A Spatio-Temporal Deep Learning Model for Automatic Arctic Sea Ice Classification with Sentinel-1 SAR Imagery
Abstract
:1. Introduction
- (1)
- In the context of sea ice classification tasks, the generation of high-quality labels is typically dependent on sea ice charts. These charts are created through the manual analysis of multiple data sources and offer comprehensive information regarding sea ice, encompassing both the concentration of sea ice and its developmental stages. Institutions such as the U.S. National Ice Center (USNIC), the Norwegian Meteorological Institute (MET), the Danish Meteorological Institute (DMI), and the Canadian Ice Service (CIS) publish operational sea ice charts on a daily or weekly basis. Utilizing the aforementioned ice charts, numerous DL models have been developed, demonstrating efficacy in the classification of sea ice. Nevertheless, there remains a notable disparity in the number of distinct sea ice types that have been classified. Certain research endeavors concentrate on the classification of sea ice in contrast to open water in a binary framework [21,22,23]. Most studies aim to classify three to five sea ice types [16,17,18,19]. Song et al. [24] integrated residual convolutional neural networks (ResNet) with long short-term memory (LSTM) networks to classify seven distinct types of sea ice in Hudson Bay. Since CIS ice charts can provide up to 10 sea ice types, it is of great interest to develop a DL model to identify more refined sea ice types. However, sea ice types with close developmental stages demonstrate little variation in SAR images (see Figure 1). This challenge underscores the need for efficient and robust DL models with high classification accuracy.
- (2)
- In the field of computer vision, DL models designed for classification tasks are typically constructed using artificially balanced datasets, where each category has a roughly equal number of samples. Conversely, real-world datasets often exhibit class imbalance, as exemplified by the sea ice datasets utilized in this research. When dealing with such imbalanced datasets, common DL methods are not able to achieve outstanding classification accuracy. To illustrate this, we trained the ResNet-50 model [25] to classify sea ice types. The sea ice type distribution of the training dataset and the classwise F1-score of the test dataset are shown in Figure 2.
2. Study Area and Data
2.1. Area of Interest
2.2. Sentinel-1 SAR Imagery
2.3. Sea Ice Charts
2.4. Temporal and Spatial Variation Characteristics of Sea Ice
2.5. Dataset Construction
3. Methods
3.1. Framework of the Dynamic MLP Model
3.1.1. The CNN Block
3.1.2. The MLP Block
3.1.3. The Dynamic Projection Block
3.2. Framework of Dynamic Curriculum Learning Training
3.2.1. Sampling Scheduler
3.2.2. Loss Scheduler
3.3. Evaluation Metrics
3.4. Implementation Details
4. Results
4.1. Performance Comparison of Sea Ice Classification Models
4.2. Influence of Incidence Angle Dependence
- (1)
- The NRCS can be normalized through incidence angle correction for all swath ranges [11,12,14,16,21,40]. The incidence angle dependence of OW and sea ice NRCS in HH polarization is illustrated in Figure 12. The NRCS of OW and sea ice is a linear function of the incidence angle, with the incidence angle dependence for OW being significantly higher than for sea ice. This is consistent with previous studies [36,37,38,39]. Although we can calculate the dependence relationship for OW and each sea ice type by simple linear fitting, it is difficult to determine the total compensation because the surface type is not known a priori. As a result, the incidence angle influence has not been considered in some studies [19,22,24].
- (2)
- The incidence angle can be considered as an additional input channel, with the same two-dimensional size as the input patches [17]. Specifically, the input of the SAR image branch consists of three channels: , , and the incidence angles. This method is not optimal because no textural information is contained in incidence angles. This will also significantly increase the computational load.Following the core idea of dynamic MLP, we propose the third method:
- (3)
- The averaged incidence angle of each sample is utilized as an additional input of the spatio-temporal branch. By projecting similar sea ice features to different incidence angles, the sea ice classification ability of our model can be further enhanced.
5. Discussion
5.1. Advantages
5.2. Limitations and Future Work
6. Conclusions
Author Contributions
Funding
Data Availability Statement
Acknowledgments
Conflicts of Interest
Appendix A
References
- Comiso, J.C.; Parkinson, C.L.; Gersten, R.; Stock, L. Accelerated decline in the Arctic sea ice cover. Geophys. Res. Lett. 2008, 35, L01703. [Google Scholar] [CrossRef]
- Liu, Z.; Risi, C.; Codron, F.; He, X.; Poulsen, C.J.; Wei, Z.; Chen, D.; Li, S.; Bowen, G.J. Acceleration of western Arctic sea ice loss linked to the Pacific North American pattern. Nat. Commun. 2021, 12, 1519. [Google Scholar] [CrossRef] [PubMed]
- Tivy, A.; Howell, S.E.; Alt, B.; McCourt, S.; Chagnon, R.; Crocker, G.; Carrieres, T.; Yackel, J.J. Trends and variability in summer sea ice cover in the Canadian Arctic based on the Canadian Ice Service Digital Archive, 1960–2008 and 1968–2008. J. Geophys. Res. Ocean. 2011, 116, C03007. [Google Scholar] [CrossRef]
- Wang, Z.; Li, Z.; Zeng, J.; Liang, S.; Zhang, P.; Tang, F.; Chen, S.; Ma, X. Spatial and temporal variations of Arctic sea ice from 2002 to 2017. Earth Space Sci. 2020, 7, e2020EA001278. [Google Scholar] [CrossRef]
- Cai, Q.; Wang, J.; Beletsky, D.; Overland, J.; Ikeda, M.; Wan, L. Accelerated decline of summer Arctic sea ice during 1850–2017 and the amplified Arctic warming during the recent decades. Environ. Res. Lett. 2021, 16, 034015. [Google Scholar] [CrossRef]
- Xie, T.; Perrie, W.; Fang, H.; Zhao, L.; Yu, W.; He, Y. Spatial and temporal variability of sea ice deformation rates in the Arctic Ocean observed by RADARSAT-1. Sci. China Earth Sci. 2017, 60, 858–865. [Google Scholar] [CrossRef]
- Rodriguez-Alvarez, N.; Holt, B.; Jaruwatanadilok, S.; Podest, E.; Cavanaugh, K.C. An Arctic sea ice multi-step classification based on GNSS-R data from the TDS-1 mission. Remote Sens. Environ. 2019, 230, 111202. [Google Scholar] [CrossRef]
- Yan, Q.; Huang, W. Sea Ice Remote Sensing Using GNSS-R: A Review. Remote Sens. 2019, 11, 2565. [Google Scholar] [CrossRef]
- Yan, Q.; Huang, W. Sea Ice Sensing From GNSS-R Data Using Convolutional Neural Networks. IEEE Geosci. Remote. Sens. Lett. 2018, 15, 1510–1514. [Google Scholar] [CrossRef]
- Zhu, Y.; Tao, T.; Li, J.; Yu, K.; Wang, L.; Qu, X.; Li, S.; Semmling, M.; Wickert, J. Spaceborne GNSS-R for Sea Ice Classification Using Machine Learning Classifiers. Remote Sens. 2021, 13, 4577. [Google Scholar] [CrossRef]
- Liu, H.; Guo, H.; Zhang, L. SVM-based sea ice classification using textural features and concentration from RADARSAT-2 dual-pol ScanSAR data. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2015, 8, 1601–1613. [Google Scholar] [CrossRef]
- Zakhvatkina, N.; Korosov, A.; Muckenhuber, S.; Sandven, S.; Babiker, M. Operational algorithm for ice–water classification on dual-polarized RADARSAT-2 images. Cryosphere 2017, 11, 33–46. [Google Scholar] [CrossRef]
- Zhang, L.; Liu, H.; Gu, X.; Guo, H.; Chen, J.; Liu, G. Sea ice classification using TerraSAR-X ScanSAR data with removal of scalloping and interscan banding. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2019, 12, 589–598. [Google Scholar] [CrossRef]
- Park, J.-W.; Korosov, A.A.; Babiker, M.; Won, J.-S.; Hansen, M.W.; Kim, H.-C. Classification of sea ice types in Sentinel-1 synthetic aperture radar images. Cryosphere 2019, 14, 2629–2645. [Google Scholar] [CrossRef]
- Fredensborg Hansen, R.M.; Rinne, E.; Skourup, H. Classification of Sea Ice Types in the Arctic by Radar Echoes from SARAL/AltiKa. Remote Sens. 2021, 13, 3183. [Google Scholar] [CrossRef]
- Boulze, H.; Korosov, A.; Brajard, J. Classification of sea ice types in Sentinel-1 SAR data using convolutional neural networks. Remote Sens. 2020, 12, 2165. [Google Scholar] [CrossRef]
- Khaleghian, S.; Ullah, H.; Kræmer, T.; Hughes, N.; Eltoft, T.; Marinoni, A. Sea ice classification of SAR imagery based on convolution neural networks. Remote Sens. 2021, 13, 1734. [Google Scholar] [CrossRef]
- Zhang, J.; Zhang, W.; Hu, Y.; Chu, Q.; Liu, L. An improved sea ice classification algorithm with Gaofen-3 dual-polarization SAR data based on deep convolutional neural networks. Remote Sens. 2022, 14, 906. [Google Scholar] [CrossRef]
- Lyu, H.; Huang, W.; Mahdianpari, M. Eastern Arctic Sea Ice Sensing: First Results from the RADARSAT Constellation Mission Data. Remote Sens. 2022, 14, 1165. [Google Scholar] [CrossRef]
- Zhao, L.; Xie, T.; Perrie, W.; Yang, J. Deep Learning-Based Sea Ice Classification with Sentinel-1 and AMSR-2 Data. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2023, 16, 5514–5525. [Google Scholar] [CrossRef]
- Wang, Y.-R.; Li, X.-M. Arctic sea ice cover data from spaceborne synthetic aperture radar by deep learning. Earth Syst. Sci. Data 2021, 13, 2723–2742. [Google Scholar] [CrossRef]
- Ren, Y.; Li, X.; Yang, X.; Xu, H. Development of a dual-attention U-Net model for sea ice and open water classification on SAR images. IEEE Geosci. Remote. Sens. Lett. 2022, 19, 4010205. [Google Scholar] [CrossRef]
- Zhao, L.; Xie, T.; Perrie, W.; Yang, J. Sea Ice Detection from RADARSAT-2 Quad-Polarization SAR Imagery Based on Co- and Cross-Polarization Ratio. Remote Sens. 2024, 16, 515. [Google Scholar] [CrossRef]
- Song, W.; Li, M.; Gao, W.; Huang, D.; Ma, Z.; Liotta, A.; Perra, C. Automatic Sea-Ice Classification of SAR Images Based on Spatial and Temporal Features Learning. IEEE Trans. Geosci. Remote Sens. 2021, 59, 9887–9901. [Google Scholar] [CrossRef]
- He, K.; Zhang, X.; Ren, S.; 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]
- Yang, L.; Li, X.; Song, R.; Zhao, B.; Tao, J.; Zhou, S.; Liang, J.; Yang, J. Dynamic MLP for Fine-Grained Image Classification by Leveraging Geographical and Temporal Information. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, 18–24 June 2022; pp. 10945–10954. [Google Scholar]
- Mac Aodha, O.; Cole, E.; Perona, P. Presence-only geographical priors for fine-grained image classification. In Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea, 27 October–2 November 2019; pp. 9596–9606. [Google Scholar]
- Bengio, Y.; Louradour, J.; Collobert, R.; Weston, J. Curriculum learning. In Proceedings of the 26th Annual International Conference on Machine Learning, Montreal, QC, Canada, 14–18 June 2009; pp. 41–48. [Google Scholar]
- Soviany, P.; Ionescu, R.T.; Rota, P.; Sebe, N. Curriculum learning: A survey. Int. J. Comput. Vision 2022, 130, 1526–1565. [Google Scholar] [CrossRef]
- Wang, X.; Chen, Y.; Zhu, W. A survey on curriculum learning. IEEE Trans. Pattern Anal. Mach. Intell. 2021, 44, 4555–4576. [Google Scholar] [CrossRef]
- Radhakrishnan, K.; Scott, K.A.; Clausi, D.A. Sea Ice Concentration Estimation: Using Passive Microwave and SAR Data With a U-Net and Curriculum Learning. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2021, 14, 5339–5351. [Google Scholar] [CrossRef]
- Wang, Y.; Gan, W.; Yang, J.; Wu, W.; Yan, J. Dynamic curriculum learning for imbalanced data classification. In Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea, 27 October–2 November 2019; pp. 5017–5026. [Google Scholar]
- Masolele, R.N.; De Sy, V.; Herold, M.; Marcos, D.; Verbesselt, J.; Gieseke, F.; Mullissa, A.G.; Martius, C. Spatial and temporal deep learning methods for deriving land-use following deforestation: A pan-tropical case study using Landsat time series. Remote Sens. Environ. 2021, 264, 112600. [Google Scholar] [CrossRef]
- Shorten, C.; Khoshgoftaar, T.M. A survey on image data augmentation for deep learning. J. Big Data 2019, 6, 1–48. [Google Scholar] [CrossRef]
- Goyal, P.; Dollár, P.; Girshick, R.; Noordhuis, P.; Wesolowski, L.; Kyrola, A.; Tulloch, A.; Jia, Y.; He, K. Accurate, large minibatch sgd: Training imagenet in 1 hour. arXiv 2017, arXiv:1706.02677. [Google Scholar] [CrossRef]
- Mäkynen, M.; Karvonen, J. Incidence angle dependence of first-year sea ice backscattering coefficient in Sentinel-1 SAR imagery over the Kara Sea. IEEE Trans. Geosci. Remote Sens. 2017, 55, 6170–6181. [Google Scholar] [CrossRef]
- Mahmud, M.S.; Geldsetzer, T.; Howell, S.E.; Yackel, J.J.; Nandan, V.; Scharien, R.K. Incidence angle dependence of HH-polarized C-and L-band wintertime backscatter over Arctic sea ice. IEEE Trans. Geosci. Remote Sens. 2018, 56, 6686–6698. [Google Scholar] [CrossRef]
- Komarov, A.S.; Buehner, M. Detection of first-year and multi-year sea ice from dual-polarization SAR images under cold conditions. IEEE Trans. Geosci. Remote Sens. 2019, 57, 9109–9123. [Google Scholar] [CrossRef]
- Aldenhoff, W.; Eriksson, L.E.; Ye, Y.; Heuzé, C. First-year and multiyear sea ice incidence angle normalization of dual-polarized sentinel-1 SAR images in the beaufort sea. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2020, 13, 1540–1550. [Google Scholar] [CrossRef]
- Zhu, T.; Li, F.; Heygster, G.; Zhang, S. Antarctic sea-ice classification based on conditional random fields from RADARSAT-2 dual-polarization satellite images. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2016, 9, 2451–2467. [Google Scholar] [CrossRef]
- Huang, B.; Xie, Y.; Xu, C. Learning with noisy labels via clean aware sharpness aware minimization. Sci. Rep. 2025, 15, 1350. [Google Scholar] [CrossRef]
Stage of Development | Thickness (in cm) | WMO Code |
---|---|---|
OW | NA | 55 |
NI | <10 | 81 |
GI | 10–15 | 84 |
GWI | 15–30 | 85 |
ThinFYI | 30–70 | 87 |
MFYI | 70–120 | 91 |
ThickFYI | 120 | 93 |
OI | NA | 95 |
SYI | NA | 96 |
MYI | NA | 97 |
Layer Name | Kernel Size | Filters | Stride |
---|---|---|---|
conv1 | , BN, ReLU | 64 | 2 |
max_pool | \ | 2 | |
conv2_x | |||
conv3_x | |||
conv4_x | |||
conv5_x |
Model | ||
---|---|---|
LSTM | 80.93 | 69.25 |
Dynamic MLP | 89.49 | 80.13 |
Dynamic MLP + DCL | 95.62 | 88.37 |
Method | ||
---|---|---|
As an additional input channel of the SAR image branch | 95.83 | 88.74 |
As an additional input of the spatio-temporal branch | 96.58 | 90.13 |
Model | Training Efficiency (Hours) | Inference Efficiency (Minutes) |
---|---|---|
LSTM | 65 | 22 |
Dynamic MLP | 13 | 3 |
Dynamic MLP + DCL | 19 | 3 |
Model | Proportion of Incorrect Labels | |||||
---|---|---|---|---|---|---|
10% | 20% | 30% | ||||
LSTM | 77.84 | 65.31 | 72.43 | 61.05 | 66.28 | 55.69 |
Dynamic MLP | 86.37 | 77.25 | 79.66 | 70.81 | 71.95 | 65.23 |
Dynamic MLP + DCL | 91.10 | 85.37 | 85.32 | 78.52 | 80.29 | 73.09 |
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. |
© 2025 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
Zhao, L.; Zhou, Y.; Zhong, W.; Jin, C.; Liu, B.; Li, F. A Spatio-Temporal Deep Learning Model for Automatic Arctic Sea Ice Classification with Sentinel-1 SAR Imagery. Remote Sens. 2025, 17, 277. https://doi.org/10.3390/rs17020277
Zhao L, Zhou Y, Zhong W, Jin C, Liu B, Li F. A Spatio-Temporal Deep Learning Model for Automatic Arctic Sea Ice Classification with Sentinel-1 SAR Imagery. Remote Sensing. 2025; 17(2):277. https://doi.org/10.3390/rs17020277
Chicago/Turabian StyleZhao, Li, Yufeng Zhou, Wei Zhong, Cheng Jin, Bo Liu, and Fangzhao Li. 2025. "A Spatio-Temporal Deep Learning Model for Automatic Arctic Sea Ice Classification with Sentinel-1 SAR Imagery" Remote Sensing 17, no. 2: 277. https://doi.org/10.3390/rs17020277
APA StyleZhao, L., Zhou, Y., Zhong, W., Jin, C., Liu, B., & Li, F. (2025). A Spatio-Temporal Deep Learning Model for Automatic Arctic Sea Ice Classification with Sentinel-1 SAR Imagery. Remote Sensing, 17(2), 277. https://doi.org/10.3390/rs17020277