Datasets:

allenai

/

s2-naip

like 2

NAIP-S2 is a super-resolution dataset for remote sensing consisting of paired NAIP and Sentinel-2 images in the continental US.

Data is divided into tiles. Each tile spans 512x512 pixels at 1.25 m/pixel in a UTM projection. At each tile, the following data is available:

• NAIP: an image from 2019-2021 at 1.25 m/pixel (512x512).
• Sentinel-2: between 16 and 32 images captured within a few months of the NAIP image at 10 m/pixel (64x64).
• Sentinel-1: 4 images captured in the same year as the NAIP image at 10 m/pixel (64x64).
• Landsat: 4 images captured in the same year as the NAIP image at 10 m/pixel (64x64).
• OpenStreetMap: a GeoJSON containing buildings, roads, and 30 other categories. It uses pixel coordinates relative to the 512x512 NAIP image.
• WorldCover: the 2021 land cover image at 10 m/pixel (64x64).

Structure

Once extracted, the dataset contains the different data types in different folders. Each folder contains files named by a tile ID, which consists of the UTM projection, column, and row. The column and row are based on tiles that are 512x512 pixels with pixel coordinates at 1.25 m/pixel, e.g. 32612_960_-6049.png spans (614400, -3871360) to (615040, -3870720) in projection units.

Here is an example of NAIP data:

naip/
    32612_960_-6049.png
    32612_960_-6050.png
    32612_960_-6051.png
    ...

And an example of Sentinel-2 data:

sentinel2/
    32612_960_-6049_16.tif
    32612_960_-6049_32.tif
    32612_960_-6049_8.tif
    32612_960_-6050_16.tif
    ...

Note that the Sentinel-2 images are GeoTIFFs so they contain georeference metadata. Furthermore, the 10 m/pixel (_8.tif), 20 m/pixel (_16.tif), and 60 m/pixel (_32.tif) bands are stored separately.