{"success":true,"data":{"author":"Jiawei Zhang, Yifei Zhang, Baozhao Yi, Yao Ren et al. (original data); BatteryLife team, HKUST Guangzhou (processed copy)","bucketAccessType":"public","bucketName":"Battery-Life/BatteryLife_Farasis","bucketPrefix":"","category":"Energy","cloudProvider":"huggingface","createdAt":"2026-11-19T15:09:18.526Z","description":"Cycling data for 123 industrial-grade large-format lithium-ion pouch cells from Farasis Energy, released with Zhang et al., Discovery Learning predicts battery cycle life from minimal experiments (Nature, 2026). The cells cover eight cell types with diverse material-design combinations and cycling protocols and form 37 groups of near-identical cells, which supports study of cell-to-cell variability and early cycle-life prediction. The original Zenodo record (doi:10.5281/zenodo.17654407) provides one-second raw Parquet logs of current, voltage, temperature and step information, reference performance test (RPT) capacity workbooks and a cell-to-group map with cycle-life labels; seven mission-profile or driving-protocol cells keep only their RPT segments because the cycling portions are proprietary. This Hugging Face repository, from the BatteryLife benchmark team (HKUST Guangzhou), holds 123 processed Python pickle files, one per cell named by the original Farasis cell id (about 121 GB), with SOC and corrections applied for use with the BatteryLife preprocessing and benchmarking code (github.com/Ruifeng-Tan/BatteryLife). Original data licensed CC BY 4.0; cite Zhang et al. 2026, Nature, doi:10.1038/s41586-025-09951-7.","displayTitle":"Farasis Industrial Pouch-Cell Cycle Life Data: 123 Large-Format Li-ion Cells from Discovery Learning (Nature 2026), BatteryLife Processed Copy","doi":"10.5281/zenodo.17654407","huggingFaceUrl":"https://huggingface.co/datasets/Battery-Life/BatteryLife_Farasis","id":"96a86c12-73bb-5315-8925-eb8f631f00c8","license":"CC-BY-4.0","licenseEvidenceUrl":"https://zenodo.org/api/records/17654407","objectCountEstimate":126,"probeStatus":"ok","referenceUrl":"https://doi.org/10.1038/s41586-025-09951-7","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"Battery-Life/BatteryLife_Farasis\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"Battery-Life/BatteryLife_Farasis\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=Battery-Life, size_categories:n<1K, format:json, downloads=1160"],"format":"mixed","generatedAt":"2026-11-19T15:21:44.501Z","layout":{"example":"Farasis_PA-b1_001_single_parquet_with_soc_and_corrections.pkl","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"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","encoding":"hex","key":"Farasis_PA-b1_001_single_parquet_with_soc_and_corrections.pkl","truncatedAt":512}],"sampleObjects":["Farasis_PA-b1_001_single_parquet_with_soc_and_corrections.pkl","Farasis_PA-b1_002_single_parquet_with_soc_and_corrections.pkl","Farasis_PA-b1_003_single_parquet_with_soc_and_corrections.pkl","Farasis_PA-b1_004_single_parquet_with_soc_and_corrections.pkl","Farasis_PA-b1_005_single_parquet_with_soc_and_corrections.pkl"],"sidecars":[{"bytes":"# README\n\nThis dataset consists of 123 industrial-grade large-format lithium-ion pouch cells released with the Nature article **Discovery Learning predicts battery cycle life from minimal experiments**. The article describes these cells as having diverse material-design combinations and cycling protocols. The source data are available from Zenodo and Code Ocean through the article's Data availability section.\n\nThe local processed directory contains 123 `.pkl` files, one file per cell. File names preserve the original Farasis cell id and source parquet path, for example:\n\n```text\nFarasis_PB-b1_2_MP_029_single_parquet_with_soc_and_corrections_updated.pkl\n```\n\nIf you use this dataset, please cite the original paper:\n\n- **Discovery Learning predicts battery cycle life from minimal experiments** *2026 Nature*\n\n| Battery Number | Format | Chemical System                           | Operation Temperature                                        | Protocol                            | Data Source     | Battery Type | Year |\n| -------------- | ------ | ----------------------------------------- | ------------------------------------------------------------ | ----------------------------------- | --------------- | ------------ | ---- |\n| 123            | 1      | 2 local processed material metadata pairs | Not specified in the local processed metadata or Zenodo readme | 4 filename-derived protocol classes | Industrial test | Li-ion       | 2026 |\n\n## Source Data\n\nThe original dataset is available at:\n\n- Nature article: https://www.nature.com/articles/s41586-025-09951-7\n- Zenodo: https://doi.org/10.5281/zenodo.17654407\n- Code Ocean: https://doi.org/10.24433/CO.5569470.v1\n\nThe Nature article states that the study data contain 123 large-format lithium-ion pouch cells. The Zenodo record contains these files:\n\n- `raw_data.zip`\n- `rpt_data.zip`\n- `number_relationship.xlsx`\n- `readme.txt`\n- `Parquet_analysis.py`\n\nThe Zenodo `readme.txt` describes the source dataset as RPT `.xlsx` files and raw `.parquet` files for eight battery cell types. It states that the parquet files contain current, voltage, temperature, and other cycling information recorded at one-second resolution. It also states that `number_relationship.xlsx` maps 123 cells to 37 cell groups and records the cycle-life labels.\n\n## Local Raw Files\n\nThe local raw directory `datasets/raw/Farasis/` contains:\n\n| File type  | Count |\n| ---------- | ----: |\n| `.parquet` |   123 |\n| `.npy`     |    14 |\n\nThe 14 `.npy` files are author-provided `efc`/`soh` arrays for seven MP or driving-protocol cells.\n\nThe local parquet files use columns including:\n\n```text\ntime_stamp\ndel_time\ncurrent (A)\nvoltage (V)\nstep_no\ntemp\nsource\nrpt\nsoc\ncv_hold\nnet_thrgh_ah\ntotal_chg_thrgh_ah_rounded\ntotal_dischg_thrgh_ah_rounded\ntotal_energy_thrgh_kwh_rounded\n```\n\n## Local Processed Files\n\nThe processed pickle files are generated from the local parquet files by `process_scripts/preprocess_Farasis.py`.\n\nEach processed pickle contains BatteryML-style fields including:\n\n```text\ncell_id\ncycle_data\nform_factor\nanode_material\ncathode_material\nnominal_capacity_in_Ah\nmin_voltage_limit_in_V\nmax_voltage_limit_in_V\nSOC_interval\ncharge_protocol\ndischarge_protocol\n```\n\nEach `cycle_data` entry contains fields including:\n\n```text\ncycle_number\nvoltage_in_V\ncurrent_in_A\ntemperature_in_C\ndischarge_capacity_in_Ah\ncharge_capacity_in_Ah\ntime_in_s\nattribute\n```\n\n## Local File-Name Statistics\n\nThe 123 processed files are distributed across these filename-derived cell types:\n\n| Cell type token | Processed cell count |\n| --------------- | -------------------: |\n| `PA-b1`         |                    6 |\n| `PA-b2`         |                    5 |\n| `PA-b3`         |                    8 |\n| `PB-b1`         |                   10 |\n| `PB-b2`         |                    4 |\n| `PC-b1`         |                   57 |\n| `PC-b2`         |                   22 |\n| `PD`            |                   11 |\n\nThe filename-derived protocol tokens are:\n\n| Protocol token             | Processed cell count |\n| -------------------------- | ------------","encoding":"utf8","key":"README.md","name":"README.md","size":6894,"truncated":true}],"sourceObjectKey":"Farasis_PA-b1_001_single_parquet_with_soc_and_corrections.pkl","starterCell":"from huggingface_hub import hf_hub_download\npath = hf_hub_download(repo_id=\"Battery-Life/BatteryLife_Farasis\", filename=\"Farasis_PA-b1_001_single_parquet_with_soc_and_corrections.pkl\", repo_type=\"dataset\")\nprint(path)","starterSamplePath":"Farasis_PA-b1_001_single_parquet_with_soc_and_corrections.pkl","totalObjects":126},"summary":"Cycling data for 123 industrial-grade large-format lithium-ion pouch cells from Farasis Energy, released with Zhang et al., Discovery Learning predicts battery cycle life from…","title":"Farasis Industrial Pouch-Cell Cycle Life Data: 123 Large-Format Li-ion Cells from Discovery Learning (Nature 2026), BatteryLife Processed Copy","updatedAt":"2026-11-19T19:03:42.210Z","visibility":"public","websiteUrl":"https://huggingface.co/datasets/Battery-Life/BatteryLife_Farasis"}}