{"success":true,"data":{"author":"NASA-IBM AI4Science (Surya / SuryaBench team)","bucketAccessType":"public","bucketName":"nasa-ibm-ai4science/ar_emergence","bucketPrefix":"","category":"Astronomy & Space","cloudProvider":"huggingface","createdAt":"2026-11-16T02:38:29.715Z","description":"A dataset for early detection and forecasting of solar active region (AR) emergence, released in the NASA-IBM SuryaBench collection. For 59 large ARs that emerged on the visible disk between 2010 and 2023, a 30 x 30 degree patch is tracked over several days before, during and after emergence using SDO Helioseismic and Magnetic Imager (HMI) data: acoustic power maps computed from Doppler velocity in four frequency bands (2-3, 3-4, 4-5 and 5-6 mHz, from local helioseismology), photospheric magnetic flux and continuum intensity, each averaged onto a 9 x 9 grid at 1-hour cadence, giving a (6, 240, 9, 9) array per instance. data.zip holds one AR{NOAA number}/ folder per region with mean_pmdop, mean_mag and mean_int NPZ timelines; train.csv (37 ARs), valid.csv (9) and test.csv (13) list NOAA numbers, tracking start and end times and file paths. These products have been used to train models that forecast emergence from pre-emergence acoustic power signatures, a space weather early-warning problem. About 23 MB; read with NumPy and pandas. CC-BY-4.0 as stated in the card.","displayTitle":"SuryaBench Active Region Emergence: SDO/HMI Acoustic Power, Magnetic Flux and Intensity Timelines for 59 Emerging Active Regions","id":"86830a21-e068-592b-9fb2-a7c44ca76031","license":"CC-BY-4.0","licenseEvidenceUrl":"https://huggingface.co/datasets/nasa-ibm-ai4science/ar_emergence","objectCountEstimate":6,"probeStatus":"ok","referenceUrl":"https://github.com/NASA-IMPACT/Surya","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"nasa-ibm-ai4science/ar_emergence\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"nasa-ibm-ai4science/ar_emergence\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=nasa-ibm-ai4science, license:cc-by-4.0, size_categories:n<1K, format:csv, downloads=88"],"format":"mixed","generatedAt":"2026-11-16T02:38:35.259Z","layout":{"example":"test.csv","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"AR,t_start,t_end,mean_int_path,mean_mag_path,mean_pmdop_path\r\n12778,2020.10.27_00:00:00Z,2020.11.01_00:00:00Z,/data/AR12778/mean_int12778_flat.npz,/data/AR12778/mean_mag12778_flat.npz,/data/AR12778/mean_pmdop12778_flat.npz\r\n12864,2021.09.04_00:00:00Z,2021.09.12_00:00:00Z,/data/AR12864/mean_int12864_flat.npz,/data/AR12864/mean_mag12864_flat.npz,/data/AR12864/mean_pmdop12864_flat.npz\r\n12877,2021.09.27_00:00:00Z,2021.10.04_00:00:00Z,/data/AR12877/mean_int12877_flat.npz,/data/AR12877/mean_mag12877_flat.npz,/dat","encoding":"utf8","key":"test.csv","truncatedAt":512}],"sampleObjects":["data.zip","test.csv","train.csv","validation.csv"],"sidecars":[{"bytes":"---\nlicense: cc-by-4.0\ntags:\n- heliophysics\n- solar_active_regions\n- AR_emergence\n- space_weather\n- machine_learning\nsize_categories:\n- n<1K\nconfigs:\n- config_name: default\n  default: true\n  data_files:\n  - split: train\n    path: train.csv\n  - split: validation\n    path: validation.csv\n  - split: test\n    path: test.csv\npretty_name: Active Region Emergenc\n---\n\n# Active Region Emergence Dataset  \n\n## Dataset Summary\n\nThe **Active Region Emergence Dataset** is designed to support research on the early detection of solar Active Regions (ARs) and the development of predictive models for space weather. By characterizing the evolution of ARs before, during, and after their emergence, the dataset enables studies of pre-emergence signatures and early warning methods.  \n\nThis dataset is derived from NASA’s **Solar Dynamics Observatory (SDO)** using measurements from the **Helioseismic and Magnetic Imager (HMI)**. It includes timeline data of:  \n\n- **Acoustic power** (from Doppler velocity maps)  \n- **Photospheric magnetic field**  \n- **Continuum intensity**  \n\nfor **59 large ARs** that emerged on the visible solar disk between **2010 and 2023**. Each AR is tracked within a **30° × 30° patch** over multiple days.  \n\nThese data products have already been applied successfully in machine learning models for AR emergence forecasting in [1].  \n\n## Supported Tasks and Applications\n- **Spatio-temporal Forecasting**: Forecasting the spatially resolved emergence characteristics of active regions.\n\n\n## Data Structure\n\n### Data Files\n\nThe repository contains csv files containing paths and compressed data files for emergence characteristics.\nThe dataset is split for consistent training, validation and testing. \n- `train.csv` — training split (37 ARs)  \n- `valid.csv` — validation split (9 ARs)  \n- `test.csv` — test split (13 ARs)  \n- `README.md` — dataset description  \n\n- `data.zip` — compressed folder containing all Active Region (AR) subfolders:  \n  - `AR{noaa_num}/`  \n    - `mean_int{noaa_num}_flat.npz` → continuum intensity timeline  \n    - `mean_mag{noaa_num}_flat.npz` → magnetic field timeline  \n    - `mean_pmdop{noaa_num}_flat.npz` → 4 acoustic power timeline (2–3, 3–4, 4–5, 5–6 mHz).\n      - Index 0: 2-3 mHz\n      - Index 1: 3-4 mHz\n      - Index 2: 4-5 mHz\n      - Index 3: 5-6 mHz\nwhere `noaa_num` is the NOAA Active Region Number for the active regions in this dataset.  \n\n### Features\n\nCSV files include following features:\n- **`AR`**: NOAA Active Region number  \n- **`t_start`**: Start time of tracked patch  \n- **`t_end`**: End time of tracked patch  \n- **`mean_int_path`**: Path to continuum intensity `.npz` file \n- **`mean_mag_path`**: Path to magnetic field `.npz` file  \n- **`mean_pmdop_path`**: Path to acoustic power `.npz` file \n\n## Dataset Details\n\n| Field | Description |\n|------------------------|---------------------------------------------|\n| **Temporal Coverage** | 2010 – 2023 |\n| **Data Format** | CSV for metadata / NPZ for rasters |\n| **Data Size** | Total 59 instances |\n| **Total File Size** | ~23.1 MB |\n| **Data Shape** | (6, 240, 9, 9) per instance |\n| **Cadence** | 1 hour |\n\n\n## Example Usage  \n\n```python\nimport numpy as np\nimport pandas as pd\n\n# Load CSV metadata\ndf = pd.read_csv(\"train.csv\")\nprint(df.head())\n\n# Load one AR’s power map dopplergram data\n# for intensity and magnetic flux use mean_int_path and mean_mag_path column names on df\nsample_path = df.iloc[0][\"mean_pmdop_path\"]\n\n# Update to local path after unzipping data.zip\nsample_path = sample_path.replace(\"/data\", \"data\")  \n\ndata = np.load(sample_path)\nprint(\"Keys in npz file:\", data.files)\nprint(\"Data shape:\", data[data.files[0]].shape)\n\n```\n\n## License\nThis dataset is licensed under the Creative Commons Attribution 4.0 International (CC BY 4.0) License.\n\n## Contact\n[1] Spyros Kasapis [skasapis@princeton.edu](mailto:skasapis@princeton.edu)\n\n## References\n[1] Kasapis, S., Kitiashvili, I. N., Kosovichev, A. G. & Stefan, J. T. Prediction of intensity variations associated with emerging active regions using helioseismic power maps ","encoding":"utf8","key":"README.md","name":"README.md","size":4179,"truncated":true}],"sourceObjectKey":"test.csv","starterCell":"import pandas as pd\ndf = pd.read_csv(\"hf://datasets/nasa-ibm-ai4science/ar_emergence/test.csv\")\ndf.head()","starterSamplePath":"test.csv","totalObjects":6},"summary":"A dataset for early detection and forecasting of solar active region (AR) emergence, released in the NASA-IBM SuryaBench collection.","title":"SuryaBench Active Region Emergence: SDO/HMI Acoustic Power, Magnetic Flux and Intensity Timelines for 59 Emerging Active Regions","updatedAt":"2026-11-16T17:10:07.942Z","visibility":"public","websiteUrl":"https://huggingface.co/datasets/nasa-ibm-ai4science/ar_emergence"}}