Preprints
https://doi.org/10.5194/amt-2021-379
https://doi.org/10.5194/amt-2021-379

  06 Dec 2021

06 Dec 2021

Review status: this preprint is currently under review for the journal AMT.

An all-sky camera images classification method using cloud cover features

Xiaotong Li, Baozhu Wang, Bo Qiu, and Chao Wu Xiaotong Li et al.
  • School of Electronics and Information Engineering, Hebei University of Technology, Tianjin, 300401, China

Abstract. The all-sky camera (ASC) images can reflect the local cloud cover information, and the cloud cover is one of the first factors considered for astronomical observatory site selection. Therefore, the realization of automatic classification of the ASC images plays an important role in astronomical observatory site selection. In this paper, three cloud cover features are proposed for the TMT (Thirty Meter Telescope) classification criteria, namely cloud weight, cloud area ratio and cloud dispersion. After the features are quantified, four classifiers are used to recognize the classes of the images. Four classes of ASC images are identified: “Clear”, “Inner”, “Outer” and “Covered”. The proposed method is evaluated on a large dataset, which contains 7328 ASC images taken by an all-sky camera located in Xinjiang (38.19° N, 74.53° E). In the end, the method achieves an accuracy of 97.28 % and F1_score of 96.97 % by a random forest (RF) classifier, which greatly improves the efficiency of automatic processing of the ASC images.

Xiaotong Li et al.

Status: open (until 17 Jan 2022)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Xiaotong Li et al.

Xiaotong Li et al.

Viewed

Total article views: 261 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
209 48 4 261 2 2
  • HTML: 209
  • PDF: 48
  • XML: 4
  • Total: 261
  • BibTeX: 2
  • EndNote: 2
Views and downloads (calculated since 06 Dec 2021)
Cumulative views and downloads (calculated since 06 Dec 2021)

Viewed (geographical distribution)

Total article views: 258 (including HTML, PDF, and XML) Thereof 258 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 15 Jan 2022
Download
Short summary
The ground-based cloud images can reflect the local cloud cover which is considerable for astronomical observatory site selection. Therefore, the realization of automatic classification of the images is very important. In this paper, three cloud cover features are proposed to classify the images. The proposed method is evaluated on a large dataset, and the method achieves an accuracy of 97.28 % and F1_score of 96.97 %, which greatly improves the efficiency of automatic processing of the images.