NAIP-S2 is a super-resolution remote sensing dataset released by the Allen Institute for Artificial Intelligence, which contains paired NAIP and Sentinel-2 images over the continental United States.

The dataset is organized in tiles of 512×512 pixels, with a pixel resolution of 1.25 meters/pixel and UTM projection. Each tile integrates multi-source data including NAIP, Sentinel-2, Sentinel-1, Landsat, OpenStreetMap and WorldCover. After the dataset is decompressed, different types of data are stored in different folders. Each folder contains files named with tile ID, which consists of UTM projection, columns and rows. The NAIP-S2 dataset has a wide range of applications in remote sensing science, especially in surface monitoring, resource management and environmental change assessment, providing high-precision data support.