linear and nonlinear multivariate analysis models. Linear models can easily present how key variables contribute to the prediction but suffer from performance degradation if data has a high degree of nonlinearity. Nonlinear models tend to have good performance, but they lack simple and intuitive explanations for the contribution of variables and are prone to overfitting. Moreover, nonlinear models used in LIBS quantitative analysis, such as support vector regression (SVR) and kernel extreme learning machine (K-ELM), are not designed to incorporate domain knowledge of spectral data. In this work, a new machine learning algorithm is proposed, namely spectral knowledge-based regression (SKR), which integrates linear and nonlinear models to improve the performance of LIBS quantitative analysis. The linear model is knowledge-driven and built on key variables correlated with analyte composition. The nonlinear model is data-driven and transforms the input data into a kernel matrix. The proposed SKR is tested on 4 LIBS datasets and outperforms 5 baseline methods on 12 of 18 quantification tasks. Moreover, it intuitively explains the contribution of key variables towards prediction and has the same low computational complexity as ridge regression These results demonstrate that SKR inherits the high accuracy of nonlinear modelling and the simple variable interpretability of linear models. Therefore, it can serve as a promising method for improving the accuracy and reliability of LIBS quantitative analysis.

Quantitative analysis of trace carbon in steel samples using collinear long-short double-pulse laser-induced breakdown spectroscopy

The trace carbon (C) composition in ultra-low carbon steel is measured by Laser-Induced Breakdown Spectroscopy (LIBS). Five standard steel samples, with C content between 9 and 89 μg/g, are used to study the performance of LIBS quantitative analysis. Single-pulse LIBS (SP-LIBS) and long-short double-pulse LIBS (LS-DP-LIBS) have been used to measure these five samples. Due to the carbon contamination on sample surface, SP-LIBS cannot obtain an available analysis result. To reduce the influence of carbon contamination, the pretreatment pulse method is employed in this work. The experimental results of the continuous irradiation show that the long-short pretreatment pulses can effectively eliminate the influence of carbon contamination. Finally, the trace carbon in steel samples has been successfully measured by LS-DP-LIBS with pretreatment pulses. The LOD value of carbon is 22.6 μg/g. For the measured five samples, the relative error of prediction (REP%) is between 6.1% and 35.7% and the relative standard deviation (RSD%) is between 13.9% and 58.3%.

A transferred multitask regularization convolutional neural network (TrMR-CNN) for laser-induced breakdown spectroscopy quantitative analysis

A quantification method combining transfer learning, a convolutional neural network and multitask regularization to improve prediction accuracy and model robustness on limited data.

Determination of the uranium elemental concentration in molten salt fuel using laser-induced breakdown spectroscopy with partial least squares-artificial neural network hybrid models

Accurate uranium (U) composition analysis of the molten salt nuclear fuel mixture is a necessary step in nuclear fuel quality control. Laser-induced breakdown spectroscopy (LIBS) is an optical emission spectrometry technique for elemental composition. The non-linear phenomena in LIBS signal are the drawback of this technique, especially for high atomic number (Z) element in a complex matrix. To overcome this limitation, a hybrid chemometrics model of the partial least squares-artificial neural network (PLS-ANN) was used to quantify the U composition in the salt fuel mixture of Molten salt breeder reactor. This work shows the optimisation of several parameters, viz., spectra pre-treatment procedure, factor number of PLS for ANN input, number of hidden neurons and layers in ANN, activation function, and number of ANN iterations. The collective advantages of data dimension reduction from PLS and the nonlinear processing ability from ANN, improved the accuracy of LIBS quantitative analysis for U from ≈7% using simple PLS to ≈4% precision using a hybrid model.

Quantitative analysis of carbon content in fly ash using LIBS based on support vector regression

Laser-induced breakdown spectroscopy (LIBS) has been proved as an on-line detection technology to measure the carbon content in fly ash, which is beneficial for immediate assessment of the boiler combustion efficiency. Support vector regression (SVR) was adopted as the quantitative model for the carbon content measurement in fly ash in this study. Ash species was one of the key factors affecting quantitative accuracy. Experiments have proven that, the index of plasma temperature and the electron density among different species could be similar, while the partition function ratios and the temperature correction factor showed obvious differences among different ash species. Based on the partition function ratios, the Matrix Effect Correction Factor (MECF) was defined. SVR model was optimized by MECF and the analysis results showed that the correlation coefficient of calibration (R2) increased from 0.989 to 0.991, the root-mean-square error of calibration (RMSEC) decreased from 2.02% to 0.850%, the root-mean-square error of prediction (RMSEP) decreased from 2.13% to 1.07%, and averaged relative standard deviation (ARSD) decreased from 8.62% to 1.89%. The results showed that SVR combined with MECF was an effective method to improve the accuracy of LIBS quantitative analysis of the carbon content in fly ash.

A Review of Membrane-Facilitated Liquid-Solid Conversion: Adding Laser-Induced Breakdown Spectroscopy (LIBS) Multi-Applicability for Metal Analysis

Water splashing and evaporation are challenging aspects in Laser-Induced Breakdown Spectroscopy (LIBS) analysis when it comes to aqueous analyte. By converting the liquid sample into solid, among many other methods, one can improve the analytical performance of LIBS. Membrane is a type of material which can be used to facilitate liquid-solid conversion through various procedures; drop-wising, adsorption, filtration, and phase inversion. In a spotlight, ion exchange membrane allows LIBS technique to analyze the specific heavy metal ion species. This review article reports on advancement of membrane-facilitated liquid-solid conversion to enhance LIBS quantitative analysis of aqueous metals. Such method had been reported to generate low limit of detections (LODs), even up to sub µg/kg. The accuracy and precision produced by the reported methods were not significantly different to that obtained from conventional analytical techniques, such as Inductively Coupled Plasma Optical Emission Spectroscopy (ICP-OES). In conclusion, the use of membrane to convert the analyte can add the application of LIBS for multiple purposes with a satisfying analytical performance.

Quantitative determination of antimony in archaeological bronze artefacts by laser-induced breakdown spectroscopy

Laser-induced breakdown spectroscopy (LIBS) is a reliable, fast and micro-destructive diagnostic method for qualitative and quantitative analysis of a variety of materials. In this paper, we report the results of quantitative determination of antimony in four archaeological bronze artefacts analyzed by means of LIBS. For the purpose of this study, an approach of multi-elemental quantitative LIBS analysis is proposed, based on the use of an element with known concentration as an internal standard and measurement of the spectral lines intensities of the internal standard and the element with unknown concentration. An important plasma parameter which is included in the quantitative analysis is the excitation temperature as determined by the Boltzmann plot method. The quantity of antimony in the bronze artefacts obtained by means of the proposed LIBS approach is between 1.49% and 3.13%.

Quantitative analysis modeling for the ChemCam spectral data based on laser-induced breakdown spectroscopy using convolutional neural network

Laser-induced breakdown spectroscopy (LIBS) has been applied to many fields for the quantitative analysis of diverse materials. Improving the prediction accuracy of LIBS regression models is still of great significance for the Mars exploration in the near future. In this study, we explored the quantitative analysis of LIBS for the one-dimensional ChemCam (an instrument containing a LIBS spectrometer and a Remote Micro-Imager) spectral data whose spectra are produced by the ChemCam team using LIBS under the Mars-like atmospheric conditions. We constructed a convolutional neural network (CNN) regression model with unified parameters for all oxides, which is efficient and concise. CNN that has the excellent capability of feature extraction can effectively overcome the chemical matrix effects that impede the prediction accuracy of regression models. Firstly, we explored the effects of four activation functions on the performance of the CNN model. The results show that the CNN model with the hyperbolic tangent (tanh) function outperforms the CNN models with the other activation functions (the rectified linear unit function, the linear function and the Sigmoid function). Secondly, we compared the performance among the CNN models using different optimization methods. The CNN model with the stochastic gradient descent optimization and the initial learning rate = 0.0005 achieves satisfactory performance compared to the other CNN models. Finally, we compared the performance of the CNN model, the model based on support vector regression (SVR) and the model based on partial least square regression (PLSR). The results exhibit the CNN model is superior to the SVR model and the PLSR model for all oxides. Based on the above analysis, we conclude the CNN regression model can effectively improve the prediction accuracy of LIBS.