The CCSN dataset contains 2543 cloud images. According to the World Meterological Organization’s genera-based classification recommendation, we divide into 11 different categories： Ac, Sc, Ns, Cu, Ci, Cc, Cb, As, Ct, Cs, St. It is worth noting that contrails have consideration in our dataset. Representative sample images from each category are shown below. Ci = cirrus; Cs = cirrostratus; Cc = cirrocumulus; Ac = altocumulus; As = altostratus; Cu = cumulus; Cb = cumulonimbus; Ns = nimbostratus; Sc = stratocumulus; St = stratus; Ct = contrail.
All images are fixed resolution 256×256 pixels with the JPEG format. This dataset can be downloaded from this link https://doi.org/10.7910/DVN/CADDPD.
If you interest about this database, please fill out this form or this to receive the download instructions.
More details about the CCSN dataset can be found in the following paper and please cite the this paper if you use the CCSN dataset.
Zhang, J. L., Liu, P., Zhang, F., & Song, Q. Q. ( 2018). CloudNet: Ground‐based cloud classification with deep convolutional neural network. Geophysical Research Letters, 45, 8665– 8672. https://doi.org/10.1029/2018GL077787
- BibTex
@article{doi:10.1029/2018GL077787,
author = {Zhang, Jinglin and Liu, Pu and Zhang, Feng and Song, Qianqian},
title = {CloudNet: Ground-Based Cloud Classification With Deep Convolutional Neural Network},
journal = {Geophysical Research Letters},
volume = {45},
number = {16},
pages = {8665-8672},
keywords = {convolutional neural networks, CCSN database, ground-based cloud classification, CloudNet},
doi = {10.1029/2018GL077787},
url = {https://agupubs.onlinelibrary.wiley.com/doi/abs/10.1029/2018GL077787},
eprint = {https://agupubs.onlinelibrary.wiley.com/doi/pdf/10.1029/2018GL077787},
abstract = {Abstract Clouds have an enormous influence on the Earth's energy balance, climate, and weather. Cloud types have different cloud radiative effects, which is an essential indicator of the cloud effect on radiation. Therefore, identifying the cloud type is important in meteorology. In this letter, we propose a new convolutional neural network model, called CloudNet, for accurate ground-based meteorological cloud classification. We build a ground-based cloud data set, called Cirrus Cumulus Stratus Nimbus, which consists of 11 categories under meteorological standards. The total number of cloud images is three times that of the previous database. In particular, it is the first time that contrails, a type of cloud generated by human activity, have been taken into account in the ground-based cloud classification, making the Cirrus Cumulus Stratus Nimbus data set more discriminative and comprehensive than existing ground-based cloud databases. The evaluation of a large number of experiments demonstrates that the proposed CloudNet model could achieve good performance in meteorological cloud classification.},,
year = {2018}
}