The DOI matches its Crossref record; 38 of the 39 references it cites were found in a registry or an index; 8 of the 26 sources its claims cite were checked for support.
Identifying degradation patterns of lithium ion batteries from impedance spectroscopy using machine learning
Open accessAbstract
Forecasting the state of health and remaining useful life of Li-ion batteries is an unsolved challenge that limits technologies such as consumer electronics and electric vehicles. Here, we build an accurate battery forecasting system by combining electrochemical impedance spectroscopy (EIS)-a real-time, non-invasive and information-rich measurement that is hitherto underused in battery diagnosis-with Gaussian process machine learning. Over 20,000 EIS spectra of commercial Li-ion batteries are collected at different states of health, states of charge and temperatures-the largest dataset to our knowledge of its kind. Our Gaussian process model takes the entire spectrum as input, without further feature engineering, and automatically determines which spectral features predict degradation. Our model accurately predicts the remaining useful life, even without complete knowledge of past operating conditions of the battery. Our results demonstrate the value of EIS signals in battery management systems.
Overview
CoChat Summary
TL;DR
A Gaussian process regression model using full electrochemical impedance spectra estimates Li-ion battery capacity and remaining useful life from a single impedance measurement, trained on over 20,000 EIS spectra from commercial LiCoO2/graphite coin cells. Automatic relevance determination shows low-frequency impedance features are most predictive, and the model outperforms discharge-curve features in the reported benchmark.
Key findings
- The EIS-Capacity and EIS-RUL GPR models accurately estimate capacity and predict RUL from the current cycle’s EIS alone; for 25 °C testing cells, the end-of-life values were 150, 120, 30, and 38 cycles, and for multi-temperature testing cells they were 150, 252, and 396 cycles.
- ARD identified low-frequency impedance as most correlated with degradation: at 25 °C the largest weights were on the 91st and 100th features, corresponding to 17.80 and 2.16 Hz; at 35 °C and 45 °C the largest weight was on the 91st feature, 17.80 Hz.
- A multi-temperature model estimated capacity and predicted RUL for cells cycled at 35 °C and 45 °C without the cycling temperature as an input, under the simplification that temperature is constant over cycles.
- Under the same GPR method and train-test split, the EIS-based approach achieved lower predictive error than features extracted from the discharging curve (Supplementary Table 1).
Methods
- Twelve commercially available 45 mAh Eunicell LR2032 Li-ion coin cells with LiCoO2/graphite chemistry were cycled in climate chambers at 25 °C (25C01–25C08), 35 °C (35C01–35C02), and 45 °C (45C01–45C02); each cycle used 1C CC–CV charge to 4.2 V and 2C CC discharge to 3 V.
- EIS was measured every even-numbered cycle at nine charging/discharging stages over 0.02 Hz–20 kHz with 5 mA excitation after 15-min open circuit at SoC 0% and 100%; capacity loss was measured every odd cycle, and EoL was defined as capacity below 80% of initial after 30 room-temperature cycles.
- GPR used the real and imaginary impedance at 60 frequencies as inputs; capacity models used a squared exponential covariance with ARD, RUL models used a linear covariance, and feature importance was defined as \(w_m = \exp(-\sigma_m)\).
Limitations
- The paper states that all testing cells were charged and discharged the same way as training cells, and that estimating cells cycled at different operating charge/discharge rates requires further experiments.
- The paper states that more realistic settings—variations in cycling temperature over time or charge/discharge rate—would require a significantly larger training set, and the multi-temperature model assumes future operating temperature is close to previous operating temperature.
- Evident from the text: the dataset comprises only 12 small coin cells of one chemistry under controlled laboratory temperatures and constant rates, so validation on larger-format cells or real-world variable conditions is not reported.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures




Verification
Claims the paper makes
3 Valid · 4 Not valid · 3 Not checked · 33 Own results and interpretations
Some cited sources support this claim and some don’t — read each source’s verdict below.
In the paper
“However, those models are all developed with the charging and discharging curve as input.”
§ Identifying degradation patterns of lithium ion batteries from impedance spectroscopy using machine learning > Introduction
What the sources say
- Disputedcites [33] Richardson, R. R., Osborne, M. A. & Howey, D. A. Gaussian process regression for forecasting battery state of health. J. Power Sources 357, 209–219 (2017). sourceExperimental — accuracy not yet measured
The Introduction describes data-driven models that map cycle number to state of health and says recent support-vector-machine studies predict capacity from historical capacity-versus-cycle data. It also says capacity data can be obtained by methods other than charge–discharge measurements. These passages contradict the claim that all such models take charging and discharging curves as input; page numbers were not available in our copy. (LLM, conf=0.88)
Checked by a reasoning model — may be wrong.
- Not checked — no full text of the sourcecites [34] Yang, D., Zhang, X., Pan, R., Wang, Y. & Chen, Z. A novel gaussian process regression model for state-of-health estimation of lithium-ion battery using charging curve. J. Power Sources 384, 387–395 (2018). source
- Partly supportedcites [17] Richardson, R. R., Birkl, C. R., Osborne, M. A. & Howey, D. A. Gaussian process regression for in situ capacity estimation of lithium-ion batteries. IEEE Trans. Ind. Inform. 15, 127–136 (2019). sourceExperimental — accuracy not yet measured
The Introduction (p. 1) describes earlier regression models that use features from incremental-capacity or differential-voltage curves as inputs. But it does not establish that all existing machine-learning models use charging and discharging curves; the Conclusions (p. 10) describe this paper’s own model as using small portions of voltage-time data instead. (LLM, conf=0.84)
- Disputedcites [18] Severson, K. A. et al. Data-driven prediction of battery cycle life before capacity degradation. Nat. Energy 4, 383–391 (2019). sourceExperimental — accuracy not yet measured
The Machine learning approach section distinguishes models using discharge data alone from a model that considers both charging and discharging features. The Results section confirms that its “variance” model uses one feature from discharge curves and its “discharge” model uses discharge measurements only. The paper therefore contradicts the claim that all such models require both charging and discharging curves as input. (LLM, conf=0.87)
Checked by a reasoning model — may be wrong.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Disputed
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“suggesting that it is the change in the interfacial properties that underpins degradation for these batteries; this is consistent with the results obtained in previous works35”
§ Identifying degradation patterns of lithium ion batteries from impedance spectroscopy using machine learning > Results > Capacity estimation
What the sources say
- Partly supportedcites [35] Grugeon, S. et al. Particle size effects on the electrochemical performance of copper oxides toward lithium. J. Electrochem. Soc. 148, A285–A292 (2001). sourceExperimental — accuracy not yet measured
The Conclusions (page unavailable) say that an organic coating at the electrode surface can, depending on precursor size, negatively affect capacity retention during cycling. This supports a possible link between interfacial changes and degradation in the copper-oxide cells studied, but not the unqualified claim that such changes underpin degradation for these batteries generally. (LLM, conf=0.85)
hedgedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Features derived from the charging and discharging curve are by far the most commonly used inputs because typical battery management systems collect current–voltage data13–18.”
§ Identifying degradation patterns of lithium ion batteries from impedance spectroscopy using machine learning > Introduction
What the sources say
- Not checked — no full text of the sourcecites [13] Weng, C., Cui, Y., Sun, J. & Peng, H. On-board state of health monitoring of lithium-ion batteries using incremental capacity analysis with support vector regression. J. Power Sources 235, 36–44 (2013). source
- Not checked — no full text of the sourcecites [14] Weng, C., Feng, X., Sun, J. & Peng, H. State-of-health monitoring of lithium-ion battery modules and packs via incremental capacity peak tracking. Appl. Energy 180, 360–368 (2016). source
- Not checked — no full text of the sourcecites [15] Berecibar, M., Garmendia, M., Gandiaga, I., Crego, J. & Villarreal, I. State of health estimation algorithm of lifepo4 battery packs based on differential voltage curves for battery management system application. Energy 103, 784–796 (2016). source
- Not checked — no full text of the sourcecites [16] Berecibar, M. et al. Online state of health estimation on nmc cells based on predictive analytics. J. Power Sources 320, 239–250 (2016). source
- Partly supportedcites [17] Richardson, R. R., Birkl, C. R., Osborne, M. A. & Howey, D. A. Gaussian process regression for in situ capacity estimation of lithium-ion batteries. IEEE Trans. Ind. Inform. 15, 127–136 (2019). sourceExperimental — accuracy not yet measured
The Introduction (p. 1) describes studies using features from IC/DV curves for capacity estimation, supporting the claim that charging-curve-derived features are used. It does not establish that they are by far the most common inputs or that their use is due to typical BMS data collection; instead, it calls model-parameter estimation the most common approach to capacity estimation. (LLM, conf=0.83)
- Partly supportedcites [18] Severson, K. A. et al. Data-driven prediction of battery cycle life before capacity degradation. Nat. Energy 4, 383–391 (2019). sourceExperimental — accuracy not yet measured
The Machine learning approach section says the authors derive predictive features from discharge voltage curves and describes voltage curves and their derivatives as a rich source for degradation diagnosis. The Discussion says differential voltage-curve methods are used extensively. Neither passage establishes that charging and discharging curves are by far the most common inputs for battery health prediction or that their use is because typical battery management systems collect current–voltage data. (LLM, conf=0.84)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“Although GPR has been used in the literature in the context of Li-ion batteries17,33,34, we depart from those pioneering works by employing impedance spectra as input, as well employing ARD to shed light on salient frequencies.”
§ Identifying degradation patterns of lithium ion batteries from impedance spectroscopy using machine learning > Methods > Gaussian process regression
What the sources say
- Supportedcites [17] Richardson, R. R., Birkl, C. R., Osborne, M. A. & Howey, D. A. Gaussian process regression for in situ capacity estimation of lithium-ion batteries. IEEE Trans. Ind. Inform. 15, 127–136 (2019). source
The Introduction (p. 1) identifies this as a Gaussian-process regression method for lithium-ion battery capacity estimation, supporting its citation as prior GPR work. The impedance-spectrum inputs and ARD are described as the citing authors’ departure, not as features attributed to this source; the Conclusions (p. 10) instead describe voltage-time inputs. (LLM, conf=0.93)
- Supportedcites [33] Richardson, R. R., Osborne, M. A. & Howey, D. A. Gaussian process regression for forecasting battery state of health. J. Power Sources 357, 209–219 (2017). source
The Introduction (page unavailable) describes this paper's use of Gaussian processes to forecast lithium-ion battery capacity, supporting its citation as prior GPR work. In the citing sentence, “we depart” describes the citing authors’ own use of impedance spectra and ARD, not a method attributed to this source. (LLM, conf=0.92)
- Not checked — no full text of the sourcecites [34] Yang, D., Zhang, X., Pan, R., Wang, Y. & Chen, Z. A novel gaussian process regression model for state-of-health estimation of lithium-ion battery using charging curve. J. Power Sources 384, 387–395 (2018). source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“in Supplementary Fig. 3, we show there is a strong linear change of selected EIS features with cycle number in the Nyquist plot over cycle number at 25 °C.”
§ Identifying degradation patterns of lithium ion batteries from impedance spectroscopy using machine learning > Results > Capacity estimation
boostedstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
25 more claims
Create a free account to see all 43 claims and every source verdict.
- Probably not a substantial claim. 8
- It may state two separate claims as one. 8
- The quote only partly states this claim. 1
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Identifying degradation patterns of lithium ion batteries from impedance spectroscopy using machine learning > Results > Capacity estimation
“The pink points correspond to the 120 frequencies in the range of 0.02 Hz–20 kHz.”
§ Identifying degradation patterns of lithium ion batteries from impedance spectroscopy using machine learning > Methods > Gaussian process regression
“the real (Zre) and imaginary (Zim) parts of impedance spectra collected at 60 different frequencies (ωn, n = 1, 2, ..., 60) in the range of 0.02 Hz–20 kHz”
Citations
Cites
Lithium Batteries: Status, Prospects and Future
Scrosati, B., & Garche, J. (2010) · Journal of Power Sources · doi:10.1016/j.jpowsour.2009.11.048 · Cited by 5,153 · cited 1×
“L i-ion batteries enable a wide variety of technologies that are integral to modern life by virtue of their high energy and power density 1 – 4 . advancing However, a key stumbling block to those technologies is the unpredictability of battery degradation: accurate prediction of battery state of…”
BackgroundData-driven prediction of battery cycle life before capacity degradation
Severson, K. A., Attia, P. M., Jin, N., Perkins, N., Jiang, B., Yang, Z., Chen, M. H., Aykol, M., Herring, P. K., Fraggedakis, D., et al. (2019) · Nature Energy · doi:10.1038/s41560-019-0356-8 · Cited by 3,228 · cited 3×
“Features derived from the charging and discharging curve are by far the most commonly used inputs because typical battery management systems collect current – voltage data 13 – 18 .”
BackgroundMethodDesigning nanostructured Si anodes for high energy lithium ion batteries
Wu, H., & Cui, Y. (2012) · Nano Today · doi:10.1016/j.nantod.2012.08.004 · Cited by 2,350
Remaining useful life estimation – A review on the statistical data driven approaches
Si, X.-S., Wang, W., Hu, C.-H., & Zhou, D.-H. (2011) · European Journal of Operational Research · doi:10.1016/j.ejor.2010.11.018 · Cited by 2,162 · cited 1×
“To overcome this challenge, recent literature focuses on data-driven approaches 11,12 .”
BackgroundA review on lithium-ion battery ageing mechanisms and estimations for automotive applications
Barré, A., Deguilhem, B., Grolleau, S., Gérard, M., Suard, F., & Riu, D. (2013) · Journal of Power Sources · doi:10.1016/j.jpowsour.2013.05.040 · Cited by 1,758
A Unifying View of Sparse Approximate Gaussian Process Regression
Quiñonero-Candela, J., & Rasmussen, C. E. (2005) · doi:10.5555/1046920.1194909 · Cited by 1,671
Lithium ion secondary batteries; past 10 years and the future
Nishi, Y. (2001) · Journal of Power Sources · doi:10.1016/s0378-7753(01)00887-4 · Cited by 1,074 · cited 1×
“L i-ion batteries enable a wide variety of technologies that are integral to modern life by virtue of their high energy and power density 1 – 4 . advancing However, a key stumbling block to those technologies is the unpredictability of battery degradation: accurate prediction of battery state of…”
BackgroundYang, X.-G., Leng, Y., Zhang, G., Ge, S., & Wang, C.-Y. (2017) · Journal of Power Sources · doi:10.1016/j.jpowsour.2017.05.110 · Cited by 948
Pinson, M. B., & Bazant, M. Z. (2013) · Journal of The Electrochemical Society · doi:10.1149/2.044302jes · Cited by 946
Gaussian Processes for Machine Learning (GPML) Toolbox
Rasmussen, C. E., & Nickisch, H. (2010) · Max Planck Institute for Plasma Physics · doi:10.5555/1756006.1953029 · Cited by 895 · cited 1×
“We implement the EIS-capacity GPR model using the Gaussian processes for machine learning (GPML) toolbox 37 with a zero mean function and a diagonal squared exponential (SE) covariance function with ARD 38 where σ m represents the length scale for feature m , m = 1, 2, ..., d and σ f is the signal…”
Method
Research works printed but not linked: 1
- Popp, H., Einhorn, M. & Conte, F. V. Capacity decrease vs. impedance increase of lithium batteries. a comparative study. In Hybrid and Fuel Cell Electric Vehicle Symposium & Exhibition EVS26, Los Angeles, 6–9 (2012).
Cited by
Application of electrochemical impedance spectroscopy to commercial Li-ion cells: A review
Meddings, N., Heinrich, M., Overney, F., Lee, J.-S., Ruiz, V., Napolitano, E., Seitz, S., Hinds, G., Raccichini, R., Gaberšček, M., et al. (2020) · Journal of Power Sources · doi:10.1016/j.jpowsour.2020.228742 · Cited by 885
Data-driven capacity estimation of commercial lithium-ion batteries from voltage relaxation
Zhu, J., Wang, Y., Huang, Y., Bhushan Gopaluni, R., Cao, Y., Heere, M., Mühlbauer, M. J., Mereacre, L., Dai, H., Liu, X., et al. (2022) · Nature Communications · doi:10.1038/s41467-022-29837-w · Cited by 815
Impedance Analysis of Electrochemical Systems
Vivier, V., & Orazem, M. E. (2022) · Chemical Reviews · doi:10.1021/acs.chemrev.1c00876 · Cited by 615
Vadhva, P., Hu, J., Johnson, M. J., Stocker, R., Braglia, M., Brett, D. J. L., & Rettie, A. J. E. (2021) · ChemElectroChem · doi:10.1002/celc.202100108 · Cited by 531
A review on second-life of Li-ion batteries: prospects, challenges, and issues
Shahjalal, M., Roy, P. K., Shams, T., Fly, A., Chowdhury, J. I., Ahmed, M. R., & Liu, K. (2022) · Energy · doi:10.1016/j.energy.2021.122881 · Cited by 511
“Zhang et al. [56] applied Gaussian process machine learning to 20,000 EIS spectra to estimate capacity, remaining useful life and identify features of interested in improved SOH diagnostics.”
Background
Metadata
- Authors
- Zhang, Y., Tang, Q., Zhang, Y., Wang, J., Stimming, U., & Lee, A. A.
- Affiliations
- University of Cambridge (GB)
- The Faraday Institution (GB)
- Corresponding author
- Stimming, Ulrich
- Lee, Alpha A.
- Venue
- Nature Communications
- Published
- 2020-04-06
- Volume
- 11
- Issue
- 1
- Pages
- 1706-1706
- ISSN
- 2041-1723 (ISSN-L)
- PMC
- PMC7136228
- OpenAlex
- W3010408268
- Cited by
- 889
- References
- 39
- Citations by year
- 2026: 156 · 2025: 198 · 2024: 182 · 2023: 142 · 2022: 118 · 2021: 75 · 2020: 18
- FWCI
- 32.63
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- Locations
- Nature Communications (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Apollo (University of Cambridge) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Apollo (University of Cambridge) (submittedVersion, cc-by)
- Apollo
- Funders
- RCUK | Engineering and Physical Sciences Research Council (EP/S003053/1)
- Topics
- Physical Sciences › Engineering › Automotive Engineering › Battery Modeling and Management
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advancements in Battery Materials
- Physical Sciences › Engineering › Safety, Risk, Reliability and Quality › Reliability and Maintenance Optimization
- Keywords
- lithium-ion batteries, battery degradation, electrochemical impedance spectroscopy, remaining useful life prediction, Gaussian process regression, battery management systems, electric vehicles, battery diagnostics
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Identifying degradation patterns of lithium ion batteries from impedance spectroscopy using machine learning. https://app.cochat.ai/papers/10.1038/s41467-020-15235-7
- The paper
- Zhang, Y., Tang, Q., Zhang, Y., Wang, J., Stimming, U., & Lee, A. A. (2020). Identifying degradation patterns of lithium ion batteries from impedance spectroscopy using machine learning. Nature Communications. https://doi.org/10.1038/s41467-020-15235-7
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.