Submitted as: model description paper
16 Jan 2023
Submitted as: model description paper |  | 16 Jan 2023
Status: this preprint is currently under review for the journal GMD.

IceTFT v 1.0.0: Interpretable Long-Term Prediction of Arctic Sea Ice Extent with Deep Learning

Bin Mu, Xiaodan Luo, Shijin Yuan, and Xi Liang

Abstract. Annual reductions in Arctic sea ice extent (SIE) due to global warming. According to International Panel on Climate Change (IPCC) climate model projections, the summer Arctic will be nearly sea ice free in the 50s of the 21st century, resulting in sea level rise and thus affecting human life. Therefore, it is important to predict SIE accurately. For the most current studies, the majority of deep learning-based SIE prediction models focus on single-step prediction, and they not only have short lead times but also have limited forecasting skills. In addition, these models often lack interpretability. In this study paper, we construct the Ice Temporal Fusion Transformer (IceTFT) model, which consists mainly of the variable selection network (VSN), the long short-term memory (LSTM) encoder, and multi-headed attention mechanism. Then we select 11 predictors for IceTFT model, including SIE, atmospheric, and ocean variables according to the physical mechanisms influencing sea ice development. And the VSN in IceTFT can automatically adjust the weights of predictors and filter spuriously correlated variables. We also evaluate the IceTFT model from the division of the training set, the slicing methods of input data, and the length of input. The IceTFT model directly generates 12-month SIE with average monthly prediction errors of less than 0.21 106 km2. And it predicts the September SIE nine months in advance with prediction error of less than 0.1 106 km2, which is superior to the models from Sea Ice Outlook (SIO). Furthermore, we analyze the sensitivity of the selected predictors to the SIE prediction. It verifies that the IceTFT model has some physical interpretability. And the variable sensitivities also provide some reference for understanding the mechanisms governing sea ice development and selecting the assimilation variables in dynamic models.

Bin Mu 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 gmd-2022-293', Anonymous Referee #1, 28 Jan 2023
  • RC2: 'Comment on gmd-2022-293', Anonymous Referee #2, 10 Apr 2023

Bin Mu et al.

Data sets

Sea Ice Index, Version 3 Fetterer, F., K. Knowles, W. N. Meier, M. Savoie, and A. K. Windnagel.

Improvements of the Daily Optimum Interpolation Sea Surface Temperature (DOISST) Version 2.1 Huang, B., C. Liu, V. Banzon, E. Freeman, G. Graham, B. Hankins, T. Smith, and H.-M. Zhang

The NCEP/NCAR 40-year reanalysis project Kalnay, E., Kanamitsu, M., Kistler, R., Collins, W., Deaven, D., Gandin, L., Iredell, M., Saha, S., White, G., Woollen, J., Zhu, Y., Chelliah, M., Ebisuzaki, W., Higgins, W., Janowiak, J., Mo, K. C., Ropelewski, C., Wang, J., Leetmaa, A., Reynolds, R., Jenne, R., & Joseph, D.<0437:TNYRP>2.0.CO;2

Boulder Monthly Means: Snowfall National Oceanic and Atmospheric Administration Physical Sciences Laboratory, Boulder Climate and Weather Information

Model code and software

IceTFT: 1.0.0 Xiaodan Luo

Bin Mu et al.


Total article views: 460 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
325 125 10 460 4 2
  • HTML: 325
  • PDF: 125
  • XML: 10
  • Total: 460
  • BibTeX: 4
  • EndNote: 2
Views and downloads (calculated since 16 Jan 2023)
Cumulative views and downloads (calculated since 16 Jan 2023)

Viewed (geographical distribution)

Total article views: 436 (including HTML, PDF, and XML) Thereof 436 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 03 Jun 2023
Short summary
To improve the long-term forecast skill for SIE, we introduce the IceTFT, which directly predicts 12 months of averaged Arctic SIE. The experiment results show that IceTFT has higher forecasting skills. And we conducted a sensitivity analysis of the variables in IceTFT model. These sensitivities can help researchers study the mechanisms of sea ice development, and they also provide useful references for the selection of variables in data assimilation or the input of deep learning models.