Quantitative assessment of machine-learning segmentation of battery electrode materials for active material quantification
Source abstract
Abstract
X-ray computed tomography (CT) is an important tool for studying battery electrode microstructures but relies on robust segmentation for validity. Here, several approaches to applying accessible machine-learning segmentation software to segment open-source lithium-ion battery (LIB) electrode tomograms are followed to identify the optimised methodology that minimises variation in active material volume fraction quantification across three users. Iterative, manual training across seven cross-sectional slices (<5%) of a tomogram is identified as an optimal balance between variance and user interaction, where 10–25% of each slice was trained. This approach is applied to lab-based X-ray CT data and compared with data obtained by focused-ion beam/scanning electron microscopy slice-and-view tomography. Variation in active material volume fraction between users is lower for at least one of these two approaches (10% or 25%) when applied to raw LIB cathode tomograms, versus unsupervised techniques such as simple and watershed segmentations. On average, the absolute volume fraction values are closer to that acquired by the correlated technique, most closely matching for high-resolution data. The present analysis provides an optimised approach for using open-source software to apply machine-learning segmentation when quantifying active material volume fractions in cutting-edge LIB electrodes, providing a more robust route to active material quantification.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Electrical and Bioimpedance Tomography · Non-Destructive Testing Techniques · Geophysical and Geoelectrical Methods
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (93)
Show source-provided references
1. The lithium-ion battery: state of the art and future perspectives10.1016/j.rser.2018.03.002 ↗
2. The coming electric vehicle transformation10.1126/science.aax0704 ↗
3. Toward low-cost, high-energy density, and high-power density lithium-ion batteries10.1007/s11837-017-2404-9 ↗
4. New insight into the solid electrolyte interphase with use of a focused ion beam10.1021/jp053311a ↗
5. New insight into the interaction between propylene carbonate-based electrolytes and graphite anode material for lithium ion batteries10.1021/jp066762j ↗
6. Transport properties of LiMn2O4 electrode materials for lithium-ion batteries10.1016/S0167-2738(98)00096-4 ↗
7. Modeling 3D microstructure and ion transport in porous Li-ion battery electrodes10.1149/1.3579996 ↗
8. Comparison of three-dimensional analysis and stereological techniques for quantifying lithium-ion battery electrode microstructures10.1111/jmi.12389 ↗
9. Frank · 2013
10. TEM and electron tomography studies of carbon nanospheres for lithium secondary batteries10.1016/j.carbon.2006.05.041 ↗
11. Yao · 2007
12. Quantitative X-ray tomography10.1179/1743280413Y.0000000023 ↗
13. Measurement of three-dimensional microstructure in a LiCoO2 positive electrode10.1016/j.jpowsour.2010.04.066 ↗
14. Three-dimensional reconstruction of a LiCoO2 Li-ion battery cathode10.1149/2.002203esl ↗
15. Three-dimensional reconstruction of a composite cathode for lithium-ion cells10.1016/j.elecom.2010.12.004 ↗
16. Three-dimensional investigation of cycling-induced microstructural changes in lithium-ion battery cathodes using focused ion beam/scanning electron microscopy10.1016/j.jpowsour.2015.11.108 ↗
17. Effects of three-dimensional cathode microstructure on the performance of lithium-ion battery cathodes10.1016/j.electacta.2012.10.104 ↗
18. Three-phase multiscale modeling of a LiCoO2 cathode: combining the advantages of FIB-SEM imaging and X-ray tomography10.1002/aenm.201401612 ↗
19. Enhanced imaging of lithium ion battery electrode materials10.1149/2.0061701jes ↗
20. X-ray tomography for lithium ion battery research: a practical guide10.1146/annurev-matsci-070616-123957 ↗
21. Characterization of the 3-dimensional microstructure of a graphite negative electrode from a Li-ion battery10.1016/j.elecom.2009.12.038 ↗
22. Preparation and characterization of li-ion graphite anodes using synchrotron tomography10.3390/ma7064455 ↗
23. Anode microstructures from high-energy and high-power lithium-ion cylindrical cells obtained by X-ray nano-tomography10.1016/j.jpowsour.2014.07.070 ↗
24. Multi length scale microstructural investigations of a commercially available Li-ion battery electrode10.1149/2.053207jes ↗
25. Image based modelling of microstructural heterogeneity in LiFePO4 electrodes for Li-ion batteries10.1016/j.jpowsour.2013.04.156 ↗
26. X-ray tomography of porous, transition metal oxide based lithium ion battery electrodes10.1002/aenm.201200932 ↗
27. J. 3D analysis of a LiCoO2-Li(Ni1/3Mn 1/3Co1/3)O2 Li-ion battery positive electrode using X-ray nano-tomography10.1016/j.elecom.2012.12.021 ↗
28. J. 3D morphological evolution of Li-ion battery negative electrode LiVO2 during oxidation using X-ray nano-tomography10.1016/j.elecom.2012.04.033 ↗
29. Three-dimensional high resolution X-ray imaging and quantification of lithium ion battery mesocarbon microbead anodes10.1016/j.jpowsour.2013.08.147 ↗
30. Tortuosity anisotropy in lithium-ion battery electrodes10.1002/aenm.201301278 ↗
31. Tortuosity characterization of 3D microstructure at nano-scale for energy storage and conversion materials10.1016/j.jpowsour.2013.10.026 ↗
32. Three-dimensional imaging of chemical phase transformations at the nanoscale with full-field transmission X-ray microscopy10.1107/S0909049511019364 ↗
33. Laser-preparation of geometrically optimised samples for X-ray nano-CT10.1111/jmi.12577 ↗
34. Investigating lithium-ion battery materials during overcharge-induced thermal runaway: an operando and multi-scale X-ray CT study10.1039/C6CP04251A ↗
35. Multiscale morphological characterization of process induced heterogeneities in blended positive electrodes for lithium–ion batteries10.1007/s10853-016-0374-x ↗
36. A multiscale X-ray tomography study of the cycled-induced degradation in magnesium–sulfur batteries
37. 3D microstructure design of lithium-ion battery electrodes assisted by X-ray nano-computed tomography and modelling
38. Three-dimensional morphological measurements of LiCoO2 and LiCoO2/Li(Ni1/3Mn1/3Co1/3)O2 lithium-ion battery cathodes10.1016/j.jpowsour.2012.11.043 ↗
39. Multi-scale correlative tomography of a Li-ion battery composite cathode10.1038/srep30109 ↗
40. Multimodal nanoscale tomographic imaging for battery electrodes
41. Heterogeneous damage in Li-ion batteries: experimental analysis and theoretical modeling10.1016/j.jmps.2019.05.003 ↗
42. 4D imaging of lithium-batteries using correlative neutron and X-ray tomography with a virtual unrolling technique10.1038/s41467-019-13943-3 ↗
43. Four-dimensional studies of morphology evolution in lithium-sulfur batteries10.1021/acsaem.8b01148 ↗
44. Taiwo · 2015 · vol. 69 · 81
45. Quantifying microstructural dynamics and electrochemical activity of graphite and silicon-graphite lithium ion battery anodes10.1038/ncomms12909 ↗
46. Tool for tortuosity estimation in lithium ion battery porous electrodes10.1149/2.0111502jes ↗
47. Determining the representative volume element size for three-dimensional microstructural material characterization. Part 2: application to experimental data10.1016/j.jpowsour.2015.02.052 ↗
48. Resolving Li-ion battery electrode particles using rapid lab-based X-ray nano-computed tomography for high-throughput quantification
49. Multiscale simulation process and application to additives in porous composite battery electrodes10.1016/j.jpowsour.2014.11.090 ↗
50. Thick electrodes for Li-ion batteries: a model based analysis10.1016/j.jpowsour.2016.09.143 ↗
51. Electrode mesoscale as a collection of particles: coupled electrochemical and mechanical analysis of NMC cathodes10.1149/1945-7111/ab632b ↗
52. Exploring cycling induced crystallographic change in NMC with X-ray diffraction computed tomography10.1039/D0CP01851A ↗
53. Quantifying reaction and rate heterogeneity in battery electrodes in 3D through operando X-ray diffraction computed tomography10.1021/acsami.9b02173 ↗
54. Operando Bragg coherent diffraction imaging of LiNi0.8Mn0.1Co0.1O2 Primary particles within commercially printed NMC811 electrode sheets10.1021/acsnano.0c08575 ↗
55. Use of watersheds in contour detection
56. Morphological segmentation10.1016/1047-3203(90)90014-M ↗
57. Shading correction algorithm for improvement of cone-beam CT images in radiotherapy10.1088/0031-9155/53/20/010 ↗
58. Hastie · 2009
59. A deep convolutional encoder-decoder architecture for image segmentation10.1109/TPAMI.2016.2644615 ↗
60. O'Shea · 2015 · vols. 1–11
61. Random forests10.1023/A:1010933404324 ↗
62. A survey on deep learning in medical image analysis10.1016/j.media.2017.07.005 ↗
63. Measurement of brain structures with artificial neural networks: two- and three-dimensional applications10.1148/radiology.211.3.r99ma07781 ↗
64. Registration and machine learning-based automated segmentation of subcortical and cerebellar brain structures10.1016/j.neuroimage.2007.05.063 ↗
65. Machine learning applications in cell image analysis10.1038/icb.2017.16 ↗
66. Use of machine learning based technique to X-ray microtomographic images of concrete for phase segmentation at meso-scale10.1016/j.conbuildmat.2020.118744 ↗
67. Semantic segmentation of the micro-structure of strain-hardening cement-based composites (SHCC) by applying deep learning on micro-computed tomography scans10.1016/j.cemconcomp.2020.103551 ↗
68. Phase segmentation of X-ray computer tomography rock images using machine learning techniques: an accuracy and performance study10.5194/se-7-1125-2016 ↗
69. Machine learning for predicting properties of porous media from 2D X-ray images10.1016/j.petrol.2019.106514 ↗
70. Application of machine learning techniques in mineral phase segmentation for X-ray microcomputed tomography (μCT) data10.1016/j.mineng.2019.105882 ↗
71. Materials discovery and design using machine learning
72. Optimizing convolutional neural networks to perform semantic segmentation on large materials imaging datasets: X-ray tomography and serial sectioning10.1016/j.matchar.2020.110119 ↗
73. Comparison of segmentation algorithms for FIB-SEM tomography of porous polymers: importance of image contrast for machine learning segmentation10.1016/j.matchar.2020.110806 ↗
74. Machine learning techniques for the segmentation of tomographic image data of functional materials10.3389/fmats.2019.00145 ↗
75. Machine learning assisted materials design and discovery for rechargeable batteries10.1016/j.ensm.2020.06.033 ↗
76. Data mining of molecular dynamics data reveals Li diffusion characteristics in garnet Li7La3Zr2O12
77. Quantitative structure-property relationship study of cathode volume changes in lithium ion batteries using ab-initio and partial least squares analysis
78. Crack detection in lithium-ion cells using machine learning10.1016/j.commatsci.2017.05.012 ↗
79. Computer-vision-based approach to classify and quantify flaws in Li-ion electrodes
80. Machine-learning-revealed statistics of the particle-carbon/binder detachment in lithium-ion battery cathodes
81. Three-dimensional structural measurement and material identification of an all-solid-state lithium-ion battery by X-Ray nanotomography and deep learning10.1016/j.powera.2021.100048 ↗
82. Mapping the architecture of single lithium ion electrode particles in 3D, using electron backscatter diffraction and machine learning segmentation10.1016/j.jpowsour.2020.229148 ↗
83. Synchrotron imaging of pore formation in Li metal solid-state batteries aided by machine learning10.1021/acsaem.0c02053 ↗
84. Deep learning-based segmentation of lithium-ion battery microstructures enhanced by artificially generated electrodes10.1038/s41467-021-26480-9 ↗
85. Resolving the discrepancy in tortuosity factor estimation for li-ion battery electrodes through micro-macro modeling and experiment10.1149/2.0731814jes ↗
86. Quantitative microstructure characterization of a NMC electrode10.1149/07711.1095ecst ↗
87. Laboratory · 2017
88. Applications of advanced metrology for understanding the effects of drying temperature in the lithium-ion battery electrode manufacturing process10.1039/D2TA00861K ↗
89. Effective ultrasound acoustic measurement to monitor the lithium-ion battery electrode drying process with various coating thicknesses10.1021/acsami.1c22150 ↗
90. In situ ultrasound acoustic measurement of the lithium-ion battery electrode drying process10.1021/acsami.1c10472 ↗
91. A tlreshold selection method from gray-level histograms
92. An automated simple algorithm for realistic pore network extraction from micro-tomography images10.1016/j.petrol.2014.08.020 ↗
93. Ilastik: interactive learning and segmentation toolkit