# Severson/Attia Stanford-MIT-Toyota Battery Cycle Life Data: 124 Commercial LFP/Graphite Cells Cycled to Failure under Fast Charging (bsebench copy)

## Facts

- Provider: Kristen Severson, Peter Attia, William Chueh, Richard Braatz et al. (Stanford, MIT, Toyota Research Institute)
- License: CC-BY-4.0 (https://data.matr.io/)
- Size: 5 files
- Stored at: Hugging Face, https://huggingface.co/datasets/bsebench-org/severson-2019-raw
- Access: public, readable without an account
- DOI: https://doi.org/10.1038/s41560-019-0356-8
- Category: Energy
- Source: https://doi.org/10.1038/s41560-019-0356-8
- Page: https://scigantic.com/archive/db456201-699c-519e-b4ff-4d45dfe97764
- Keywords: Energy, Hugging Face

## About

Cycling data behind Severson et al. 2019, Data-driven prediction of battery cycle life before capacity degradation (Nature Energy), released by the Toyota Research Institute (TRI) on its Energy and Materials data portal, data.matr.io. The dataset consists of 124 commercial lithium iron phosphate (LFP)/graphite cells cycled to failure under fast-charging conditions; the study used discharge voltage curves from early cycles, before capacity fade appears, to predict cycle life with machine learning. This Hugging Face copy by BSEBench holds the three original MATLAB batch files, 2017-05-12, 2017-06-30 and 2018-04-12 batchdata_updated_struct_errorcorrect.mat (about 8.3 GB in total), each a struct with per-cell charge policy, per-cycle summary (discharge capacity, internal resistance, charge time, temperature) and within-cycle voltage, current, temperature and capacity traces. Load with scipy.io.loadmat or h5py (MATLAB v7.3), or with the BEEP and BatteryML loaders. The TRI catalog lists the dataset under CC BY 4.0; cite Severson et al. 2019, doi:10.1038/s41560-019-0356-8.

## Load the data

```python
from huggingface_hub import hf_hub_download
path = hf_hub_download(repo_id="bsebench-org/severson-2019-raw", filename="2017-05-12_batchdata_updated_struct_errorcorrect.mat", repo_type="dataset")
print(path)
```

## Data structure

Example file: `2017-05-12_batchdata_updated_struct_errorcorrect.mat`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/db456201-699c-519e-b4ff-4d45dfe97764
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/db456201-699c-519e-b4ff-4d45dfe97764
- Over MCP: `get_schema_card` with id `db456201-699c-519e-b4ff-4d45dfe97764` at https://api.scigantic.com/mcp

## Related topics

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