{"success":true,"data":{"author":"Kristen Severson, Peter Attia, William Chueh, Richard Braatz et al. (Stanford, MIT, Toyota Research Institute)","bucketAccessType":"public","bucketName":"bsebench-org/severson-2019-raw","bucketPrefix":"","category":"Energy","cloudProvider":"huggingface","createdAt":"2026-11-18T17:37:19.476Z","description":"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.","displayTitle":"Severson/Attia Stanford-MIT-Toyota Battery Cycle Life Data: 124 Commercial LFP/Graphite Cells Cycled to Failure under Fast Charging (bsebench copy)","doi":"10.1038/s41560-019-0356-8","huggingFaceUrl":"https://huggingface.co/datasets/bsebench-org/severson-2019-raw","id":"db456201-699c-519e-b4ff-4d45dfe97764","license":"CC-BY-4.0","licenseEvidenceUrl":"https://data.matr.io/","objectCountEstimate":5,"probeStatus":"ok","referenceUrl":"https://doi.org/10.1038/s41560-019-0356-8","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"bsebench-org/severson-2019-raw\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"bsebench-org/severson-2019-raw\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=bsebench-org, license:cc-by-4.0, size_categories:1B<n<10B, downloads=1613"],"format":"mixed","generatedAt":"2026-11-18T17:39:10.581Z","layout":{"example":"2017-05-12_batchdata_updated_struct_errorcorrect.mat","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"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","encoding":"hex","key":"2017-05-12_batchdata_updated_struct_errorcorrect.mat","truncatedAt":512}],"sampleObjects":["2017-05-12_batchdata_updated_struct_errorcorrect.mat","2017-06-30_batchdata_updated_struct_errorcorrect.mat","2018-04-12_batchdata_updated_struct_errorcorrect.mat"],"sidecars":[{"bytes":"---\nlicense: cc-by-4.0\nlanguage:\n  - en\nsize_categories:\n  - 1B<n<10B\ntask_categories:\n  - time-series-forecasting\n  - tabular-regression\ntags:\n  - battery\n  - state-of-charge\n  - state-of-health\n  - lithium-ion\n  - LFP\n  - lithium-iron-phosphate\n  - fast-charging\n  - cycling\n  - kalman-filter\n  - benchmark\n  - bsebench\n  - tier-1-raw\npretty_name: \"Severson 2019 LFP Fastcharge — Tier 1 Raw Mirror\"\n---\n\n# severson-2019-raw\n\n**Tier 1 raw mirror** of the Severson et al. 2019 commercial LFP fastcharge\ncycling dataset, hosted under the [BSEBench](https://bsebench.org)\norganization on the HuggingFace Hub. The files in this repository are\npreserved bit-exact as published on the original Toyota Research Institute\ndata portal at [data.matr.io](https://data.matr.io/1/). No values are\nmodified; no columns are renamed; no rows are dropped. Every file's\nSHA-256 digest is recorded in the BSEBench manifest YAML and matches the\noriginal distribution.\n\nThis repository exists for **provenance verification and audits only**.\nFor the BSEBench-canonical Parquet harmonization that consumers actually\nuse for filter benchmarking, see the Tier 2 sibling repository\n[`bsebench-org/severson-2019`](https://huggingface.co/datasets/bsebench-org/severson-2019).\n\n## Status\n\nThis is a **placeholder card**. The raw `.mat` files are not yet uploaded\nto the HuggingFace Hub. The planned upload pipeline is :\n\n1. Manual download of the three Severson batches from\n   `https://data.matr.io/1/projects/5c48dd2bc625d700019f3204` (registration\n   may be required by the TRI portal).\n2. Local SHA-256 computation via `scripts/upload_tier1_to_hf.py --src ./local\n   --repo-id bsebench-org/severson-2019-raw --private --dry-run`.\n3. Inventory cross-check against\n   `bsebench-datasets/manifests/severson_2019_lfp.yaml` (committed only after\n   real digests are populated — no fake checksums in this repository).\n4. Public upload (`--dry-run` removed) once the manifest validates.\n5. Update of this card with the populated `## File inventory` section, the\n   manifest commit SHA, and a `verified_at` timestamp.\n\nUntil step 5 is reached, treat the file inventory below as a **best-effort\nestimate** based on community references (BatteryML, BEEP, MIT Braatz Group\nGitHub repository), not as a directly verified manifest of HuggingFace\ncontent.\n\n## What this is\n\nA bit-exact mirror of the dataset published with :\n\n> **Severson, K. A., Attia, P. M., Jin, N., Perkins, N., Jiang, B.,\n> Yang, Z., Chen, M. H., Aykol, M., Herring, P. K., Fraggedakis, D.,\n> Bazant, M. Z., Harris, S. J., Chueh, W. C., Braatz, R. D. (2019).**\n> \"Data-driven prediction of battery cycle life before capacity degradation.\"\n> *Nature Energy*, **4**(5), 383–391.\n> doi:[10.1038/s41560-019-0356-8](https://doi.org/10.1038/s41560-019-0356-8)\n\n```bibtex\n@article{severson2019datadriven,\n  author  = {Severson, Kristen A. and Attia, Peter M. and Jin, Norman\n             and Perkins, Nicholas and Jiang, Benben and Yang, Zi\n             and Chen, Michael H. and Aykol, Muratahan\n             and Herring, Patrick K. and Fraggedakis, Dimitrios\n             and Bazant, Martin Z. and Harris, Stephen J.\n             and Chueh, William C. and Braatz, Richard D.},\n  title   = {Data-driven prediction of battery cycle life before\n             capacity degradation},\n  journal = {Nature Energy},\n  volume  = {4},\n  number  = {5},\n  pages   = {383--391},\n  year    = {2019},\n  doi     = {10.1038/s41560-019-0356-8},\n  url     = {https://www.nature.com/articles/s41560-019-0356-8},\n}\n```\n\n## Cell specifications\n\n| Property | Value |\n|---|---|\n| Manufacturer | A123 Systems |\n| Model | APR18650M1A |\n| Form factor | 18650 cylindrical |\n| Cathode chemistry | LFP (lithium iron phosphate, LiFePO4) |\n| Anode chemistry | Graphite |\n| Nominal capacity | 1.1 Ah |\n| Nominal voltage | 3.3 V |\n| Charge cutoff (used) | 3.6 V |\n| Discharge cutoff (used) | 2.0 V |\n| Number of cells (this dataset) | 124 |\n| End-of-life threshold | 80 % capacity retention |\n\n## Cycling protocol\n\nAll cells were cycled inside a 30 °C controlled environmental chamber.\nCharging ","encoding":"utf8","key":"README.md","name":"README.md","size":13136,"truncated":true}],"sourceObjectKey":"2017-05-12_batchdata_updated_struct_errorcorrect.mat","starterCell":"from huggingface_hub import hf_hub_download\npath = hf_hub_download(repo_id=\"bsebench-org/severson-2019-raw\", filename=\"2017-05-12_batchdata_updated_struct_errorcorrect.mat\", repo_type=\"dataset\")\nprint(path)","starterSamplePath":"2017-05-12_batchdata_updated_struct_errorcorrect.mat","totalObjects":5},"summary":"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)…","title":"Severson/Attia Stanford-MIT-Toyota Battery Cycle Life Data: 124 Commercial LFP/Graphite Cells Cycled to Failure under Fast Charging (bsebench copy)","updatedAt":"2026-11-18T18:52:26.744Z","visibility":"public","websiteUrl":"https://huggingface.co/datasets/bsebench-org/severson-2019-raw"}}