# Synthetic Li-ion Voltage-Capacity Curves with Degradation-Mode Labels (Graphite/LFP, NCA, NMC)

## Facts

- Provider: Hawaii Natural Energy Institute, PakaLi lab (Matthieu Dubarry)
- License: CC-BY-4.0 (https://huggingface.co/datasets/HNEI-PakaLi-Lab/synthetic-battery-diagnosis)
- Size: 108 files
- Format: Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/HNEI-PakaLi-Lab/synthetic-battery-diagnosis
- Access: public, readable without an account
- Category: Energy
- Source: https://doi.org/10.1016/j.jpowsour.2020.228806
- Page: https://scigantic.com/archive/ffa67737-6870-58c2-9272-7843758ce335
- Keywords: Energy, Parquet, Hugging Face

## About

Synthetic voltage versus capacity curves for lithium-ion battery degradation-mode diagnosis, released by the PakaLi lab at the Hawaii Natural Energy Institute (HNEI). Curves were computed with the mechanistic modeling approach of Dubarry et al. for three chemistries, graphite/LFP, graphite/NCA and graphite/NMC, at a C/25 charge rate, each labeled with loss of lithium inventory (LLI), loss of active material at the positive electrode (LAMPE) and at the negative electrode (LAMNE), and capacity loss. Each chemistry has about 705,000 training curves plus three 6,000-curve test sets (C1, C2, C3) for cell configurations not seen in training, taken from the DTW Li-ion diagnosis study, and a references split with the pristine curve of every configuration. Data are Parquet files under data/ / on a shared normalized-capacity grid, with metadata.json and provenance.json recording the source MATLAB files and transformations; load with the Hugging Face datasets library (configs lfp, nca, nmc). Training curves derive from Matthieu Dubarry's Mendeley Data releases (CC BY 4.0); the lab releases the curves, tests and labels under CC-BY-4.0. Cite Dubarry and Beck, Journal of Power Sources 479 (2020) 228806.

## Load the data

```python
from datasets import load_dataset
ds = load_dataset("HNEI-PakaLi-Lab/synthetic-battery-diagnosis")
print(ds)
```

## Data structure

File types in sampled files: Parquet

Example file: `data/lfp/references.parquet`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/ffa67737-6870-58c2-9272-7843758ce335
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/ffa67737-6870-58c2-9272-7843758ce335
- Over MCP: `get_schema_card` with id `ffa67737-6870-58c2-9272-7843758ce335` at https://api.scigantic.com/mcp

## Related topics

- [Parquet datasets](https://scigantic.com/topics/parquet)
- [Energy datasets](https://scigantic.com/topics/energy)
