GTA-UAV dataset provides a large continuous area dataset (covering 81.3km²) for UAV visual geo-localization, expanding the previously aligned drone-satellite pairs to arbitrary drone-satellite pairs to better align with real-world application scenarios. Our dataset contains:

33,763 simulated drone-view images, from multiple altitudes (80-650m), multiple attitudes, multiple scenes (urban, mountain, coast, forest, etc.).

14,640 tiled satellite-view images from 4 zoom levels for arbitrarily pairing.

Overlap (in IoU) of FoV for each drone-satellite pair.

Drone (camera) 6-DoF labels for each drone image.

LandCoverNet is a global annual land cover classification training dataset with labels for the multi-spectral satellite imagery from Sentinel-1, Sentinel-2 and Landsat-8 missions in 2018. LandCoverNet Asia contains data across Asia, which accounts for ~31% of the global dataset. Each pixel is identified as one of the seven land cover classes based on its annual time series. These classes are water, natural bare ground, artificial bare ground, woody vegetation, cultivated vegetation, (semi) natural vegetation, and permanent snow/ice.
There are a total of 2753 image chips of 256 x 256 pixels in LandCoverNet South America V1.0 spanning 92 tiles. Each image chip contains temporal observations from the following satellite products with an annual class label, all stored in raster format (GeoTIFF files):
* Sentinel-1 ground range distance (GRD) with radiometric calibration and orthorectification at 10m spatial resolution
* Sentinel-2 surface reflectance product (L2A) at 10m spatial resolution
* Landsat-8 surface reflectance product from Collection 2 Level-2

Radiant Earth Foundation designed and generated this dataset with a grant from Schmidt Futures with additional support from NASA ACCESS, Microsoft AI for Earth and in kind technology support from Sinergise.

LandCoverNet is a global annual land cover classification training dataset with labels for the multi-spectral satellite imagery from Sentinel-1, Sentinel-2 and Landsat-8 missions in 2018. LandCoverNet North America contains data across North America, which accounts for ~13% of the global dataset. Each pixel is identified as one of the seven land cover classes based on its annual time series. These classes are water, natural bare ground, artificial bare ground, woody vegetation, cultivated vegetation, (semi) natural vegetation, and permanent snow/ice.

There are a total of 1561 image chips of 256 x 256 pixels in LandCoverNet North America V1.0 spanning 40 tiles. Each image chip contains temporal observations from the following satellite products with an annual class label, all stored in raster format (GeoTIFF files):
* Sentinel-1 ground range distance (GRD) with radiometric calibration and orthorectification at 10m spatial resolution
* Sentinel-2 surface reflectance product (L2A) at 10m spatial resolution
* Landsat-8 surface reflectance product from Collection 2 Level-2

Radiant Earth Foundation designed and generated this dataset with a grant from Schmidt Futures with additional support from NASA ACCESS, Microsoft AI for Earth and in kind technology support from Sinergise.

Labeled RGB image data of both real world and synthetic environments of orbital;/space platforms for the purposes of supervised machine learning training to enable autonomous robotic tasking.

Automatic, accurate crop type maps can provide unprecedented information for understanding food systems, especially in developing countries where ground surveys are infrequent. However, little work has applied existing methods to these data scarce environments, which also have unique challenges of irregularly shaped fields, frequent cloud coverage, small plots, and a severe lack of training data. To address this gap in the literature, we provide the first crop type semantic segmentation dataset of small holder farms, specifically in Ghana and South Sudan. We are also the first to utilize high resolution, high frequency satellite data in segmenting small holder farms.

The dataset includes time series of satellite imagery from Sentinel-1, Sentinel-2, and PlanetScope satellites throughout 2016 and 2017. For each tile/chip in the dataset, there are time series of imagery from each of the satellites, as well as a corresponding label that defines the crop type at each pixel. The label has only one value at each pixel location, and assumes that the crop type remains the same across the full time span of the satellite image time series. In many cases where ground truth was not available, pixels have no label and are set to a value of 0.

This chipped training dataset is over N'Djamena and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 2 dataset, meaning it has NOT been thoroughly reviewed and improved. This dataset was produced for the ramp project and contains 3,044 tiles and 124,208 individual buildings. The satellite imagery resolution is 45 cm and was sourced from Maxar ODP (10300100AA405C00). Dataset keywords: Urban, Peri-urban, Rural

This chipped training dataset is over Manjama and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 1 dataset, meaning it has been thoroughly reviewed and improved. This dataset was used in developing the ramp baseline model and contains 4,671 tiles and 60,379 individual buildings. The satellite imagery resolution is 30 cm and was sourced from Maxar ODP (1040010056B6FA00). Dataset keywords: Urban, Peri-Urban.

This chipped training dataset is over Mesopotamia and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 1 dataset, meaning it has been thoroughly reviewed and improved. This dataset was used in developing the ramp baseline model and contains 3,013 tiles and 33,139 individual buildings. The satellite imagery resolution is 40 cm and was sourced from Maxar ODP (10500100236CC900). Dataset keywords: Coastal, Urban, Peri-urban.

This chipped training dataset is over Hpa-an and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 1 dataset, meaning it has been thoroughly reviewed and improved. This dataset was used in developing the ramp baseline model and contains 3,667 tiles and 44,765 individual buildings. The satellite imagery resolution is 35 cm and was sourced from Maxar ODP (1040010033320500). Dataset keywords: Urban, Peri-Urban, River.

This chipped training dataset is over Wa and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 1 dataset, meaning it has been thoroughly reviewed and improved. This dataset was used in developing the ramp baseline model and contains 7,615 tiles and 68,072 individual buildings. The satellite imagery resolution is 32 cm and was sourced from Maxar ODP (1040010056B6FA00). Dataset keywords: Urban, Peri-urban

This chipped training dataset is over Mzuzu and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 1 dataset, meaning it has been thoroughly reviewed and improved. This dataset was used in developing the ramp baseline model and contains 3,357 tiles and 91,391 individual buildings. The satellite imagery resolution is 45 cm and was sourced from Maxar ODP (10500100195A6700). Dataset keywords: Urban, Peri-Urban, Dense.

This chipped training dataset is over Sylhet and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 2 dataset, meaning it has NOT been thoroughly reviewed and improved. This dataset was produced for the ramp project and contains 16,217 tiles and 135,375 individual buildings. The satellite imagery resolution is 30 cm and was sourced from Maxar ODP 2022 imagery release for a Bangladesh flood event. Dataset keywords: Peri-urban, Rural, River, Agricultural

This chipped training dataset is over Nairobi and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 2 dataset, meaning it has NOT been thoroughly reviewed and improved. This dataset was produced for the ramp project and contains 1,195 tiles and 24,707 individual buildings. The satellite imagery resolution is 30 cm and was sourced from Maxar ODP (KE_Nairobi_19Q2_V0_R3C2). Dataset keywords: Urban, Peri-urban, Rural

This chipped training dataset is over Chittagong and parts of the Kutupalong Refugee Camp and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 1 dataset, meaning it has been thoroughly reviewed and improved. This dataset was used in the development and testing of a localized ramp model and contains 5,229 tiles and 38,096 individual buildings. The satellite imagery resolution is 40 cm and was sourced from Maxar ODP (105001001AC98900). Dataset keywords: Agricultural, Peri-urban, Refugee Camp, Rural