{"success":true,"data":{"author":"Nascetti et al. (BioMassters); re-packaged by IBM-NASA Geospatial and Clark University for Prithvi","bucketAccessType":"public","bucketName":"ibm-nasa-geospatial/BioMassters","bucketPrefix":"","category":"Earth Observation & Geospatial","cloudProvider":"huggingface","createdAt":"2026-11-14T01:01:18.736Z","description":"Sentinel-1 synthetic aperture radar (SAR) and Sentinel-2 multispectral (MSI) imagery of Finnish forests for 2016 to 2021, paired with 11,462 reference maps of aboveground biomass (AGB) derived from airborne LiDAR calibrated with in-situ forest inventory. Each reference patch covers 2,560 by 2,560 m at 256 by 256 pixels and comes with one image per month for the 12 months before the AGB observation: Sentinel-1 for every month, Sentinel-2 (10 bands plus cloud probability) where available. This copy keeps the original BioMassters (NeurIPS 2023 Datasets and Benchmarks) layout and adds biomassters_chip_tracker.csv with cloud_percentage, corrupt_values, red_mean and an 80/20 train/validation split, used to train the Prithvi geospatial foundation model. Listing the root (measured 2026-11-13) shows train_features as a 14-part split zip (thirteen 10.7 GB .z01 to .z13 parts plus train_features.zip), test_features_splits as a 5-part split zip, train_agbm.zip (0.58 GB), test_agbm.tar (0.73 GB) and feature and AGB metadata CSVs; about 201 GB in all. Rejoin the split zips before extracting, then read the image chips with rasterio or xarray. Released under CC-BY-4.0; cite the BioMassters paper.","displayTitle":"BioMassters: Forest Aboveground Biomass from Sentinel-1 and Sentinel-2 Time Series","id":"4ddb2e42-a07b-5c80-8c8b-9f50a61fe148","license":"CC-BY-4.0","licenseEvidenceUrl":"https://proceedings.neurips.cc/paper_files/paper/2023/file/40daf2a00278c4bea1b26cd4c8a654f8-Paper-Datasets_and_Benchmarks.pdf","objectCountEstimate":27,"probeStatus":"ok","referenceUrl":"https://proceedings.neurips.cc/paper_files/paper/2023/file/40daf2a00278c4bea1b26cd4c8a654f8-Paper-Datasets_and_Benchmarks.pdf","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"ibm-nasa-geospatial/BioMassters\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"ibm-nasa-geospatial/BioMassters\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=ibm-nasa-geospatial, license:cc-by-4.0, size_categories:100K<n<1M, downloads=803"],"format":"mixed","generatedAt":"2026-11-14T01:01:19.494Z","layout":{"example":"The_BioMassters_-_features_metadata.csv.csv","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"filename,chip_id,satellite,split,month,size,cksum,s3path_us,s3path_eu,s3path_as,corresponding_agbm\n0003d2eb_S1_00.tif,0003d2eb,S1,train,September,1049524,3953454613,s3://drivendata-competition-biomassters-public-us/train_features/0003d2eb_S1_00.tif,s3://drivendata-competition-biomassters-public-eu/train_features/0003d2eb_S1_00.tif,s3://drivendata-competition-biomassters-public-as/train_features/0003d2eb_S1_00.tif,0003d2eb_agbm.tif\n0003d2eb_S1_01.tif,0003d2eb,S1,train,October,1049524,3531005382,s3://drivenda","encoding":"utf8","key":"The_BioMassters_-_features_metadata.csv.csv","truncatedAt":512}],"sampleObjects":["Data_specifications.png","The_BioMassters_-_features_metadata.csv.csv","The_BioMassters_-_train_agbm_metadata.csv.csv","biomassters_chip_tracker.csv","test_agbm.tar"],"sidecars":[{"bytes":"---\nlicense: cc-by-4.0\nlanguage:\n- en\ntags:\n- climate\npretty_name: BioMassters\nsize_categories:\n- 100K<n<1M\n---\n# Dataset Card for BioMassters for Global Prithvi\n\n## Dataset Description\n\nCopied from BioMassters: A Benchmark Dataset for Forest Biomass Estimation using Multi-modal Satellite Time-series https://nascetti-a.github.io/BioMasster/\n\n- **Original Dataset: https://huggingface.co/datasets/nascetti-a/BioMassters**\n- **Point of Contact For Updated Dataset: Denys Godwin (dgodwin@clarku.edu)**\n\n### Dataset Summary\n\nThis dataset contains Sentinel-1 SAR and Sentinel-2 MSI imagery of Finnish forests for the years 2016-2021. There are 11,462 reference images of Above Ground Biomass (AGB). Each reference AGB has corresponding S1 and S2 imagery for the 12 months leading up to the AGB observation. Sentinel-1 data exists for each of the 12 months, while Sentinel-2 data does not have full temporal coverage. All imagery has height and width of 256x256.\n\n### Modifications for Prithvi\n\nThe directory structure of the dataset has been preserved. However, to enable the filtering needed for Prithvi training, some chip metadata has been calculated and stored in biomassters_chip_tracker.csv. Additional metadata are as follows:\n\n- cloud_percentage: the percentage of clouds, defined as pixels where the cloud probability band of the input image exceeds 70\n- corrupt_values: boolean representing whether there are corrupt values in the image. These are defined as blocks of identical values, which are present in some images\n- red_mean: the mean value of the red band (band 3) of the Sentinel-2 image, used to filter scenes with anomalously high reflectance due to snow and Top of Atmosphere (ToA) correction issues\n\n### Data Splits\n\nTraining and testing splits are as given by The BioMassters original dataset. The training dataset has been further randomly split into training (80%) and validation (20%) sets. These are tracked in the 'split' column of the biomassters_chip_tracker.csv\n\n### Reference data: \n* Reference AGB measurements were collected using LiDAR (Light Detection and Ranging) calibrated with in-situ measurements.\n* Total 11,462 patches, each patch covering 2,560 by 2,560 meter area.\n\n### Feature data: \n* Sentinel-1 SAR and Sentinel-2 MSI data\n* 12 months of data (1 image per month)\n* Sentinel-2 data does not exist for all months for all scenes\n* Sentinel-2 data contains 10 selected spectral bands and 1 band of cloud probability\n\n### Dataset Specification\n\n![img](./Data_specifications.png)\n\n### Data Size:\n\n```\n  dataset         | # files  | size\n  --------------------------------------\n  train_features  |  189078  | 215.9GB\n  test_features   |   63348  |  73.0GB\n  train_agbm      |    8689  |   2.1GB\n  test_agbm       |    2773  |   705MB\n```\n\n## Citation : under review\n","encoding":"utf8","key":"README.md","name":"README.md","size":2805,"truncated":false}],"sourceObjectKey":"The_BioMassters_-_features_metadata.csv.csv","starterCell":"import pandas as pd\ndf = pd.read_csv(\"hf://datasets/ibm-nasa-geospatial/BioMassters/The_BioMassters_-_features_metadata.csv.csv\")\ndf.head()","starterSamplePath":"Data_specifications.png","totalObjects":27},"summary":"Sentinel-1 synthetic aperture radar (SAR) and Sentinel-2 multispectral (MSI) imagery of Finnish forests for 2016 to 2021, paired with 11,462 reference maps of aboveground biomass…","title":"BioMassters: Forest Aboveground Biomass from Sentinel-1 and Sentinel-2 Time Series","updatedAt":"2026-11-14T02:46:36.618Z","visibility":"public","websiteUrl":"https://nascetti-a.github.io/BioMasster/"}}