24 Jul 2023
 | 24 Jul 2023
Status: a revised version of this preprint is currently under review for the journal AMT.

Estimation of twenty-four-hour continuous cloud cover using ground-based imager with convolutional neural network

Bu-Yo Kim, Joo Wan Cha, and Yong Hee Lee

Abstract. In this study, we aimed to estimate cloud cover with high accuracy using images from a camera-based imager and a convolutional neural network (CNN) as a potential alternative to human-eye observation on the ground. Image data collected at 1 h intervals from 2019 to 2020 at a manned weather station, where human-eye observations were performed, were used as input data. The 2019 dataset was used for training and validating the CNN model, whereas the 2020 dataset was used for testing the estimated cloud cover. Additionally, we compared satellite (SAT) and ceilometer (CEI) cloud cover to determine the method most suitable for cloud cover estimation at the ground level. The CNN model was optimized using a deep layer and detailed hyperparameter settings. Consequently, the model achieved an accuracy, bias, root mean square error (RMSE), and correlation coefficient (R) of 0.92, −0.13, 1.40 tenths, and 0.95, respectively, on the test dataset, and exhibited approximately 93 % high agreement at a difference within ± 2 tenths of the observed cloud cover. This result demonstrates an improvement over previous studies that used threshold, machine learning, and deep learning methods. In addition, compared with the SAT (with an accuracy, bias, RMSE, R, and agreement of 0.89, 0.33 tenths, 2.31 tenths, 0.87, and 83 %, respectively) and CEI (with an accuracy, bias, RMSE, R, agreement of 0.86, −1.58 tenths, 3.34 tenths, 0.76, and 74 %, respectively), the camera-based imager with the CNN was found to be the most suitable method to replace ground cloud cover observation by humans.

Bu-Yo Kim et al.

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on amt-2023-131', Anonymous Referee #1, 12 Aug 2023
    • RC2: 'Reply on RC1', Anonymous Referee #2, 15 Aug 2023
      • AC2: 'Reply on RC2', Bu-Yo Kim, 31 Aug 2023
    • AC1: 'Reply on RC1', Bu-Yo Kim, 31 Aug 2023

Bu-Yo Kim et al.

Bu-Yo Kim et al.


Total article views: 264 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
203 46 15 264 4 6
  • HTML: 203
  • PDF: 46
  • XML: 15
  • Total: 264
  • BibTeX: 4
  • EndNote: 6
Views and downloads (calculated since 24 Jul 2023)
Cumulative views and downloads (calculated since 24 Jul 2023)

Viewed (geographical distribution)

Total article views: 253 (including HTML, PDF, and XML) Thereof 253 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 23 Sep 2023
Short summary
A camera-based imager and convolutional neural network (CNN) were used to estimate ground cloud cover. Image data from 2019 were used for training and validation, and those from 2020 were used for testing. The CNN model exhibited high performance, with an accuracy of 0.92, RMSE of 1.40 tenths, and 93 % agreement with observed cloud cover within ± 2 tenths difference. It also outperformed satellites and ceilometers and proved to be the most suitable for ground-based cloud cover estimation.