{"success":true,"data":{"author":"Peter Attia, Aditya Grover, Norman Jin, Kristen Severson, William Chueh et al. (Stanford, MIT, Toyota Research Institute)","bucketAccessType":"public","bucketName":"bsebench-org/tri-attia-fast-charge-2020-raw","bucketPrefix":"","category":"Energy","cloudProvider":"huggingface","createdAt":"2026-11-18T17:37:19.603Z","description":"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.","displayTitle":"Attia et al. Closed-Loop Optimization of Extreme Fast Charging: Toyota Research Institute Cell Cycling Data (bsebench copy)","doi":"10.1038/s41586-020-1994-5","huggingFaceUrl":"https://huggingface.co/datasets/bsebench-org/tri-attia-fast-charge-2020-raw","id":"15f42b54-6e1e-529e-a8a5-154509d3e1fb","license":"CC-BY-4.0","licenseEvidenceUrl":"https://data.matr.io/","objectCountEstimate":727,"probeStatus":"ok","referenceUrl":"https://doi.org/10.1038/s41586-020-1994-5","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"bsebench-org/tri-attia-fast-charge-2020-raw\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"bsebench-org/tri-attia-fast-charge-2020-raw\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=bsebench-org, license:cc-by-4.0, size_categories:10M<n<100M, format:csv, downloads=1122"],"format":"mixed","generatedAt":"2026-11-18T17:39:10.834Z","layout":{"example":"source_files/data_csv/Batch9__validation_batch_/2019-01-24_batch9_CH1.csv","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"Data_Point,Test_Time,DateTime,Step_Time,Step_Index,Cycle_Index,Current,Voltage,Charge_Capacity,Discharge_Capacity,Charge_Energy,Discharge_Energy,dV/dt,Internal_Resistance,Temperature,Aux_Voltage\n0,-17140.3059,1548370038.9499,60.0026,0,0,0.0,3.2998075,0.0,0.0,0.0,0.0,-2.8610229e-05,,,\n1,-17080.3085,1548370098.9473,120.0,0,0,0.0,3.2998018,0.0,0.0,0.0,0.0,2.8610229e-06,,31.576925066659555,\n2,-17020.3046,1548370158.9512,180.0039,0,0,0.0,3.2997913,0.0,0.0,0.0,0.0,-3.528595e-05,,31.526485,\n3,-16960.3056,154837021","encoding":"utf8","key":"source_files/data_csv/Batch9__validation_batch_/2019-01-24_batch9_CH1.csv","truncatedAt":512}],"sampleObjects":["BSEBENCH_SOURCE.json","SHA256SUMS.txt","SOURCE_FILE_MANIFEST.json","source_files/data_csv/Batch9__validation_batch_/2019-01-24_batch9_CH1.csv","source_files/data_csv/Batch9__validation_batch_/2019-01-24_batch9_CH10.csv"],"sidecars":[{"bytes":"---\ntitle: Closed-loop optimization of extreme fast charging for batteries\nlicense: cc-by-4.0\npretty_name: Closed-loop optimization of extreme fast charging for batteries\ntags:\n- bsebench\n- batteries\n- fast-charging\n- raw-mirror\n- materials-science\n---\n\n# Closed-loop optimization of extreme fast charging for batteries\n\nBSEBench status: `raw_mirror_pending_validation`\n\nThis dataset repository is a raw mirror of the TRI Energy & Materials Data / data.matr.io project \"Closed-loop optimization of extreme fast charging for batteries using machine learning\". The source describes commercial lithium-ion phosphate (LFP)/graphite cells cycled under fast-charging conditions for the associated Nature publication.\n\nSource page: https://data.matr.io/  \nProject URL: https://data.matr.io/1/projects/5d80e633f405260001c0b60a  \nDOI: https://doi.org/10.1038/s41586-020-1994-5  \nLicense: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)  \nSource institution/credibility: Stanford University / MIT / Toyota Research Institute  \nDownload date: 2026-05-08\n\n## Contents\n\nThe files under `source_files/` are the official source downloads retrieved from `https://data.matr.io/1/api/v1/file/<file_id>/download` and organized by source file kind and batch. No scientific data values were transformed.\n\nActual downloaded source payload:\n\n| Kind | Files | Bytes |\n|---|---:|---:|\n| MATLAB struct files | 5 | 3975095856 |\n| JSON structure ZIP files | 5 | 6855320161 |\n| Raw CSV data files | 236 | 11275069907 |\n| Metadata CSV files | 236 | 124514 |\n| Schedule files | 236 | 5038701 |\n| Total source files | 718 | 22110649139 |\n\n`SOURCE_FILE_MANIFEST.json` records the official file IDs, source URLs, source API metadata, local paths, and measured local byte counts. `SHA256SUMS.txt` records checksums for uploaded files.\n\n## Provenance Notes\n\nThe TRI catalog page lists this dataset with license CC BY 4.0, and the project API page includes the citation and DOI for Attia et al. (2020). The Nature article data-availability section links the study datasets to `https://data.matr.io/1/`.\n\nSome `size` values returned by the source API differ from the byte counts of the redirected downloadable assets, especially JSON-structure ZIP archives. This mirror treats the actual downloaded files and SHA-256 checksums as authoritative and records both API-reported and measured sizes in `SOURCE_FILE_MANIFEST.json`.\n\n## Citation\n\nAttia, P. M., Grover, A., Jin, N. et al. Closed-loop optimization of fast-charging protocols for batteries with machine learning. Nature 578, 397-402 (2020). https://doi.org/10.1038/s41586-020-1994-5\n\n## License\n\nThe source page and API configuration identify the dataset license as Creative Commons Attribution 4.0 International (CC BY 4.0). Users should follow the source license and cite the original work.\n","encoding":"utf8","key":"README.md","name":"README.md","size":2820,"truncated":false}],"sourceObjectKey":"source_files/data_csv/Batch9__validation_batch_/2019-01-24_batch9_CH1.csv","starterCell":"import pandas as pd\ndf = 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\")\ndf.head()","starterSamplePath":"source_files/data_csv/Batch9__validation_batch_/2019-01-24_batch9_CH1.csv","totalObjects":727},"summary":"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…","title":"Attia et al. Closed-Loop Optimization of Extreme Fast Charging: Toyota Research Institute Cell Cycling Data (bsebench copy)","updatedAt":"2026-11-18T19:17:45.694Z","visibility":"public","websiteUrl":"https://huggingface.co/datasets/bsebench-org/tri-attia-fast-charge-2020-raw"}}