Machine Learning with Explainable Artificial Intelligence Vision for Characterization of Solution Conductivity Using Optical Emission Spectroscopy of Plasma in Aqueous Solution

Abstract

This study presents an explainable artificial intelligence (XAI) vision for optical emission spectroscopy (OES) of plasma in aqueous solution. We aim to characterize the plasma and OES with XAI. Trained with 18000 spectra, a multilayer artificial neural network (ANN) model accurately predicted the solution conductivity. Local interpretable model-agnostics explanations (LIME), an XAI method, interpreted the model through perturbing spectral features and fitting the feature contribution with a linear model. LIME showed that OH, H γ , and H β emission lines were critical to the model, differing from the lines typically selected by humans. The results demonstrated that machine captured the spectral features neglected by humans. We believe using XAI for plasma OES analysis impacts the fields of plasma and analytical chemistry.

Review: Machine learning for advancing low-temperature plasma modeling and simulation

“…As an example, local interpretable model-agnostic explanations (LIME) have been suggested for identifying interpretable models that locally approximate the nonlinear behavior of any underlying model 181 . While this is possibly an underexplored aspect in the context of LTP, an example where LIME relates to the data-driven classification and interpretation of OES experiments of plasma in aqueous solution has been proposed 182 . Further works by Lundberg et al 183 .…”

“…181 While this is possibly an underexplored aspect in the context of LTP, an example where LIME relates to the datadriven classification and interpretation of OES experiments of plasma in aqueous solution has been proposed. 182 Further works by Lundberg et al 183 have included LIME and other methods in an extension Shapley additive explanations. It is similarly based on local explanation models but defines additive feature attribution methods to unify several of the included interpretable methods.…”

Explainable AI for unveiling deep learning pollen classification model based on fusion of scattered light patterns and fluorescence spectroscopy

“…Although pollen classification models are yet to be unveiled by xAI, applications build upon principles of chemistry, physics or spectroscopy can demonstrate potential benefits of this methodology in the broader context. For example xAI for optical emission spectroscopy 41 in plasma-based processes unveil why model made certain predictions thus allowing to characterize the plasma and the spectra. Study of Gomez-Fernandez et al 42 examined whether domain-specific characteristics are being identified by deep learning models on gamma spectroscopy tasks.…”

Explainable Predictive Modeling for Limited Spectral Data

“…Explainable AI techniques in general have been widely used to explain predictions in financial and chemical time-series data [77,78,79,80] vibrational-based Structural Health Monitoring signals [50], hyperspectral imaging [81] and electrocardiogram data [82]. However, to the best of our knowledge, only one recent work focused on using the model-agnostic method (LIME) to explain the non-linear predictions of spectroscopy data to characterize plasma solution conductivity [29].…”

“…Most publications in the field either solely focus on obtaining prediction, for example, applying popular ML methods for octane prediction using infrared spectroscopy [25], or the use of common feature elimination techniques [26] to improve the prediction accuracy. The implementation of explainable black-box models is limited to interpreting functional nearinfrared spectra data in developmental cognitive neuroscience using simple multi-variate analysis [27] and using Local Interpretable Model-Agnostic Explanations (LIME) [28] on optical emission spectroscopy of plasma [29].…”