Research / 2025 American Chemical Society Western Regional Meeting (WRM)

Early prediction of lithium-ion battery degradation: Using six health indicators to analyze long short-term memory and random forest in battery health prognostics

Yingying Zou, Kaiwen Zhao, Irene Lu, Emily Liu, Mandy Hung, Richard Song, Chris Lin, Andrew Cha, Linda Shi

San Jose, CA · Poster

Read the poster →

Figures

Hybrid model architecture: a BiLSTM module feeding feature enhancement and random forest regression to produce a remaining-useful-life estimate.

LSTM and random forest training prediction against measured constant-discharge cycle time.

Measured against predicted state of health, showing the 80% threshold and the resulting remaining-useful-life estimate (R² = 0.972).

ACS Western Regional Meeting 2025 · CC BY 4.0

Citation

Zou, Y., Zhao, K., Lu, I., Liu, E., Hung, M., Song, R., Lin, C., Cha, A., & Shi, L. (2025). Early prediction of lithium-ion battery degradation: Using six health indicators to analyze long short-term memory and random forest in battery health prognostics [Poster]. 2025 American Chemical Society Western Regional Meeting (WRM), San Jose, CA. https://doi.org/10.6084/m9.figshare.30443747

@misc{zou2025early,
  author       = {Zou, Yingying and Zhao, Kaiwen and Lu, Irene and Liu, Emily and Hung, Mandy and Song, Richard and Lin, Chris and Cha, Andrew and Shi, Linda},
  title        = {Early prediction of lithium-ion battery degradation: Using six health indicators to analyze long short-term memory and random forest in battery health prognostics},
  year         = {2025},
  howpublished = {2025 American Chemical Society Western Regional Meeting (WRM), San Jose, CA},
  note         = {Poster},
  doi          = {10.6084/m9.figshare.30443747},
  url          = {https://doi.org/10.6084/m9.figshare.30443747}
}

The wider project →← All research