{"success":true,"data":{"author":"Hawaii Natural Energy Institute, PakaLi lab (Matthieu Dubarry)","bucketAccessType":"public","bucketName":"HNEI-PakaLi-Lab/synthetic-battery-diagnosis","bucketPrefix":"","category":"Energy","cloudProvider":"huggingface","createdAt":"2026-11-18T00:06:05.362Z","description":"Synthetic voltage versus capacity curves for lithium-ion battery degradation-mode diagnosis, released by the PakaLi lab at the Hawaii Natural Energy Institute (HNEI). Curves were computed with the mechanistic modeling approach of Dubarry et al. for three chemistries, graphite/LFP, graphite/NCA and graphite/NMC, at a C/25 charge rate, each labeled with loss of lithium inventory (LLI), loss of active material at the positive electrode (LAMPE) and at the negative electrode (LAMNE), and capacity loss. Each chemistry has about 705,000 training curves plus three 6,000-curve test sets (C1, C2, C3) for cell configurations not seen in training, taken from the DTW Li-ion diagnosis study, and a references split with the pristine curve of every configuration. Data are Parquet files under data/<chemistry>/ on a shared normalized-capacity grid, with metadata.json and provenance.json recording the source MATLAB files and transformations; load with the Hugging Face datasets library (configs lfp, nca, nmc). Training curves derive from Matthieu Dubarry's Mendeley Data releases (CC BY 4.0); the lab releases the curves, tests and labels under CC-BY-4.0. Cite Dubarry and Beck, Journal of Power Sources 479 (2020) 228806.","displayTitle":"Synthetic Li-ion Voltage-Capacity Curves with Degradation-Mode Labels (Graphite/LFP, NCA, NMC)","huggingFaceUrl":"https://huggingface.co/datasets/HNEI-PakaLi-Lab/synthetic-battery-diagnosis","id":"ffa67737-6870-58c2-9272-7843758ce335","license":"CC-BY-4.0","licenseEvidenceUrl":"https://huggingface.co/datasets/HNEI-PakaLi-Lab/synthetic-battery-diagnosis","objectCountEstimate":108,"probeStatus":"ok","referenceUrl":"https://doi.org/10.1016/j.jpowsour.2020.228806","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"HNEI-PakaLi-Lab/synthetic-battery-diagnosis\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"HNEI-PakaLi-Lab/synthetic-battery-diagnosis\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=HNEI-PakaLi-Lab, license:cc-by-4.0, size_categories:1M<n<10M, format:parquet, downloads=244"],"format":"mixed","generatedAt":"2026-11-18T00:09:36.793Z","layout":{"example":"data/lfp/references.parquet","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"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","encoding":"hex","key":"data/lfp/references.parquet","truncatedAt":512}],"sampleObjects":["data/lfp/references.parquet","data/lfp/test_c1.parquet","data/lfp/test_c2.parquet","data/lfp/test_c3.parquet","data/lfp/train/part-1-000000.parquet"],"sidecars":[{"bytes":"Attribution 4.0 International\n\n=======================================================================\n\nCreative Commons Corporation (\"Creative Commons\") is not a law firm and\ndoes not provide legal services or legal advice. Distribution of\nCreative Commons public licenses does not create a lawyer-client or\nother relationship. Creative Commons makes its licenses and related\ninformation available on an \"as-is\" basis. Creative Commons gives no\nwarranties regarding its licenses, any material licensed under their\nterms and conditions, or any related information. Creative Commons\ndisclaims all liability for damages resulting from their use to the\nfullest extent possible.\n\nUsing Creative Commons Public Licenses\n\nCreative Commons public licenses provide a standard set of terms and\nconditions that creators and other rights holders may use to share\noriginal works of authorship and other material subject to copyright\nand certain other rights specified in the public license below. The\nfollowing considerations are for informational purposes only, are not\nexhaustive, and do not form part of our licenses.\n\n     Considerations for licensors: Our public licenses are\n     intended for use by those authorized to give the public\n     permission to use material in ways otherwise restricted by\n     copyright and certain other rights. Our licenses are\n     irrevocable. Licensors should read and understand the terms\n     and conditions of the license they choose before applying it.\n     Licensors should also secure all rights necessary before\n     applying our licenses so that the public can reuse the\n     material as expected. Licensors should clearly mark any\n     material not subject to the license. This includes other CC-\n     licensed material, or material used under an exception or\n     limitation to copyright. More considerations for licensors:\n    wiki.creativecommons.org/Considerations_for_licensors\n\n     Considerations for the public: By using one of our public\n     licenses, a licensor grants the public permission to use the\n     licensed material under specified terms and conditions. If\n     the licensor's permission is not necessary for any reason--for\n     example, because of any applicable exception or limitation to\n     copyright--then that use is not regulated by the license. Our\n     licenses grant only permissions under copyright and certain\n     other rights that a licensor has authority to grant. Use of\n     the licensed material may still be restricted for other\n     reasons, including because others have copyright or other\n     rights in the material. A licensor may make special requests,\n     such as asking that all changes be marked or described.\n     Although not required by our licenses, you are encouraged to\n     respect those requests where reasonable. More considerations\n     for the public:\n    wiki.creativecommons.org/Considerations_for_licensees\n\n=======================================================================\n\nCreative Commons Attribution 4.0 International Public License\n\nBy exercising the Licensed Rights (defined below), You accept and agree\nto be bound by the terms and conditions of this Creative Commons\nAttribution 4.0 International Public License (\"Public License\"). To the\nextent this Public License may be interpreted as a contract, You are\ngranted the Licensed Rights in consideration of Your acceptance of\nthese terms and conditions, and the Licensor grants You such rights in\nconsideration of benefits the Licensor receives from making the\nLicensed Material available under these terms and conditions.\n\n\nSection 1 -- Definitions.\n\n  a. Adapted Material means material subject to Copyright and Similar\n     Rights that is derived from or based upon the Licensed Material\n     and in which the Licensed Material is translated, altered,\n     arranged, transformed, or otherwise modified in a manner requiring\n     permission under the Copyright and Similar Rights held by the\n     Licensor. For purposes of this Public License, where the Licensed\n     Material is a musical work, performance, or sound recording,\n ","encoding":"utf8","key":"LICENSE","name":"LICENSE","size":18657,"truncated":true},{"bytes":"---\nlicense: cc-by-4.0\ntask_categories:\n- tabular-regression\ntags:\n- battery-hub\nbattery_hub:\n  chemistry:\n  - graphite-lfp\n  - graphite-nca\n  - graphite-nmc\n  data_type: voltage-capacity-curves\n  origin: synthetic\n  generation: mechanistic-model\n  task: degradation-mode-diagnosis\n  labels:\n  - lli\n  - lampe\n  - lamne\n  - qloss\n  operating_range:\n    rate: C/25 charge\npretty_name: Synthetic battery diagnosis\nsize_categories:\n- 1M<n<10M\nconfigs:\n- config_name: lfp\n  default: true\n  data_files:\n  - split: train\n    path: data/lfp/train/*.parquet\n  - split: test_c1\n    path: data/lfp/test_c1.parquet\n  - split: test_c2\n    path: data/lfp/test_c2.parquet\n  - split: test_c3\n    path: data/lfp/test_c3.parquet\n  - split: references\n    path: data/lfp/references.parquet\n- config_name: nca\n  data_files:\n  - split: train\n    path: data/nca/train/*.parquet\n  - split: test_c1\n    path: data/nca/test_c1.parquet\n  - split: test_c2\n    path: data/nca/test_c2.parquet\n  - split: test_c3\n    path: data/nca/test_c3.parquet\n  - split: references\n    path: data/nca/references.parquet\n- config_name: nmc\n  data_files:\n  - split: train\n    path: data/nmc/train/*.parquet\n  - split: test_c1\n    path: data/nmc/test_c1.parquet\n  - split: test_c2\n    path: data/nmc/test_c2.parquet\n  - split: test_c3\n    path: data/nmc/test_c3.parquet\n  - split: references\n    path: data/nmc/references.parquet\n---\n# Synthetic battery diagnosis\n\nSynthetic voltage-capacity curves and degradation labels for graphite/LFP, graphite/NCA and graphite/NMC.\n\n## Configurations and splits\n\nSelect `lfp`, `nca` or `nmc`. Each has `train`, `test_c1`, `test_c2`, `test_c3` and `references`.\n\n| Chemistry | Train | Each test split |\n| --- | --- | --- |\n| LFP | 705,651 | 6,000 |\n| NCA | 705,643 | 6,000 |\n| NMC | 705,382 | 6,000 |\n\n## Loading\n\n```python\nfrom datasets import load_dataset\n\nrepo = \"HNEI-PakaLi-Lab/synthetic-battery-diagnosis\"\nlfp = load_dataset(repo, \"lfp\")\ntrain = lfp[\"train\"]\ntest_c1 = lfp[\"test_c1\"]\nstream = load_dataset(repo, \"nmc\", split=\"train\", streaming=True)\n```\n\nFor local loading, replace the repository ID with this directory's absolute path. No custom loader or `trust_remote_code` is needed.\n\nThe `references` split holds the 4 pristine curves of a chemistry, one per cell configuration\n(`configuration` = C0, C1, C2, C3, in that order). Use them as the undegraded context of a cell or as\nthe baseline of any comparison against pristine:\n\n- `C0` is the pristine training curve: the one row of `train` with LLI = LAMPE = LAMNE = 0 (`curve_id` 0),\n  copied unchanged.\n- `C1`, `C2` and `C3` are the pristine curves of the cells of `test_c1`, `test_c2` and `test_c3`. They come\n  from `V_references.mat` of the test-source repository (rows 1 to 3; `source_file` and\n  `source_index_1based` say which).\n\nAll four have all labels equal to 0, `curve_id` null (C1-C3) and `duty_id_1based`/`cycle` null. They are\non the same `qnorm` grid as every other curve and keep their NaN masks (`NaN` voltage where the source\ncurve is undefined, e.g. the end of the charge).\n\n## Fields and units\n\n- `sample_id` is the original unique chemistry-scoped record ID. Training retains the `chemistry-raw-NNNNNN` format. References are `chemistry-ref-c0` to `chemistry-ref-c3`.\n- `chemistry` is `lfp`, `nca` or `nmc`.\n- `curve_id` is the original zero-based raw index within chemistry, and is null in tests.\n- `configuration` is C0 for source raw simulations, or C1/C2/C3 for tests. In `references` it is the configuration the pristine curve belongs to.\n- `source_file` and `source_index_1based` trace each record to MATLAB. Raw indices identify the within-file voltage column. Test indices identify the duty-major flattened position.\n- `duty_id_1based` and `cycle` identify test observations and are null in training.\n- `lli` is loss of lithium inventory (%).\n- `lampe` is loss of active material at the positive electrode (%).\n- `lamne` is loss of active material at the negative electrode (%).\n- `qloss` is capacity loss (%).\n- `qnorm` contains normalized-capacity percentage coordinates, not measured Ah.\n- `voltage` conta","encoding":"utf8","key":"README.md","name":"README.md","size":7180,"truncated":true},{"bytes":"{\n  \"sources\": {\n    \"lfp\": {\n      \"id\": \"bs2j56pn7y\",\n      \"doi\": {\n        \"id\": \"10.17632/bs2j56pn7y.3\",\n        \"status\": \"allocated\",\n        \"prefix\": \"10.17632\"\n      },\n      \"name\": \"Graphite//LFP synthetic V vs. Q dataset (>700,000 unique curves)\",\n      \"description\": \"This dataset contains more than 700,000 unique voltage vs. capacity curves.  It was calculated using the mechanistic modeling approach. See  \\u201cBig data training data for artificial intelligence-based Li-ion diagnosis and prognosis\\u201c  (Journal of Power Sources, Volume 479, 15 December 2020, 228806) and \\\"Analysis of Synthetic Voltage vs. Capacity Datasets for Big Data Li-ion Diagnosis and Prognosis\\\" (Energies, under review) for more details.\\n\\nThis dataset was compiled with a resolution of 0.01 for the triplets and C/25 charges. This accounts for more than 5,000 different paths. Each path was simulated with at most 0.85% increases for each degradation mode.\\n\\n4 Variables are included, see read me file for details and example how to use.\\n\",\n      \"version\": 3,\n      \"contributors\": [\n        {\n          \"profile_id\": \"da2d3d28-7f7a-318d-ac62-688bc100cac1\",\n          \"first_name\": \"Matthieu\",\n          \"last_name\": \"Dubarry\"\n        }\n      ],\n      \"publish_date\": \"2021-03-19T05:22:08.478Z\",\n      \"data_licence\": {\n        \"id\": \"01d9c749-3c4d-4431-9df3-620b2dcfe144\",\n        \"description\": \"You can share, copy and modify this dataset so long as you give appropriate credit, provide a link to the CC BY license, and indicate if changes were made, but you may not do so in a way that suggests the rights holder has endorsed you or your use of the dataset. Note that further permission may be required for any content within the dataset that is identified as belonging to a third party.\",\n        \"url\": \"http://creativecommons.org/licenses/by/4.0\",\n        \"category\": \"Creative\",\n        \"short_name\": \"CC BY 4.0\",\n        \"full_name\": \"Creative Commons Attribution 4.0 International\"\n      }\n    },\n    \"nca\": {\n      \"id\": \"2h8cpszy26\",\n      \"doi\": {\n        \"id\": \"10.17632/2h8cpszy26.1\",\n        \"status\": \"allocated\",\n        \"prefix\": \"10.17632\"\n      },\n      \"name\": \"Graphite//NCA synthetic V vs. Q & duty cycle datasets\",\n      \"description\": \"These datasets were calculated using the mechanistic modeling approach. See  \\u201cBig data training data for artificial intelligence-based Li-ion diagnosis and prognosis\\u201c  (Journal of Power Sources, Volume 479, 15 December 2020, 228806) and \\\"Analysis of Synthetic Voltage vs. Capacity Datasets for Big Data Li-ion Diagnosis and Prognosis\\\" (Energies, under review) for more details\\n\\nThe V vs. Q dataset (Gr-NCA_Co33_cha_n) was compiled with a resolution of 0.01 for the triplets and C/25 charges. This accounts for more than 5,000 different paths. \\nEach path was simulated with at most 0.85% increases for each. The dataset contains more than 700,000 unique voltage vs. capacity curves. \\n4 Variables are included, see corresponding read me file for details and example how to use.\\n\\nThe duty cycle dataset is composed of close to 125,000 duty cycles with one voltage curve at most every 200 cycles (one every 10 cycles for cycles 1-200).\\n15 variables are included in the duty cycle dataset (Gr-NCA_Co33_cha_124652duty).  See corresponding read me file for details and example how to use.\",\n      \"version\": 1,\n      \"contributors\": [\n        {\n          \"profile_id\": \"da2d3d28-7f7a-318d-ac62-688bc100cac1\",\n          \"first_name\": \"Matthieu\",\n          \"last_name\": \"Dubarry\"\n        }\n      ],\n      \"publish_date\": \"2021-03-19T05:16:57.546Z\",\n      \"data_licence\": {\n        \"id\": \"01d9c749-3c4d-4431-9df3-620b2dcfe144\",\n        \"description\": \"You can share, copy and modify this dataset so long as you give appropriate credit, provide a link to the CC BY license, and indicate if changes were made, but you may not do so in a way that suggests the rights holder has endorsed you or your use of the dataset. Note that further permission may be required for any content within the dataset that is identified as bel","encoding":"utf8","key":"metadata.json","name":"metadata.json","size":140178,"truncated":true}],"sourceObjectKey":"data/lfp/references.parquet","starterCell":"from datasets import load_dataset\nds = load_dataset(\"HNEI-PakaLi-Lab/synthetic-battery-diagnosis\")\nprint(ds)","starterSamplePath":"data/lfp/references.parquet","totalObjects":108},"summary":"Synthetic voltage versus capacity curves for lithium-ion battery degradation-mode diagnosis, released by the PakaLi lab at the Hawaii Natural Energy Institute (HNEI).","title":"Synthetic Li-ion Voltage-Capacity Curves with Degradation-Mode Labels (Graphite/LFP, NCA, NMC)","updatedAt":"2026-11-18T03:50:39.620Z","visibility":"public","websiteUrl":"https://huggingface.co/datasets/HNEI-PakaLi-Lab/synthetic-battery-diagnosis"}}