Quantitative analysis of ToF‐SIMS data of a two organic compound mixture using an autoencoder and simple artificial neural networks

Abstract

Rationale Matrix effects cause a nonlinear relationship between ion intensities and concentrations in mass spectrometry, including time‐of‐flight secondary ion mass spectrometry (ToF‐SIMS). Here, two artificial neural network (ANN)‐based methods, autoencoder‐based and simple ANN methods, were employed for the quantitative and qualitative analyses of a two organic compound mixture via ToF‐SIMS. Methods The multilayer model sample contained a mixture of Irganox 1010 and Fmoc‐pentafluoro‐L‐phenylalanine (Fmoc‐PFLPA). The sample's positive and negative ion depth profiles were collected through ToF‐SIMS. ToF‐SIMS‐derived cross‐sectional image datasets were analyzed using three unsupervised methods, namely principal component analysis (PCA), multivariate curve resolution (MCR), and use of a sparse autoencoder (SAE). The supervised simple ANN method was optimized based on the spectra and validated by predicting the test dataset ratios of Irganox 1010. Results The results obtained using the SAE demonstrated linear calibration curves and appropriate material distribution images. The Irganox 1010 and Fmoc‐PFLPA positive and negative ion datasets exhibited >0.97 correlation coefficients. The PCA and MCR results demonstrated lower linearity than that of SAE. Moreover, SAE weights indicated the ions important for each organic compound. The simple ANN method accurately predicted the ratios in the test dataset and indicated the important ions. Conclusions Both the supervised and unsupervised methods based on ANN, which were employed in regulating nonlinear relationships, were effective in the quantitative and qualitative analyses of the ToF‐SIMS data of the two organic compound mixtures. Regarding qualitative analysis, both ANN‐based methods indicated specific ions from the molecules in the sample.

Identification of Lithium Compounds on Surfaces of Lithium Metal Anode with Machine-Learning-Assisted Analysis of ToF-SIMS Spectra

“…Moreover, depth profiles can be measured to investigate probabilities change as a function of sputter time utilizing the high sensitivity and lateral resolution of ToF-SIMS. This could be helpful in identifying any artifact introduced by sputtering and assist in making more confident interpretations about oxidation, surface segregation, and other related activities such as the matrix effects. , …”

“…This could be helpful in identifying any artifact introduced by sputtering and assist in making more confident interpretations about oxidation, surface segregation, and other related activities such as the matrix effects. 44,45…”

Quantitative and Qualitative Analyses of Mass Spectra of OEL Materials by Artificial Neural Network and Interface Evaluation: Results from a VAMAS Interlaboratory Study

“…Numerical analysis methods using artificial neural networks (ANNs) are useful for interpreting data based on nonlinear combinations, such as SIMS data containing matrix effects. Sparse autoencoders − composed of one middle layer show higher concentration dependence than that observed with conventional multivariate analysis methods, such as principal component analysis and multivariate curve resolution. , A simple ANN system with only one middle layer provides answers as well as processes to reach the answers regarding the relationship between the variables and the weights in ANNs …”

“…20,21 A simple ANN system with only one middle layer provides answers as well as processes to reach the answers regarding the relationship between the variables and the weights in ANNs. 19 In this study, we prepared binary systems of organic e l e c t r o l u m i n e s c e n t ( O E L ) c o m p o u n d s t r i s ( 2phenylpyridinato)iridium(III) (Ir(ppy) 3 ) and tris(8-hydroxyquinolinato)aluminum (Alq 3 ). Monolayers with different mixture ratios were used as standard samples for quantitative analysis.…”