EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Accounting-Guided Data Augmentation for LightGBM Prediction of Cradle-to-Gate Carbon Footprints of LFP and NMC811 Battery Cells

Zhihao Xu, Haoyang Li, Songxian Peng, Guangzong Xu, Xinlong Wang, Lijing Wang

Batteries · 07.11.2026 · 12 (11) · 477

DOI: 10.3390/batteries12110477 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Batteries, online erschienen am 07.11.2026. Verfasst von Zhihao Xu und 5 weiteren Autor:innen. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Zhejiang Provincial Administration for Market Regulation “Pioneer”.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Machine-learning models fitted to limited battery inventory data may reproduce nominal carbon footprints accurately while failing to preserve known inventory–emission relationships under changed inputs. This study evaluates accounting-guided data augmentation for component-wise LightGBM prediction of cradle-to-gate carbon footprints of lithium iron phosphate (LFP) and nickel manganese cobalt oxide (NMC811) pouch cells. Published inventories were expanded through ±10% input perturbations, zero-input samples, and proportional scaling. The models use material quantities, manufacturing-energy inputs, and regional production descriptors, with footprints normalized to 1 kWh of cell capacity. On the held-out synthetic test set, the framework achieved an R2 of 0.9991, a mean absolute error of 0.4486 kg CO2-eq/kWh, and a root mean square error of 0.6246 kg CO2-eq/kWh. When numeric inputs were scaled to 60% of their original values, augmentation improved R2 from −1.9425 to 0.8333 relative to unaugmented LightGBM. In a single random-masking realization, R2 remained above 0.995 with 50% of numeric inputs masked and imputed. These results show improved surrogate consistency within the represented inventory domain. They do not establish superiority over direct calculation or linear regression, or validate prediction from a restricted set of early-design inputs.

Förderung

  • Zhejiang Provincial Administration for Market Regulation “Pioneer”

Zitieren

APA

Xu, Z., Li, H., Peng, S., Xu, G., Wang, X., & Wang, L. (2026). Accounting-Guided Data Augmentation for LightGBM Prediction of Cradle-to-Gate Carbon Footprints of LFP and NMC811 Battery Cells. Batteries, 12(11), 477. https://doi.org/10.3390/batteries12110477

Vancouver

Xu Z, Li H, Peng S, Xu G, Wang X, Wang L. Accounting-Guided Data Augmentation for LightGBM Prediction of Cradle-to-Gate Carbon Footprints of LFP and NMC811 Battery Cells. Batteries. 2026;12(11):477. doi:10.3390/batteries12110477

BibTeX
@article{Xu2026,
  author = {Xu, Zhihao and Li, Haoyang and Peng, Songxian and Xu, Guangzong and Wang, Xinlong and Wang, Lijing},
  title = {Accounting-Guided Data Augmentation for LightGBM Prediction of Cradle-to-Gate Carbon Footprints of LFP and NMC811 Battery Cells},
  journal = {Batteries},
  year = {2026},
  volume = {12},
  number = {11},
  pages = {477},
  doi = {10.3390/batteries12110477}
}
Kostenlos starten →