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

Aug 5, 2026

Detailed knowledge about contamination and passivation compounds on the surface of lithium metal anodes enables their use in all-solid-state batteries. Time-of-flight secondary ion mass spectrometry (ToF-SIMS) provides highly surface-sensitive characterization, but manual interpretation is hindered by complex spectra. Machine learning, especially logistic regression, is applied to identify characteristic secondary ions of five pure lithium compounds, then extended to mixtures and LMA samples for composition identification from measured spectra. The strategy demonstrates strong accuracy on unseen samples and discusses scope and limitations for practical applications.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages10

Reading Time25 min

AccessFree to download

Introduction

Surface contamination and passivation in lithium metal anodes

ToF-SIMS for surface characterization

Limits of manual ToF-SIMS analysis and motivation for ML

This article is licensed under CC-BY-NC-ND 4.0 [www.acsami.org](www.acsami.org) Research Article Identification of Lithium Compounds on Surfaces of Lithium Metal Anode with Machine-Learning-Assisted Analysis of ToF-SIMS Spectra Yinghan Zhao,∥ Svenja-K. Otto, ∥ Teo Lombardo, Anja Henss, Arnd Koeppe, * Michael Selzer, J̈urgen Janek, and Britta Nestler Cite This: ACS Appl. Mater. Interfaces 2023, 15, 50469−50478 Read Online Downloaded via KIT BIBLIOTHEK on November 27, 2023 at 17:00:22 (UTC) . See [https://pubs.acs.org/sharingguidelines](https://pubs.acs.org/sharingguidelines) for options on how to legitimately share published articles. ACCESS Metrics & More Article Recommendations *sı Supporting Information ABSTRACT: Detailed knowledge about contamination and passivation compounds on the surface of lithium metal anodes (LMAs) is essential to enable their use in all-solid-state batteries (ASSBs). Time-of-flight secondary ion mass spectrometry (ToF-SIMS), a highly surface-sensitive technique, can be used to reliably characterize the surface status of LMAs. However, as ToF-SIMS data are usually highly complex, manual data analysis can be difficult and time-consuming. In this study, machine learning techniques, especially logistic regression (LR), are used to identify the characteristic secondary ions of 5 different pure lithium compounds. Furthermore, these models are applied to the mixture and LMA samples to enable identification of their compositions based on the measured ToF-SIMS spectra. This machine-learning-based analysis approach shows good performance in identifying characteristic ions of the analyzed compounds that fit well with their chemical nature. Moreover, satisfying accuracy in identifying the compositions of unseen new samples is achieved. In addition, the scope and limitations of such a strategy in practical applications are discussed. This work presents a robust analytical method that can assist researchers in simplifying the analysis of the studied lithium compound samples, offering the potential for broader applications in other material systems. KEYWORDS: lithium metal anode, all-solid-state battery, ToF-SIMS, machine-learning-assisted analysis, data science 1. INTRODUCTION Lithium metal anodes (LMAs) are of great interest for future battery applications due to their high theoretical specific capacity and low redox potential. Particularly, LMAs have great potential for their use in all-solid-state batteries (ASSBs), because they are currently the sole option that could lead to ASSBs with a higher energy density than commercial lithiumion batteries (LIBs) using liquid electrolytes and graphite anodes.1 However, the application of LMAs still faces severe challenges, such as morphological instability and low Coulomb efficiency.2,3 Different investigations carried out so far on this topic indicate that one critical aspect of LMAs is the degradation process at the surface. Hence, the precise knowledge about contaminations and passivation compounds on its surface is key to unlocking LMA-based ASSBs.4−7 In this context, we have previously reported how X-ray photoelectron spectroscopy (XPS) and time-of-flight secondary ion mass spectrometry (ToF-SIMS) can be used to reliably characterize lithium metal surfaces.8 On the one hand, XPS allows one to obtain both quantitative information on the surface elements and compounds and their qualitative depth distributions (depth profiling). On the other hand, ToF-SIMS depth profiling can complement the XPS results with higher lateral resolution and quantitative depth information, even if | Received: July 4, 2023
Accepted: September 13, 2023
Published: October 18, 2023 | | | --- | --- | © 2023 The Authors. Published by American Chemical Society 50469 [https://doi.org/10.1021/acsami.3c09643](https://doi.org/10.1021/acsami.3c09643)[ ](https://doi.org/10.1021/acsami.3c09643)ACS Appl. Mater. Interfaces 2023, 15, 50469−50478 ToF-SI

FAQs

Why is knowing surface contamination and passivation compounds important for lithium metal anodes?

It is essential for enabling lithium metal anodes in all-solid-state batteries, since degradation at the surface strongly affects performance.

How does the study use machine learning with ToF-SIMS spectra?

Logistic regression models are trained to identify characteristic secondary ions of five pure lithium compounds and then applied to mixture and LMA samples to infer compositions from measured spectra.

What challenges does the paper address in analyzing ToF-SIMS data?

Manual interpretation is difficult and time-consuming due to hundreds of peaks, and important information can be overlooked; the work addresses this by using data science methods.

Aug 5, 2026

Upload by Ava Thompson