104 datasets found

The Sentinel-2 Imagery dataset provides agriculture imagery for the contiguous U.S. continent from 2017 to 2022.

The USDA Crop Dataset and HRRR Computed Dataset are used for predicting crop yields at the county level across the United States.

Remote sensing image-text retrieval dataset

Remote sensing image-text retrieval dataset

The RSICD dataset is a benchmark remote sensing text-image dataset. It contains a total of 10921 aerial remote sensing images with various resolutions collected from Google...

The RSI-CB dataset is a dataset of satellite images, where each image is classified into one of 10 categories.

The AutoIce competition dataset is a benchmark for automatic sea ice concentration charting. It provides a dataset for training and testing sea ice classification models.

The AI4Arctic Sea Ice Challenge Dataset is a benchmark for deep learning-based sea ice mapping. It provides a large-scale dataset for training and testing sea ice classification...

Landsat dataset

National Land Cover Database (NLCD) dataset

National Agriculture Imagery Program (NAIP) dataset

Land cover change detection dataset for the 2021 IEEE GRSS Data Fusion Contest

The Cropland Data Layer (CDL) is a raster, geo-referenced, crop-specific land cover map.

The CalCrop21 dataset is a georeferenced multi-spectral dataset of satellite imagery and crop labels.

LEVIR-CD and SYSU-CD datasets for remote sensing change detection and urban prediction tasks

Crop yield forecasting plays a significant role in addressing growing concerns about food security and guiding decision-making for policymakers and farmers. The dataset is used...

BigEarthNet is a large-scale Sentinel-2 dataset collected from a total of 125 Sentinel-2 tiles covering areas of 10 countries in Europe. The dataset was prepared with data from...

LEVIR-CD is a public large-scale remote sensing Building Change Detection dataset consisting of 637 VHR image patch pairs with a size of 1024 × 1024 pixels.

WHU-CD is a public remote sensing Building Change Detection dataset with 1260 training images and 690 images.

Very-high-resolution remote sensing (RS) image change detection (CD) has been a challenging task for its very rich spatial information and sample imbalance problem.