Satlas Renewable Energy Infrastructure: Onshore Wind Turbine Points and Solar Farm Polygons from Sentinel-2, 2016 Onward (Ai2)
- Provider
- Allen Institute for AI (Ai2)
- License
- ODC-By-1.0 (source)
- Stored at
- Google Cloud Storage, gs://satlas-explorer-public/outputs/renewable (us)
- Access
- Free and public. No account with the data provider is needed.
- Category
- Energy
- Source
- https://github.com/allenai/satlas
About this dataset
Satlas Renewable Energy Infrastructure maps onshore wind turbines (points) and solar farms (polygons) worldwide, detected by Ai2's deep learning models in Sentinel-2 satellite imagery at 10 m per pixel. Each feature carries a category attribute, wind_turbine or solar_farm. The outputs/renewable/ folder holds dated snapshots starting in January 2016, each as YYYY-MM.geojson and YYYY-MM.kml plus separate shapefiles for wind turbines (YYYY-MM_wind.shp) and solar farms (YYYY-MM_solar.shp), along with latest.* files, an index.txt of every file with hash and modification time, and renewable.geojson, a combined file whose start and end attributes record when each installation appeared or was removed (solar farms are less accurate in that combined form because they are split where parts were built at different times). Snapshots are refreshed as new imagery arrives and earlier months can be revised. Use it to measure the growth of wind and photovoltaic capacity by country, study land use by renewable energy, or train detectors. Read with GeoPandas, GDAL/OGR or any GIS. License: ODC-By (Open Data Commons Attribution). Cite Satlas, Allen Institute for AI (satlas.allen.ai).
How to access this dataset in Python
import gcsfs
fs = gcsfs.GCSFileSystem(token='anon')
fs.ls('satlas-explorer-public/outputs/renewable/', detail=False)[:10]Lists the files with anonymous access. Runs on any machine, with no cloud account.
Data structure
Files
Example file: outputs/renewable/2016-01.geojson
Analyze this dataset without downloading it
On Scigantic, Satlas Renewable Energy Infrastructure: Onshore Wind Turbine Points and Solar Farm Polygons from Sentinel-2, 2016 Onward (Ai2) opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.
This page is also available as Markdown and as JSON.
Related Energy datasets
- Imperial College LG M50T 21700 Silicon-Graphite Degradation Data: Rapid Loss of Active Silicon (Kirkaldy et al., bsebench copy)
- DOE Geothermal Data Repository: Soda Lake Geothermal: Raw 3D and 3C Seismic-Reflection Data from 2010 Survey
- Seoul National University Markov-Chain User-Profile Cycling Data: 130 VTC6 and Samsung 25R Cells for RUL Prediction (bsebench copy)
- Beijing Institute of Technology (BIT) AESA Battery Degradation Dataset: 77 18650 Li-ion Cells under Fixed and Arbitrary-Use Current Profiles (bsebench copy)
- Tongji-KIT Voltage Relaxation Dataset: Capacity Estimation of Commercial NCA, NCM and NCM+NCA 18650 Cells (Zhu et al., bsebench copy)
- HNEI Benchmark Relaxation Dataset for Commercial NMC811 and LFP Cells
- OPFData (GridOpt) Release 1: 300k Solved AC Optimal Power Flow Problems per PGLib Grid with Load Perturbations
- The MIT Supercloud Dataset