Journal cover Journal topic
The Cryosphere An interactive open-access journal of the European Geosciences Union
Journal topic

Journal metrics

Journal metrics

  • IF value: 4.790 IF 4.790
  • IF 5-year value: 5.921 IF 5-year
    5.921
  • CiteScore value: 5.27 CiteScore
    5.27
  • SNIP value: 1.551 SNIP 1.551
  • IPP value: 5.08 IPP 5.08
  • SJR value: 3.016 SJR 3.016
  • Scimago H <br class='hide-on-tablet hide-on-mobile'>index value: 63 Scimago H
    index 63
  • h5-index value: 51 h5-index 51
Discussion papers
https://doi.org/10.5194/tc-2019-159
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/tc-2019-159
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

Submitted as: research article 05 Aug 2019

Submitted as: research article | 05 Aug 2019

Review status
This discussion paper is a preprint. It is a manuscript under review for the journal The Cryosphere (TC).

Prediction of monthly Arctic sea ice concentration using satellite and reanalysis data based on convolutional neural networks

Young Jun Kim1, Hyun-Cheol Kim2, Daehyeon Han1, Sanggyun Lee3, and Jungho Im1,4 Young Jun Kim et al.
  • 1School of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology, Ulsan, South Korea
  • 2Unit of Arctic Sea-Ice Prediction, Korea Polar Research Institute, Incheon, Republic of Korea
  • 3Centre for Polar Observation and Modelling, University College London, London, UK
  • 4Environmental Resources Engineering, tate University of New York College of Environmental Science and Forestry,Syracuse, NY, USA

Abstract. Changes in Arctic sea ice affect atmospheric circulation, ocean current, and polar ecosystems. There have been unprecedented decreases in the amount of Arctic sea ice, due to the global warming and its various adjoint cases. In this study, a novel one-month sea ice concentration (SIC) prediction model is proposed, with eight predictors using a deep learning approach, Convolutional Neural Networks (CNN). This monthly SIC prediction model based CNN is shown to perform better predictions (mean absolute error (MAE) of 2.28 %, root mean square error (RMSE) of 5.76 %, normalized RMSE (nRMSE) of 16.15 %, and NSE of 0.97) than a random forest (RF)-based model (MAE of 2.45 %, RMSE of 6.61 %, nRMSE of 18.64 %, and NSE of 0.96) and a simple prediction model based on the yearly trend (MAE of 9.36 %, RMSE of 21.93 %, nRMSE of 61.94 %, and NSE of 0.83) through hindcast validations. Spatiotemporal analysis also confirmed the superiority of the CNN model. The CNN model showed good SIC prediction results in extreme cases that recorded unforeseen sea ice plummets in 2007 and 2012 with less than 5.0 % RMSEs. This study also examined the importance of the input variables through a sensitivity analysis. In both the CNN and RF models, the variables of past SICs were identified as the most sensitive factor in predicting SIC. For both models, the SIC-related variables generally contributed more to predict SICs over ice-covered areas, while other meteorological and oceanographic variables were more sensitive to the prediction of SICs in marginal ice zones. The proposed one-month SIC prediction model provides valuable information which can be used in various applications, such as Arctic shipping route planning, management of fishery industry, and long-term sea ice forecasting and dynamics.

Young Jun Kim et al.
Interactive discussion
Status: open (until 16 Oct 2019)
Status: open (until 16 Oct 2019)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
[Subscribe to comment alert] Printer-friendly Version - Printer-friendly version Supplement - Supplement
Young Jun Kim et al.
Young Jun Kim et al.
Viewed  
Total article views: 319 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
246 70 3 319 2 3
  • HTML: 246
  • PDF: 70
  • XML: 3
  • Total: 319
  • BibTeX: 2
  • EndNote: 3
Views and downloads (calculated since 05 Aug 2019)
Cumulative views and downloads (calculated since 05 Aug 2019)
Viewed (geographical distribution)  
Total article views: 108 (including HTML, PDF, and XML) Thereof 107 with geography defined and 1 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Cited  
Saved  
No saved metrics found.
Discussed  
No discussed metrics found.
Latest update: 14 Oct 2019
Publications Copernicus
Download
Short summary
In this study, we proposed a novel one-month sea ice concentration (SIC) prediction model, with eight predictors using a deep-learning approach, Convolutional Neural Networks (CNN). The proposed CNN model was evaluated and compared with the two baseline approaches, random forest and simple regression models, resulting in better performance. This study also examined SIC predictions for two extreme cases in 2007 and 2012 in detail, and the influencing factors through a sensitivity analysis.
In this study, we proposed a novel one-month sea ice concentration (SIC) prediction model, with...
Citation