# Attia et al. Closed-Loop Optimization of Extreme Fast Charging: Toyota Research Institute Cell Cycling Data (bsebench copy)

## Facts

- Provider: Peter Attia, Aditya Grover, Norman Jin, Kristen Severson, William Chueh et al. (Stanford, MIT, Toyota Research Institute)
- License: CC-BY-4.0 (https://data.matr.io/)
- Size: 727 files
- Format: JSON, CSV (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/bsebench-org/tri-attia-fast-charge-2020-raw
- Access: public, readable without an account
- DOI: https://doi.org/10.1038/s41586-020-1994-5
- Category: Energy
- Source: https://doi.org/10.1038/s41586-020-1994-5
- Page: https://scigantic.com/archive/15f42b54-6e1e-529e-a8a5-154509d3e1fb
- Keywords: Energy, time series, JSON, CSV, Hugging Face

## About

Battery cycling data from Attia et al. 2020, Closed-loop optimization of fast-charging protocols for batteries with machine learning (Nature), published by the Toyota Research Institute (TRI) on data.matr.io. Commercial lithium-ion cells were cycled under candidate extreme fast-charging protocols chosen in a closed-loop optimization (optimal experimental design, OED) that combined Bayesian optimization with an early-prediction model of cycle life, plus a validation batch. The BSEBench copy keeps the files exactly as downloaded from the TRI file API, organized by kind and batch under source_files/: 236 raw cycler CSV time series (data_csv), 236 metadata and 236 schedule files, and five MATLAB struct files plus five JSON structure ZIPs, for batches Batch_oed_0 to Batch_oed_3 and Batch9 (validation), about 22 GB in all. CSVs read with pandas; the structs with scipy or h5py, or the BEEP library. The TRI catalog lists the dataset under CC BY 4.0; cite Attia et al. 2020, doi:10.1038/s41586-020-1994-5.

## Load the data

```python
import pandas as pd
df = pd.read_csv("hf://datasets/bsebench-org/tri-attia-fast-charge-2020-raw/source_files/data_csv/Batch9__validation_batch_/2019-01-24_batch9_CH1.csv")
df.head()
```

## Data structure

File types in sampled files: JSON, CSV

Example file: `source_files/data_csv/Batch9__validation_batch_/2019-01-24_batch9_CH1.csv`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/15f42b54-6e1e-529e-a8a5-154509d3e1fb
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/15f42b54-6e1e-529e-a8a5-154509d3e1fb
- Over MCP: `get_schema_card` with id `15f42b54-6e1e-529e-a8a5-154509d3e1fb` at https://api.scigantic.com/mcp

## Related topics

- [JSON datasets](https://scigantic.com/topics/json)
- [CSV datasets](https://scigantic.com/topics/csv)
- [Time series datasets](https://scigantic.com/topics/time-series)
- [Energy datasets](https://scigantic.com/topics/energy)
