SCM-Net: A Lightweight AI-Based Sea Ice Classification for Climate Change
DOI:
https://doi.org/10.4108/eetinis.132.12246Keywords:
Light-weight deep learning models, real-time applications, SCM-Net, sea ice classification, swin transformerAbstract
Sea ice is considered one of the most valuable sources of information for maintaining the balance of Earth’s climate system and preventing excessive warming. This study introduces a lightweight yet accurate model designed for real-time sea ice classification to provide an accessible and practical tool for operational use. We propose the SCM-Net, a deep learning model for sea ice classification applications, and compare its performance against other state-of-the-art models, including MobileNet, Residual Network (ResNet), Visual Geometry Group Network (VGGNet), Vision Transformers (ViT), and Shifted Window Transformers (SwinT). The Swin Transformer Convolutional Hybrid model (SCM-Net) is a lightweight model with around 45 times less parameters, enabling usage in real time applications. The results demonstrate that the proposed SCMNet model achieves a comparable and even better accuracy in comparison to other models. Moreover, the proposed model significantly reduces the number of parameters while improving inference efficiency. These results show that the proposed model is well suited for real time sea ice classification applications.
Downloads
References
[1] R. Lindsey and M. Scott, “Climate change: Arctic sea ice summer minimum,” https://www. climate.gov/news-features/understanding-climate/ climate-change-arctic-sea-ice-summer-minimum, 2020, accessed on 8 October 2024.
[2] N. Zakhvatkina, V. Smirnov, and I. Bychkova, “Satellite sar data-based sea ice classification: An overview,” Geosciences, vol. 9, no. 4, p. 152, 2019.
[3] I. Sudakow, V. K. Asari, R. Liu, and D. Demchev, “Meltpondnet: A swin transformer u-net for detection of melt ponds on arctic sea ice,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 15, pp. 8776–8784, Oct. 2022.
[4] Z. Zhang, G. Deng, C. Luo, X. Li, Y. Ye, and D. Xian, “A multiscale dual attention network for the automatic classification of polar sea ice and open water based on sentinel-1 sar images,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 17, pp. 5500–5516, Jan. 2024.
[5] J. Zhang, W. Zhang, X. Zhou, Q. Chu, X. Yin, G. Li, X. Dai, S. Hu, and F. Jin, “Cnn and transformer fusion network for sea ice classification using gaofen-3 polarimetric sar images,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 17, pp. 1234–1245, Sep. 2024.
[6] S. Khaleghian, H. Ullah, T. Kramer, N. Hughes, T. Eltoft, and A. Marinoni, “Sea ice classification of sar imagery based on convolution neural networks,” Remote Sensing, vol. 13, no. 9, p. 1734, Apr. 2021.
[7] J. Lohse, A. P. Doulgeris, and W. Dierking, “Mapping sea-ice types from sentinel-1 considering the surfacetype dependent effect of incidence angle,” Annals of Glaciology, vol. 61, no. 83, pp. 260–270, Jun. 2020.
[8] T. Zhang et al., “Deep learning based sea ice classification with gaofen-3 fully polarimetric sar data,” Remote Sensing, vol. 13, no. 8, p. Art. no. 1452, Apr. 2021.
[9] D. Kim, D. Park, J. Seo, H. Cho, S. Ahn, N. Kang, and S. Kim, “Estimation of electromagnetic field strength: Experiments using vision transformers,” IEEE Access, vol. 13, pp. 195 735–195 748, Dec. 2025.
[10] O. Agbo-Ajala and S. Viriri, “A lightweight convolutional neural network for real and apparent age estimation in unconstrained face images,” IEEE Access, vol. 8, pp. 162 800–162 808, Sep. 2020.
[11] M. Jiang, X. Chen, L. Xu, and D. A. Clausi, “Icegcn: An interactive sea ice classification pipeline for sar imagery based on graph convolutional network,” Remote Sensing, vol. 16, no. 13, Jun. 2024.
[12] J. Deng,W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, “Imagenet: A large-scale hierarchical image database,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2009, pp. 248–255.
[13] L. Papa, P. Russo, I. Amerini, and L. Zhou, “A survey on efficient vision transformers: Algorithms, techniques, and performance benchmarking,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 46, no. 12, pp. 7682–7700, Dec. 2024.
[14] T. C. Nauen, S. Palacio, F. Rauer, and A. Dengel, “Which transformer to favor: A comparative analysis of efficiency in vision transformers,” arXiv preprint arXiv:2308.09372, Aug 2023. [Online]. Available: https://arxiv.org/abs/2308.09372
[15] L. Peng, Y. Cao, Y. Sun, and Y. Wang, “Lightweight adaptive feature de-drifting for compressed image classification,” IEEE Transactions on Multimedia, vol. 26, pp. 6424–6436, Jul. 2024.
[16] H. Zhang, J. Liu, D. Jiang, Z. Luo, W. Liang, S. Li, X. Chen, X. Yuan, and S. Gao, “Lms-net: A light-weight network for mungbean salt stress identification,” IEEE Access, vol. 12, pp. 131 701–131 713, Sep. 2024.
[17] Y. Zhang, Z. Lei, H. Yu, and L. Zhuang, “Imbalanced high-resolution sar ship recognition method based on a lightweight cnn,” IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1–5, Jan. 2022.
[18] J. Kong and F. Zhang, “Sar target recognition with generative adversarial network (gan)-based data augmentation,” in Proc. 13th Int. Conf. Advanced Infocomm Technology (ICAIT). IEEE, Oct. 2021, pp. 215–218.
[19] G. F. Araujo, R. Machado, and M. I. Pettersson, “Synthetic sar data generator using pix2pix cgan architecture for automatic target recognition,” IEEE Access, vol. 11, pp. 143 369–143 386, Dec. 2023.
[20] S. Du et al., “Multi-category sar images generation based on improved generative adversarial network,” in Proceedings of the IEEE International Geoscience and Remote Sensing Symposium (IGARSS). Brussels, Belgium: IEEE, Jul. 2021, pp. 4260–4263.
[21] I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial networks,” in Advances in Neural Information Processing Systems (NeurIPS), vol. 27, Dec. 2014, pp. 2672–2680.
[22] A. Creswell, T. White, V. Dumoulin, K. Arulkumaran, B. Sengupta, and A. A. Bharath, “Generative adversarial networks: An overview,” IEEE Signal Processing Magazine, vol. 35, no. 1, pp. 53–65, Jan. 2018.
[23] PyTorch Contributors, “Pytorch,” https://pytorch.org/, accessed: Mar. 10, 2026.
[24] Z. Liu, Y. Lin, Y. Cao, H. Hu, R. Wang, Q. Guo, L. Zhang, and D. Lin, “Swin transformer: Hierarchical vision transformer using shifted windows,” arXiv preprint arXiv:2103.14030, Mar. 2021.
[25] A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam, “Mobilenets: Efficient convolutional neural networks for mobile vision applications,” arXiv preprint arXiv:1704.04861, Apr. 2017. [Online]. Available: https://arxiv.org/abs/1704.04861
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Nazanin Baramaki, Quang Nhat Le, Brad D. E. McNiven, Muhammad Fahim
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 3.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
