Machine learning and transfer learning for correction of the chemical and physical matrix effects in the determination of alkali and alkaline earth metals with LIBS in rocks

Shabbir, Sahar; Xu, Weijie; Zhang, Yuqing; Sun, Chen; Yue, Zengqi; Zou, Long; Chen, Fengye; Yu, Jin

doi:10.1016/j.sab.2022.106478

Cited by 14 publications

(8 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To enable the sharing of prediction models between LIBS instruments, a transfer-learning method based on dynamic time warping (DTW) algorithms was proposed by Rao et al 212 Even though the method based on DTW was superior to a piecewise direct standardisation algorithm for prediction of both lithology and quantitative elemental composition on another instrument, the Pearson coefficient was introduced to improve the performance of the prediction further. Multivariate regression models based 213 on machine and transfer learning were developed to correct for chemical and physical matrix effects. A set of 27 fully characterised rocks were prepared as pressed powder pellets, and LIBS spectra of both the pellets and the parent rocks recorded.…”

Section: Analysis Of Geological Materialsmentioning

confidence: 99%

Atomic spectrometry update – a review of advances in environmental analysis

Bacon,

Butler,

Cairns

et al. 2024

J. Anal. At. Spectrom.

View full text Add to dashboard Cite

show abstract

Section: Analysis Of Geological Materialsmentioning

confidence: 99%

Atomic spectrometry update – a review of advances in environmental analysis

Bacon,

Butler,

Cairns

et al. 2024

J. Anal. At. Spectrom.

View full text Add to dashboard Cite

show abstract

“…The detailed denitions of these metrics are explained in the relevant literature. 18,35 The coefficient of determination is a measure of how well the model ts the training data, the mean absolute error represents the average absolute difference between the predicted and true values, and the root mean squared error is used to observe the degree of dispersion between the predicted and true values.…”

Section: Data Processingmentioning

confidence: 99%

Rapid quantitative analysis of raw rocks by LIBS coupled with feature-based transfer learning

Rao,

Ren,

Kong

et al. 2024

J. Anal. At. Spectrom.

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

“…Therefore, the ML models with knowledge transfer have been investigated and established as effective tools for qualitative and quantitative analysis of LIBS measurement. Transfer learning-based ML models have achieved promising results in spectral correction 38 and efficiently dealing with the gap in the distribution of training and test sets. 39 To fulfill the requirement of an extensive training dataset, it is essential to use an augmented training set consisting of LIBS measurements of samples of known composition.…”

Section: Introductionmentioning

confidence: 99%

Adversarial Data Augmentation and Transfer Net for Scrap Metal Identification Using Laser-Induced Breakdown Spectroscopy Measurement of Standard Reference Materials

et al. 2023

View full text Add to dashboard Cite

In this study, we propose a transfer learning-based classification model for identifying scrap metal using an augmented training dataset consisting of laser-induced breakdown spectroscopy (LIBS) measurement of standard reference material (SRMs) samples, considering varying experimental setups and environmental conditions. LIBS provides unique spectra for identifying unknown samples without complicated sample preparation. Thus, LIBS systems combined with machine learning methods have been actively studied for industrial applications such as scrap metal recycling. However, in machine learning models, a training set of the used samples may not cover the diversity of the scrap metal encountered in field measurements. Moreover, differences in experimental configuration, where laboratory standards and real samples are analyzed in situ, may lead to a wider gap in the distribution of training and test sets, dramatically reducing the performance of the LIBS-based fast classification system for real samples. To address these challenges, we propose a two-step Aug2Tran model. First, we augment the SRM dataset by synthesizing spectra of unobserved types through attenuation of dominant peaks corresponding to sample composition and generating spectra depending on the target sample using a generative adversarial network. Second, we used the augmented SRM dataset to build a robust real-time classification model with a convolutional neural network, which is further customized for the target scrap metal with limited measurements through transfer learning. For evaluation, SRMs of five representative metal types, including aluminum, copper, iron, stainless steel, and brass, are measured with a typical setup to form the SRM dataset. For testing, scrap metal from actual industrial fields is experimented with three different configurations, resulting in eight different test datasets. The experimental results show that the proposed scheme produces an average classification accuracy of 98.25% for the three experimental conditions, as high as the results of the conventional scheme with three separately trained and executed models. Additionally, the proposed model improves the classification accuracy of arbitrarily shaped static or moving samples with various surface contaminations and compositions, and even for differing ranges of charted intensities and wavelengths. Therefore, the proposed Aug2Tran model can be used as a systematic model for scrap metal classification with generalizability and ease of implementation.

show abstract

Machine learning and transfer learning for correction of the chemical and physical matrix effects in the determination of alkali and alkaline earth metals with LIBS in rocks

Cited by 14 publications

References 35 publications

Atomic spectrometry update – a review of advances in environmental analysis

Atomic spectrometry update – a review of advances in environmental analysis

Rapid quantitative analysis of raw rocks by LIBS coupled with feature-based transfer learning

Adversarial Data Augmentation and Transfer Net for Scrap Metal Identification Using Laser-Induced Breakdown Spectroscopy Measurement of Standard Reference Materials

Contact Info

Product

Resources

About