SICFormer: A 3D-Swin Transformer for Sea Ice Concentration Prediction
Abstract
:1. Introduction
2. Methods
2.1. Data
2.2. Problem Definition
2.3. The Overall Structure
2.4. The Input
2.5. The Encoder
2.6. The Intermediate Module
2.7. The Decoder
2.8. The Output
2.9. The Training and Evaluation Setup
3. Results
3.1. Overall Performance
3.2. Exploring the Details
4. Discussion
5. Conclusions
- A Video Swin Transformer based on the classical Transformer framework is used as an encoder, and a ViTs-CNN-CNN architecture is proposed and applied to a sea ice density prediction task to achieve the best performance.
- A hierarchical nested residual structure is designed. The first layer is a jump connection across the whole model to add raw data to the last CNN block, and the second layer nests a shortcut layer outside the two ResNet blocks. This design ensures stable training.
- Based on the evaluation metrics selected in this paper, the MAE is reduced to 1.89%, the RMSE is 5.99%, and the MAPE is 4.32%. The NSE is 0.980, and the combined performance is the best among all the models compared.
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Parkinson, C.L. A 40-y record reveals gradual Antarctic sea ice increases followed by decreases at rates far exceeding the rates seen in the Arctic. Proc. Nat. Acad. Sci. USA 2019, 116, 3126280. Available online: https://www.ncbi.nlm.nih.gov/pubmed/31262810 (accessed on 11 October 2023). [CrossRef]
- Olonscheck, D.; Mauritsen, T.; Notz, D. Arctic sea-ice variability is primarily driven by atmospheric temperature fluctuations. Nat. Geosci. 2019, 12, 430–434. [Google Scholar] [CrossRef]
- Kim, Y.H.; Min, S.K.; Gillett, N.P.; Notz, D.; Malinina, E. Observationally-constrained projections of an ice-free Arctic even under a low emission scenario. Nat. Commun. 2023, 14, 3139. [Google Scholar] [CrossRef]
- Chen, J.; Kang, S.; You, Q.; Zhang, Y.; Du, W. Projected changes in sea ice and the navigability of the Arctic passages under global warming of 2 °C and 3 °C. Anthropocene 2022, 40, 100349. [Google Scholar] [CrossRef]
- Yang, Q.; Losa, S.N.; Losch, M. Assimilating SMOS sea ice thickness into a coupled ice-ocean model using a local SEIK filter. J. Geophys. Res. Oceans 2014, 119, 6680–6692. [Google Scholar] [CrossRef]
- Zhang, J. Sea ice properties in high-resolution sea ice models. J. Geophys. Res. Ocean. 2021, 126, e2020JC016686. [Google Scholar] [CrossRef]
- Adcroft, A.; Anderson, W.; Balaji, V. The GFDL global ocean and sea ice model OM4.0: Model description and simulation features. J. Adv. Model. Earth Syst. 2019, 11, 3167–3211. [Google Scholar] [CrossRef]
- Smith, G.C.; Roy, F.; Reszka, M.; Colan, D.S.; He, Z.; Deacu, D.; Belanger, J.-M.; Skachko, S.; Liu, Y.; Dupont, F.; et al. Sea ice forecast verification in the Canadian global ice ocean prediction system. Quart. J. Roy. Meteorolog. Soc. 2016, 142, 659–671. [Google Scholar] [CrossRef]
- Hebert, D.A. Short-term sea ice forecasting: An assessment of ice concentration and ice drift forecasts using the U.S. Navy’s Arctic cap nowcast/forecast system. J. Geophys. Res. Ocean. 2015, 120, 8327–8345. [Google Scholar] [CrossRef]
- Liang, X.; Zhao, F.; Li, C.; Zhang, L.; Li, B. Evaluation of ArcIOPS sea ice forecasting products during the ninth CHINARE-Arctic in summer 2018. Adv. Polar Sci. 2020, 31, 14–25. [Google Scholar] [CrossRef]
- Mu, L.; Liang, X.; Yang, Q.; Liu, J.; Zheng, F. Arctic ice ocean prediction system: Evaluating sea-ice forecasts during Xuelong’s first trans-arctic passage in summer 2017. J. Glaciol. 2019, 65, 813–821. [Google Scholar] [CrossRef]
- Yang, Q.H.; Mu, L.J.; Wu, X.R. Improving Arctic sea ice seasonal outlook by ensemble prediction using an ice-ocean model. Atmos. Res. 2019, 227, 14–23. [Google Scholar] [CrossRef]
- Wang, L.; Yuan, X.; Ting, M.; Li, C. Predicting summer Arctic sea ice concentration intraseasonal variability using a vector autoregressive Model. J. Clim. 2016, 29, 1529–1543. [Google Scholar] [CrossRef]
- Yuan, X.; Chen, D.; Li, C.; Wang, L.; Wang, W. Arctic sea ice seasonal prediction by a linear Markov model. J. Clim. 2016, 29, 8151–8173. [Google Scholar] [CrossRef]
- Wang, L.; Yuan, X.; Li, C. Subseasonal forecast of Arctic sea ice concentration via statistical approaches. Clim. Dyn. 2019, 52, 4953–4971. [Google Scholar] [CrossRef]
- Ham, Y.G.; Kim, J.H.; Luo, J.J. Deep learning for multi-year ENSO forecasts. Nature 2019, 573, 568–572. [Google Scholar] [CrossRef]
- Ren, Y.; Cheng, T.; Zhang, Y. Deep spatio-temporal residual neural networks for road-network-based data modeling. Int. J. Geogr. Inf. Sci. 2019, 33, 1894–1912. [Google Scholar] [CrossRef]
- Reichstein, M. Deep learning and process understanding for data driven Earth system science. Nature 2019, 566, 195–204. [Google Scholar] [CrossRef]
- Zheng, G.; Li, X.; Zhang, R.H.; Liu, B. Purely satellite data–driven deep learning forecast of complicated tropical instability waves. Sci. Adv. 2020, 6, 1482. [Google Scholar] [CrossRef]
- Li, X. Deep-learning-based information mining from ocean remote-sensing imagery. Nat. Sci. Rev. 2020, 7, 1584–1605. [Google Scholar] [CrossRef] [PubMed]
- Zhang, X.; Li, X.; Zheng, Q. A machine-learning model for forecasting internal wave propagation in the Andaman sea. IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens. 2021, 14, 3095–3106. [Google Scholar] [CrossRef]
- Zhang, X.; Li, X. Combination of satellite observations and machine learning method for internal wave forecast in the Sulu and Celebes seas. IEEE Trans. Geosci. Remote Sens. 2021, 59, 2822–2832. [Google Scholar] [CrossRef]
- Liu, B.; Li, X.; Zheng, G. Coastal inundation mapping from bitemporal and dual-polarization SAR imagery based on deep convolutional neural networks. J. Geophys. Res. Ocean. 2019, 124, 9101–9113. [Google Scholar] [CrossRef]
- Lecun, Y.; Bottou, L.; Bengio, Y.; Haffner, P. Gradient-based learning applied to document recognition. Proc. IEEE 1998, 86, 2278–2324. [Google Scholar] [CrossRef]
- Williams, R.J.; Zipser, D. A Learning Algorithm for Continually Running Fully Recurrent Neural Networks. Neural Comput. 1989, 1, 270–280. [Google Scholar] [CrossRef]
- Bahdanau, D.; Cho, K.; Bengio, Y. Neural Machine Translation by Jointly Learning to Align and Translate. arXiv 2014, arXiv:1409.0473. [Google Scholar]
- Gao, Z.Y.; Tang, C.; Wu, L.R. SimVP: Simpler yet Better Video Prediction. In Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, 18–24 June 2022; pp. 3160–3170. [Google Scholar]
- Wang, Y.; Zhang, J.; Zhu, H.; Long, M.; Wang, J.; Yu, P.S. Memory in memory: A predictive neural network for learning higher-order nonstationarity from spatiotemporal dynamics. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, 15–20 June 2019; pp. 9154–9162. [Google Scholar]
- Wang, Y.; Long, M.; Wang, J.; Gao, Z.; Yu, P.S. Predrnn: Recurrent neural networks for predictive learning using spatiotemporal lstms. In Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, CA, USA, 4–9 December 2017; pp. 879–888. [Google Scholar]
- Shi, X.; Chen, Z.; Wang, H.; Yeung, D.Y.; Wong, W.K.; Woo, W. Convolutional lstm network: A machine learning approach for precipitation nowcasting. In Proceedings of the Advances in neural information processing systems, Montreal, QC, Canada, 7–12 December 2015; pp. 802–810. [Google Scholar]
- Castrejon, L.; Ballas, N.; Courville, A.N. Improved conditional vrnns for video prediction. In Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea, 27 October–2 November 2019; pp. 7608–7617. [Google Scholar]
- Guen, V.L.; Thome, N. Disentangling physical dynamics from unknown factors for unsupervised video prediction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 13–19 June 2020; pp. 11474–11484. [Google Scholar]
- Dosovitskiy, A.; Beyer, L.; Kolesnikov, A.; Weissenborn, D.; Zhai, X.; Unterthiner, T. An Image is Worth 16 × 16 Words: Transformers for Image Recognition at Scale. arXiv 2020, arXiv:2010.11929. [Google Scholar]
- Arnab, A.; Dehghani, M.; Heigold, G.; Sun, C.; Lucic, M.; Schmid, C. Vivit: A video vision transformer. arXiv 2012, arXiv:2103.15691. [Google Scholar]
- Bertasius, G.; Wang, H.; Torresani, L. Is space-time attention all you need for video understanding? arXiv 2021, arXiv:2102.05095. [Google Scholar]
- Fan, H.; Xiong, B.; Mangalam, K.; Li, Y.; Yan, Z.; Malik, J. Multiscale vision transformers. arXiv 2021, arXiv:2104.11227. [Google Scholar]
- Xu, Z.; Wang, Y.; Long, M.; Wang, J. Predcnn: Predictive learning with cascade convolutions. In Proceedings of the IJCAI, Stockholm, Sweden, 13–19 July 2018; pp. 2940–2947. [Google Scholar]
- Gao, H.; Xu, H.; Cai, Q.; Wang, R. Disentangling propagation and generation for video prediction. In Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea, 27 October–2 November 2019; pp. 9006–9015. [Google Scholar]
- Chi, J.; Kim, H.C. Prediction of Arctic sea ice concentration using a fully data driven deep neural network. Remote Sens. 2017, 9, 1305. [Google Scholar] [CrossRef]
- Chi, J.; Bae, J.; Kwon, Y.J. Two-stream convolutional long and short-term memory model using perceptual loss for sequence-to sequence Arctic sea ice prediction. Remote Sens. 2021, 13, 3413. [Google Scholar] [CrossRef]
- Kim, Y.J.; Kim, H.C.; Han, D.; Lee, S. Prediction of monthly Arctic sea ice concentrations using satellite and reanalysis data based on convolutional neural networks. Cryosphere 2020, 14, 1083–1104. [Google Scholar] [CrossRef]
- Andersson, T.R.; Hosking, J.S.; Maria, P.O. Seasonal Arctic sea ice forecasting with probabilistic deep learning. Nat. Commun. 2021, 12, 5124. [Google Scholar] [CrossRef] [PubMed]
- Ren, Y.; Li, X.; Zhang, W. A Data-Driven Deep Learning Model for Weekly Sea Ice Concentration Prediction of the Pan-Arctic During the Melting Season. IEEE Trans. Geosci. Remote Sens. 2022, 60, 4304819. [Google Scholar] [CrossRef]
- Zheng, Q.Y.; Wang, R.; Han, G.J. A Spatiotemporal Multiscale Deep Learning Model for Subseasonal Prediction of Arctic Sea Ice. IEEE Trans. Geosci. Remote Sens. 2024, 62, 4300522. [Google Scholar] [CrossRef]
- Vaswani, A.; Shazeer, N.M.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A.N.; Kaiser, L. Attention is All you Need. In Proceedings of the Neural Information Processing Systems, Long Beach, CA, USA, 4–9 December 2017. [Google Scholar] [CrossRef]
- Liu, Z.; Lin, Y.T.; Cao, Y. Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. In Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada, 10–17 October 2021; pp. 9992–10002. [Google Scholar]
- Liu, Z.; Ning, J.; Cao, Y.; Wei, Y.; Zhang, Z. Video Swin Transformer. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, 18–24 June 2022; pp. 3192–3201. [Google Scholar]
- He, K.M.; Zhang, X.Y.; Ren, S.Q.; Sun, J. Deep Residual Learning for Image Recognition. In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 27–30 June 2016; pp. 770–778. [Google Scholar]
- Shi, W.Z.; Caballero, J.; Huszár, F. Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network. In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 27–30 June 2016; pp. 1874–1883. [Google Scholar]
- Tan, C.; Gao, Z.; Li, S.; Xu, Y.; Li, S. Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning. In Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada, 17–24 June 2023; pp. 18770–18782. [Google Scholar]
- Chang, Z. MAU: A Motion-Aware Unit for Video Prediction and Beyond. Neural Inf. Process. Syst. 2021, 34, 26950–26962. [Google Scholar]
- Wang, Y.; Gao, Z.; Long, M.; Wang, J.; Yu, P.S. PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning. In Proceedings of the International Conference on Machine Learning, Stockholm, Sweden, 10–15 July 2018. [Google Scholar]
- Bi, K.F.; Xie, L.X.; Zhang, H.H.; Chen, X.; Gu, X.T.; Tian, Q. Pangu-Weather: A 3D High-Resolution Model for Fast and Accurate Global Weather Forecast. arXiv 2022, arXiv:2211.02556. [Google Scholar]
Metrics | 2018 | 2019 | 2020 | 2021 | 2022 | Average |
---|---|---|---|---|---|---|
MAE (%) | 1.87 | 1.87 | 1.89 | 1.91 | 1.93 | 1.89 |
RMSE (%) | 5.96 | 5.92 | 5.96 | 5.94 | 5.96 | 5.98 |
MAPE (%) | 4.27 | 4.34 | 4.35 | 4.31 | 4.29 | 4.31 |
NSE | 0.98 | 0.98 | 0.97 | 0.98 | 0.98 | 0.98 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Jiang, Z.; Guo, B.; Zhao, H.; Jiang, Y.; Sun, Y. SICFormer: A 3D-Swin Transformer for Sea Ice Concentration Prediction. J. Mar. Sci. Eng. 2024, 12, 1424. https://doi.org/10.3390/jmse12081424
Jiang Z, Guo B, Zhao H, Jiang Y, Sun Y. SICFormer: A 3D-Swin Transformer for Sea Ice Concentration Prediction. Journal of Marine Science and Engineering. 2024; 12(8):1424. https://doi.org/10.3390/jmse12081424
Chicago/Turabian StyleJiang, Zhuoqing, Bing Guo, Huihui Zhao, Yangming Jiang, and Yi Sun. 2024. "SICFormer: A 3D-Swin Transformer for Sea Ice Concentration Prediction" Journal of Marine Science and Engineering 12, no. 8: 1424. https://doi.org/10.3390/jmse12081424