Photo by Shubham Dhage on Unsplash

PALSAR-2 ScanSAR CARD4L (L2.2) Dataset for Machine Learning

Install DagsHub:

pip install dagshub
Click on copy button to copy content

To stream this data directly on DagsHub

from dagshub.streaming import DagsHubFilesystem

fs = DagsHubFilesystem(".", repo_url="https://dagshub.com/DagsHub-Datasets/jaxa-alos-palsar2-scansar-dataset")

fs.listdir("s3://jaxaalos2/palsar2/L2.2/Africa/")
Click on copy button to copy content

Description

The 25 m PALSAR-2 ScanSAR is normalized backscatter data of PALSAR-2 broad area observation mode with observation width of 350 km. The SAR imagery was ortho-rectificatied and slope corrected using the ALOS World 3D – 30 m (AW3D30) Digital Surface Model. Polarization data are stored as 16-bit digital numbers (DN). The DN values can be converted to gamma naught values in decibel unit (dB) using the following equation: γ0 = 10*log10(DN2) – 83.0 dB CARD4L stands for CEOS Analysis Ready Data for Land (Level 2.2) data are ortho-rectified and radiometrically terrain-corrected. This dataset is compatible with the Committee on Earth Observation (CEOS) Analysis Ready Data for LAND (CARD4L) standard.

Additional information

Update frequency

Every month after 42 days observed

License

Data is available for free under the terms of use.

Related datasets

BodyM Dataset

Cloud to Street – Microsoft Flood and Clouds Dataset

A2D2: Audi Autonomous Driving Dataset

Galaxy Evolution Explorer Satellite (GALEX)

Launch your ML development to new heights with DagsHub

Back to top