journal article·2026-05

Enhancing lithium-ion battery analysis: A machine learning approach to investigate innovative silicon thin film anode parameters and discharge capacity

Elif Muslu Yilmaz, Aysegul Uygun Oksuz, Satoshi Hamaguchi, Elif Ceren Gok Yildirim, Murat Onur Yildirim, Kazumasa Ikuse, Pierre Vinchon, Nicolas Mauchamp, Esin Eren

Publisher page

Abstract

Silicon (Si) thin film anodes offer very high theoretical capacity but also undergo severe volume expansion during lithiation, which causes fracture, loss of electrical contact, and rapid capacity fade in lithium-ion batteries. This study develops a machine learning (ML) framework that predicts discharge capacity and derives processing and operating guidelines for Si thin film anodes. A curated literature dataset with missing fabrication and cycling parameters is completed using ML-based imputation, for which Random Forest gives the highest accuracy. A Random Forest regressor then predicts discharge capacity with strong performance (validation R2 = 0.86, mean absolute error = 174.1 mAh g−1). Feature importance analysis identifies working pressure, cycle number, and C-rate as the most influential variables. The trained model also extrapolates learned degradation trends to later cycle numbers, producing hypothetical capacity fade projections that qualitatively align with the reported behaviour of Si thin film anodes, rather than representing statistically validated long-term predictions. Finally, a model-agnostic Accumulated Local Effects analysis quantifies how fabrication parameters and operating conditions shape both absolute capacity and its fading. The results show that ML not only predicts performance reliably but also supports the rational design of next-generation Si thin film anodes.
Source: openaire · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Advancements in Battery Materials · Advanced Battery Technologies Research · Advanced Battery Materials and Technologies

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (91)

Show source-provided references
1. Brief history of early lithium-battery development10.3390/ma13081884 ↗
2. Carbon anode materials for rechargeable alkali metal ion batteries and in-situ characterization techniques10.3389/fchem.2020.607504 ↗
3. Development of lithium-ion batteries from micro-structured to nanostructured materials: its issues and challenges10.3184/003685012X13421145651372 ↗
4. A deep learning approach for solving diffusion-induced stress in large-deformed thin film electrodes10.1016/j.est.2023.107037 ↗
5. Silicon-based anodes for lithium-ion batteries: from fundamentals to practical applications10.1002/smll.201702737 ↗
6. Kinetic analysis of silicon-lithium alloying reaction in silicon single crystal using soft X-ray absorption spectroscopy10.1039/D3RA02554C ↗
7. Investigations of Si Thin Films as Anode of Lithium-Ion Batteries
8. Long-term cyclability of substoichiometric silicon nitride thin film anodes for li-ion batteries10.1038/s41598-017-13699-0 ↗
9. The influence of different Si:C ratios on the electrochemical performance of silicon/carbon layered film anodes for lithium-ion batteries
10. Nanoporous helium–silicon Co-Deposition thin film via plasma-assisted process for lithium-ion-battery anodes10.1002/aesr.202400300 ↗
11. Advances in physical vapor deposited silicon/carbon based anode materials for Li-ion batteries10.1016/j.heliyon.2024.e30431 ↗
12. Si-based anode materials for li-ion batteries: a mini review10.1007/s40820-014-0008-2 ↗
13. C-Rate capability of ion-beam sputter deposited silicon, carbon and silicon/carbon multilayer thin films for Li-Ion batteries10.1149/1945-7111/ac8a79 ↗
14. Growth of the cycle life and rate capability of LIB silicon anodes based on macroporous membranes10.3390/membranes12111037 ↗
15. Toward quantifying capacity losses due to solid electrolyte interphase evolution in silicon thin film batteries10.1063/1.5142643 ↗
16. Communication—effect of lower cutoff voltage on the 1 st cycle performance of silicon electrodes10.1149/2.0111902jes ↗
17. Silicon thin films as anodes for high-performance lithium-ion batteries with effective stress relaxation10.1002/aenm.201100634 ↗
18. Investigating the Mg-Si binary system via combinatorial sputter deposition as high energy density anodes for lithium-ion batteries10.1021/acsami.5b05382 ↗
19. Porous amorphous silicon film anodes for high-capacity and stable all-solid-state lithium batteries10.1038/s42004-018-0026-y ↗
20. Silicon-tin thin-film anodes for low and high power-density lithium-ion batteries10.1016/j.tsf.2024.140332 ↗
21. Insight into the decay mechanism of non-ultra-thin silicon film anode for lithium-ion batteries10.1016/j.electacta.2023.142112 ↗
22. Thickness gradient promotes the performance of Si-based anode material for lithium-ion battery10.1016/j.matdes.2020.108993 ↗
23. Modeling the delamination of amorphous-silicon thin film anode for lithium-ion battery10.1016/j.jpowsour.2013.06.089 ↗
24. Multi-scale analysis of an electrochemical model including coupled diffusion, stress, and nonideal solution in a silicon thin film anode10.1016/j.jpowsour.2016.01.037 ↗
25. Quantitative analysis of energy dissipation in thin film Si anodes upon lithiation10.1016/j.jpowsour.2025.236231 ↗
26. A composite electrode model for lithium-ion batteries with silicon/graphite negative electrodes10.1016/j.jpowsour.2022.231142 ↗
27. Comprehensive study of lithium diffusion in Si/C-Layer and Si/C3N4 composites in a faceted crystalline silicon anode for fast-charging lithium-ion batteries10.1021/acsomega.3c05523 ↗
28. Integrating physics-based modeling and machine learning for degradation diagnostics of lithium-ion batteries
29. An analytical model for predicting the remaining battery capacity of lithium-ion batteries
30. Multiphysics-informed machine learning for mechanical-induced degradation of silicon anode
31. Transferable and robust machine learning model for predicting stability of Si anodes for multivalent cation batteries10.1007/s10853-023-08705-y ↗
32. Lithium-ion battery degradation modelling using universal differential equations: development of a cost-effective parameterisation methodology10.1016/j.apenergy.2024.125221 ↗
33. Machine learning-accelerated discovery and design of electrode materials and electrolytes for lithium ion batteries
34. Machine learning in lithium-ion battery: applications, challenges, and future trends10.1007/s42979-024-03046-2 ↗
35. Machine-learning approach for predicting the discharging capacities of doped lithium nickel-cobalt-manganese cathode materials in Li-Ion batteries10.1021/acscentsci.1c00611 ↗
36. Robust State of Health estimation of lithium-ion batteries using convolutional neural network and random forest10.1016/j.est.2021.103857 ↗
37. Forecasting battery capacity and power degradation with multi-task learning
38. A data-driven interpretable method to predict capacities of metal ion doped TiO2 anode materials for lithium-ion batteries using machine learning classifiers10.1039/D3QI01705B ↗
39. Machine learning-assisted accelerated research of energy storage properties of BaTiO3-BiMeO3 ceramics
40. Lithium–Ion battery data: from production to prediction10.3390/batteries9070385 ↗
41. An analysis of the current state and obstacles in discrete layered finite element simulation of crushing cylindrical lithium-ion cells10.1016/j.est.2023.108029 ↗
42. Sputtered LiCoO2 cathode materials for all-solid-state thin-film lithium microbatteries10.3390/ma12172687 ↗
43. The effect of sputter cathode design on deposition parameters: design enhancements expand capabilities for the magnetron sputtering of thin films10.1002/vipr.201900718 ↗
44. High capacity, reversible silicon thin-film anodes for lithium-ion batteries10.1149/1.1596918 ↗
45. Electrochemical properties of negative SiMox electrodes deposited on a roughened substrate for rechargeable lithium batteries10.1016/j.jpowsour.2009.05.047 ↗
46. Magnetron sputtering silicon thin film electrodes for lithium-ion batteries10.20964/2018.03.05 ↗
47. Effect of succinic anhydride as an electrolyte additive on electrochemical characteristics of silicon thin-film electrode10.1016/j.jpowsour.2009.11.142 ↗
48. Effect of vinylene carbonate electrolyte additive and battery cycling protocol on the electrochemical and cyclability performance of silicon thin-film anodes10.1016/j.est.2021.103868 ↗
49. Physical vapor deposition cluster arrival energy enhances the electrochemical performance of silicon thin-film anodes for Li-Ion batteries10.1021/acsaem.1c02035 ↗
50. Silicon nanofibrils on a flexible current collector for bendable lithium-ion battery anodes10.1002/adfm.201202458 ↗
51. Sputtered Ge/Si nanocomposite films as high performance anode materials for lithium-ion battery10.1007/s10904-019-01201-4 ↗
52. Surface-modified Si thin film electrode for Li ion batteries (LiFePO4/Si) by cluster-structured Ni under layer10.1016/j.jpowsour.2008.08.018 ↗
53. Scalable interlayer nanostructure design for high-rate (10C) submicron silicon-film electrode by incorporating silver nanoparticles
54. Silicon/graphene-sheet hybrid film as anode for lithium ion batteries10.1016/j.elecom.2012.07.001 ↗
55. Cobalt nanomountain array supported silicon film anode for high-performance lithium ion batteries10.1016/j.electacta.2012.10.119 ↗
56. Periodic porous silicon thin films with interconnected channels as durable anode materials for lithium ion batteries10.1016/j.matchemphys.2013.12.003 ↗
57. Machine learning assisted synthesis of lithium-ion batteries cathode materials10.1016/j.nanoen.2022.107214 ↗
58. 2008
59. Silicon-oxycarbide based thin film anodes for lithium ion batteries10.1016/j.jpowsour.2011.02.091 ↗
60. Investigating the impact of missing data imputation techniques on battery energy management system10.1049/stg2.12011 ↗
61. State of health estimation for lithium-ion batteries using Gaussian process regression-based data reconstruction method during random charging process10.1016/j.est.2023.108390 ↗
62. Machine learning motivated data imputation of storm data used in coastal hazard assessments10.1016/j.coastaleng.2024.104505 ↗
63. Hybrid machine learning approaches for landslide susceptibility modeling10.3390/f10020157 ↗
64. Discharge capacity estimation for Li-Ion batteries: a comparative study
65. Python-based scikit-learn machine learning models for thermal and electrical performance prediction of high-capacity lithium-ion battery10.1002/er.7202 ↗
66. Predicting perovskite bandgap and solar cell performance with machine learning10.1002/solr.202100927 ↗
67. Effect of feature scaling pre-processing techniques on machine learning algorithms to predict particulate matter concentration for Gandhinagar, Gujarat, India
68. An analysis of four missing data treatment methods for supervised learning10.1080/713827181 ↗
69. How much missing data is too much to impute for longitudinal health indicators? A preliminary guideline for the choice of the extent of missing proportion to impute with multiple imputation by chained equations10.1186/s12963-025-00364-2 ↗
70. Local gaussian process extrapolation for BART models with applications to causal inference10.1080/10618600.2023.2240384 ↗
71. Data extrapolation from learned prior images for truncation correction in computed tomography10.1109/TMI.2021.3072568 ↗
72. Reproduction of environment reflection using extrapolation of front camera images in Mobile AR
73. The effect of oxygen incorporation in sputtered scandium nitride films10.1016/j.tsf.2008.05.050 ↗
74. Dependence of the properties of sputter deposited Al-doped ZnO thin films on base pressure10.1016/j.jallcom.2012.01.078 ↗
75. Revised structure zone model for thin film physical structure10.1116/1.572604 ↗
76. Spectroscopic ellipsometry study of non-hydrogenated fully amorphous silicon films deposited by room-temperature radio-frequency magnetron sputtering on glass: influence of the argon pressure10.1016/j.jnoncrysol.2020.120305 ↗
77. Properties of Amorphous Si prepared by RF sputtering with a high Ar pressure10.1143/JJAP.19.L235 ↗
78. Low-density silicon thin films for lithium-ion battery anodes10.1016/j.tsf.2016.01.029 ↗
79. Fast charging and high-efficiency sputter-deposited silicon thin film anodes for Li-ion batteries10.1016/j.jpowsour.2025.236967 ↗
80. Effect on silicon nitride thin films properties at various powers of RF magnetron sputtering10.14419/ijet.v7i4.30.22000 ↗
81. Effect of sputtering power on the nucleation and growth of Cu films deposited by magnetron sputtering10.2320/matertrans.M2009183 ↗
82. Effect of sputtering power on the properties of SiO2 films grown by radio frequency magnetron sputtering at room temperature10.1007/s11082-020-02639-4 ↗
83. Role of hydrogen in controlling the growth of μc-Si:H films from argon diluted SiH 4 plasma10.1063/1.1454201 ↗
84. Magnetron sputtering technique for analyzing the influence of RF sputtering power on microstructural surface morphology of aluminum thin films deposited on SiO2/Si substrates10.1007/s00339-021-04892-0 ↗
85. In situ measurements of stress evolution in silicon thin films during electrochemical lithiation and delithiation10.1016/j.jpowsour.2010.02.013 ↗
86. Designing nanostructured Si anodes for high energy lithium ion batteries10.1016/j.nantod.2012.08.004 ↗
87. Quantifying lithium loss in amorphous silicon thin-film anodes via titration-gas chromatography
88. Insights into electrolytic pre-lithiation: a thorough analysis using silicon thin film anodes10.1002/smll.202206092 ↗
89. The effect of silicon grade and electrode architecture on the performance of advanced anodes for next generation lithium-ion cells10.3390/nano11123448 ↗
90. Anomalous capacity increase at high-rates in lithium-ion battery anodes based on silicon-coated vertically aligned carbon nanofibers10.1016/j.jpowsour.2014.11.094 ↗
91. Increased cycling efficiency and rate capability of copper-coated silicon anodes in lithium-ion batteries10.1016/j.jpowsour.2010.06.043 ↗