Laser-Induced Breakdown Spectroscopy Quantitative Analysis Using a Bayesian Optimization-Based Tunable Softplus Backpropagation Neural Network
Laser-induced breakdown spectroscopy (LIBS) has played a critical role in Mars exploration missions, substantially contributing to the geochemical analysis of Martian surface substances. However, the complex nonlinearity of LIBS processes can considerably limit the quantification accuracy of convent...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/14/2457 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849252066020556800 |
|---|---|
| author | Xuesen Xu Shijia Luo Xuchen Zhang Weiming Xu Rong Shu Jianyu Wang Xiangfeng Liu Ping Li Changheng Li Luning Li |
| author_facet | Xuesen Xu Shijia Luo Xuchen Zhang Weiming Xu Rong Shu Jianyu Wang Xiangfeng Liu Ping Li Changheng Li Luning Li |
| author_sort | Xuesen Xu |
| collection | DOAJ |
| description | Laser-induced breakdown spectroscopy (LIBS) has played a critical role in Mars exploration missions, substantially contributing to the geochemical analysis of Martian surface substances. However, the complex nonlinearity of LIBS processes can considerably limit the quantification accuracy of conventional LIBS chemometric methods. Hence chemometrics based on artificial neural network (ANN) algorithms have become increasingly popular in LIBS analysis due to their extraordinary ability in nonlinear feature modeling. The hidden layer activation functions are key to ANN model performance, yet common activation functions usually suffer from problems such as gradient vanishing (e.g., Sigmoid and Tanh) and dying neurons (e.g., ReLU). In this study, we propose a novel LIBS quantification method, named the Bayesian optimization-based tunable Softplus backpropagation neural network (BOTS-BPNN). Based on a dataset comprising 1800 LIBS spectra collected by a laboratory duplicate of the MarSCoDe instrument onboard the Zhurong Mars rover, we have revealed that a BPNN model adopting a tunable Softplus activation function can achieve higher prediction accuracy than BPNN models adopting other common activation functions if the tunable Softplus parameter <i>β</i> is properly selected. Moreover, the way to find the proper <i>β</i> value has also been investigated. We demonstrate that the Bayesian optimization method surpasses the traditional grid search method regarding both performance and efficiency. The BOTS-BPNN model also shows superior performance over other common machine learning models like random forest (RF). This work indicates the potential of BOTS-BPNN as an effective chemometric method for analyzing Mars in situ LIBS data and sheds light on the use of chemometrics for data analysis in future planetary explorations. |
| format | Article |
| id | doaj-art-37e4ee74e90d4f38ae184ec8a5096a30 |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-37e4ee74e90d4f38ae184ec8a5096a302025-08-20T03:56:45ZengMDPI AGRemote Sensing2072-42922025-07-011714245710.3390/rs17142457Laser-Induced Breakdown Spectroscopy Quantitative Analysis Using a Bayesian Optimization-Based Tunable Softplus Backpropagation Neural NetworkXuesen Xu0Shijia Luo1Xuchen Zhang2Weiming Xu3Rong Shu4Jianyu Wang5Xiangfeng Liu6Ping Li7Changheng Li8Luning Li9School of Physics and Optoelectronic Engineering, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou 310024, ChinaSchool of Physics and Optoelectronic Engineering, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou 310024, ChinaSchool of Physics and Optoelectronic Engineering, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou 310024, ChinaSchool of Physics and Optoelectronic Engineering, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou 310024, ChinaSchool of Physics and Optoelectronic Engineering, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou 310024, ChinaSchool of Physics and Optoelectronic Engineering, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou 310024, ChinaKey Laboratory of Space Active Opto-Electronics Technology, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, ChinaSchool of Physics and Optoelectronic Engineering, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou 310024, ChinaSchool of Physics and Optoelectronic Engineering, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou 310024, ChinaKey Laboratory of Space Active Opto-Electronics Technology, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, ChinaLaser-induced breakdown spectroscopy (LIBS) has played a critical role in Mars exploration missions, substantially contributing to the geochemical analysis of Martian surface substances. However, the complex nonlinearity of LIBS processes can considerably limit the quantification accuracy of conventional LIBS chemometric methods. Hence chemometrics based on artificial neural network (ANN) algorithms have become increasingly popular in LIBS analysis due to their extraordinary ability in nonlinear feature modeling. The hidden layer activation functions are key to ANN model performance, yet common activation functions usually suffer from problems such as gradient vanishing (e.g., Sigmoid and Tanh) and dying neurons (e.g., ReLU). In this study, we propose a novel LIBS quantification method, named the Bayesian optimization-based tunable Softplus backpropagation neural network (BOTS-BPNN). Based on a dataset comprising 1800 LIBS spectra collected by a laboratory duplicate of the MarSCoDe instrument onboard the Zhurong Mars rover, we have revealed that a BPNN model adopting a tunable Softplus activation function can achieve higher prediction accuracy than BPNN models adopting other common activation functions if the tunable Softplus parameter <i>β</i> is properly selected. Moreover, the way to find the proper <i>β</i> value has also been investigated. We demonstrate that the Bayesian optimization method surpasses the traditional grid search method regarding both performance and efficiency. The BOTS-BPNN model also shows superior performance over other common machine learning models like random forest (RF). This work indicates the potential of BOTS-BPNN as an effective chemometric method for analyzing Mars in situ LIBS data and sheds light on the use of chemometrics for data analysis in future planetary explorations.https://www.mdpi.com/2072-4292/17/14/2457laser-induced breakdown spectroscopybackpropagation neural networktunable Softplus activation functionBayesian optimizationMarSCoDe |
| spellingShingle | Xuesen Xu Shijia Luo Xuchen Zhang Weiming Xu Rong Shu Jianyu Wang Xiangfeng Liu Ping Li Changheng Li Luning Li Laser-Induced Breakdown Spectroscopy Quantitative Analysis Using a Bayesian Optimization-Based Tunable Softplus Backpropagation Neural Network Remote Sensing laser-induced breakdown spectroscopy backpropagation neural network tunable Softplus activation function Bayesian optimization MarSCoDe |
| title | Laser-Induced Breakdown Spectroscopy Quantitative Analysis Using a Bayesian Optimization-Based Tunable Softplus Backpropagation Neural Network |
| title_full | Laser-Induced Breakdown Spectroscopy Quantitative Analysis Using a Bayesian Optimization-Based Tunable Softplus Backpropagation Neural Network |
| title_fullStr | Laser-Induced Breakdown Spectroscopy Quantitative Analysis Using a Bayesian Optimization-Based Tunable Softplus Backpropagation Neural Network |
| title_full_unstemmed | Laser-Induced Breakdown Spectroscopy Quantitative Analysis Using a Bayesian Optimization-Based Tunable Softplus Backpropagation Neural Network |
| title_short | Laser-Induced Breakdown Spectroscopy Quantitative Analysis Using a Bayesian Optimization-Based Tunable Softplus Backpropagation Neural Network |
| title_sort | laser induced breakdown spectroscopy quantitative analysis using a bayesian optimization based tunable softplus backpropagation neural network |
| topic | laser-induced breakdown spectroscopy backpropagation neural network tunable Softplus activation function Bayesian optimization MarSCoDe |
| url | https://www.mdpi.com/2072-4292/17/14/2457 |
| work_keys_str_mv | AT xuesenxu laserinducedbreakdownspectroscopyquantitativeanalysisusingabayesianoptimizationbasedtunablesoftplusbackpropagationneuralnetwork AT shijialuo laserinducedbreakdownspectroscopyquantitativeanalysisusingabayesianoptimizationbasedtunablesoftplusbackpropagationneuralnetwork AT xuchenzhang laserinducedbreakdownspectroscopyquantitativeanalysisusingabayesianoptimizationbasedtunablesoftplusbackpropagationneuralnetwork AT weimingxu laserinducedbreakdownspectroscopyquantitativeanalysisusingabayesianoptimizationbasedtunablesoftplusbackpropagationneuralnetwork AT rongshu laserinducedbreakdownspectroscopyquantitativeanalysisusingabayesianoptimizationbasedtunablesoftplusbackpropagationneuralnetwork AT jianyuwang laserinducedbreakdownspectroscopyquantitativeanalysisusingabayesianoptimizationbasedtunablesoftplusbackpropagationneuralnetwork AT xiangfengliu laserinducedbreakdownspectroscopyquantitativeanalysisusingabayesianoptimizationbasedtunablesoftplusbackpropagationneuralnetwork AT pingli laserinducedbreakdownspectroscopyquantitativeanalysisusingabayesianoptimizationbasedtunablesoftplusbackpropagationneuralnetwork AT changhengli laserinducedbreakdownspectroscopyquantitativeanalysisusingabayesianoptimizationbasedtunablesoftplusbackpropagationneuralnetwork AT luningli laserinducedbreakdownspectroscopyquantitativeanalysisusingabayesianoptimizationbasedtunablesoftplusbackpropagationneuralnetwork |