<- Back to Datasets

CloudCast

A large-scale dataset and baseline for forecasting clouds

CloudCast

The CloudCast dataset contains 70080 images with 11 different cloud types for multiple layers of the atmosphere annotated on a pixel level. The dataset has a spatial resolution of 928 x 1530 pixels recorded with 15-min intervals for the period 2017-2018, where each pixel represents an area of 3Ă—3 km.To enable standardized datasets for benchmarking computer vision methods, we include a full-resolution dataset centered and projected dataset over Europe (728Ă—728). To support small-scale experiments and analysis, we also include a downsampled low-resolution dataset 128Ă—128 (15Ă—15 km), which is significantly smaller in size compared to the full dataset.

View this Dataset
->
Aarhus University
View author website
Task
Remote Sensing
Annotation Types
3D Point Cloud
70080
Items
11
Classes
70080
Labels
Models using this dataset
Last updated on 
July 14, 2022
Licensed under 
CC-BY-NC-SA
Gain control of your training data
15,000+ ML engineers can’t be wrong