Журнал

About Editorial Board Information for authors and reviewers Publication ethics Contacts User Account: send / review a manuscript
Archive
Volume 22, 2025
Number 1 Number 2 Number 3
Volume 21, 2024
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 20, 2023
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 19, 2022
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 18, 2021
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 17, 2020
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 16, 2019
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 15, 2018
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 14, 2017
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 13, 2016
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 12, 2015
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 11, 2014
Number 1 Number 2 Number 3 Number 4
Volume 10, 2013
Number 1 Number 2 Number 3 Number 4
Volume 9, 2012
Number 1 Number 2 Number 3 Number 4 Number 5
Volume 8, 2011
Number 1 Number 2 Number 3 Number 4
Volume 7, 2010
Number 1 Number 2 Number 3 Number 4
Issue 6, 2009
Volume 1 Volume 2
Issue 5, 2008
Volume 1 Volume 2
Issue 4, 2007
Volume 1 Volume 2
Issue 3, 2006
Volume 1 Volume 2
Issue 2, 2005
Volume 1 Volume 2
Issue 1, 2004
Volume 1
Search
Find:
русский
ISSN 2070-7401 (Print), ISSN 2411-0280 (Online)
Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa
CURRENT PROBLEMS IN REMOTE SENSING OF THE EARTH FROM SPACE

  

Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2025, V. 22, No. 3, pp. 81-94

Satellite image segmentation methods for river plume delineation using neural networks

A.N. Yakusheva 1 , N.A. Knyazev 1 , M.V. Vrublevsky 1 
1 Space Research Institute RAS, Moscow, Russia
Accepted: 18.06.2025
DOI: 10.21046/2070-7401-2025-22-3-81-94
The work is devoted to the development and study of methods of automatic segmentation of satellite images using convolutional neural networks with the aim of river plume delineation. The study was based on analysis of data from Sentinel-2 MSI multispectral sensors for four main regions: the mouth zones of the Sulak and Terek rivers in the Caspian Sea, the Mzymta River in the Black Sea and the Kaliningrad Canal in the Baltic Sea. A dataset comprising 587 fragments of satellite images with expert marking of river plumes was created. A comprehensive comparison of 10 different neural network architectures was conducted, including combinations of encoders (VGG16, ResNet50, Xception) with decoders (U-Net, DeepLabv3+, FCN), as well as the YOLO 11-Seg model. To improve the quality of segmentation, a software package for data pre-processing was developed, including modules for loading, cropping and labeling satellite images. Experimental studies showed that the YOLO 11-Seg architecture demonstrated the best performance with a Dice coefficient of 0.74. To further improve the results, two ensembling methods were implemented: weighted mask averaging and stacking using Random Forest as a metamodel. The stacking approach showed the best results, achieving a Dice coefficient of 0.78. The developed methodology demonstrates high efficiency of automatic detection of river plumes in various hydrological conditions and can be integrated into operational satellite monitoring systems of the marine environment.
Keywords: satellite monitoring, Sentinel-2 MSI, river plume, neural networks, segmentation, Sulak, Terek, Mzymta, Kaliningrad Bay
Full text

References:

  1. Lavrova O. Yu., Kostianoy A. G., Lebedev S. A., Mityagina M. I., Ginzburg A. I., Sheremet N. A., Kompleksnyi sputnikovyi monitoring morei Rossii (Complex satellite monitoring of Russian seas), Moscow: IKI RAS, 2011, 480 p. (in Russian).
  2. Lavrova O. Yu., Nazirova K. R., Alferyeva Ya. O. et al., Comparison of plume parameters of the Sulak and Terek rivers based on satellite data and in situ measurements, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2022, V. 19, No. 5, pp. 264–283 (in Russian), DOI: 10.21046/2070-7401-2022-19-5-264-283.
  3. Loupian E. A., Matveev A. A., Uvarov I. A. et al., The Satellite Service See the Sea — a tool for the study of oceanic phenomena and processes, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2012, V. 9, No. 2, pp. 251–261 (in Russian).
  4. Nazirova K. R., Lavrova O. Yu., Krayushkin E. V. et al., Features of river plume parameter determination by in situ and remote sensing methods, Sovremennye problem distantsionnogo zondirovaniya Zemli iz kosmosa, 2019, V. 16, No. 2, pp. 227–243 (in Russian), DOI: 10.21046/2070-7401-2019-16-2-227-243.
  5. Nazirova K. R., Lavrova O. Yu., Alferyeva Ya. O., Knyazev N. A., Spatiotemporal plume variability of Terek and Sulak rivers from satellite data and concurrent in situ measurements, Sovremennye problem distantsionnogo zondirovaniya Zemli iz kosmosa, 2023, V. 20, No. 5, pp. 285–303 (in Russian), DOI: 10.21046/2070-7401-2023-20-5-285-303.
  6. Bochkovskiy A., Wang C.-Y., Liao H.-Y. M., YOLOv4: Optimal speed and accuracy of object detection, https://arxiv.org/, 2020, 17 p., DOI: 10.48550/arXiv.2004.10934.
  7. Chen L.-C., Zhu Y., Papandreou G. et al., Encoder-decoder with atrous separable convolution for semantic image segmentation, In: Proc. 15 th European Conf. Computer Vision — ECCV 2018, Pt. 7, Lecture Notes in Computer Science, V. 11211, Cham: Springer, 2018, pp. 833–851, DOI: 10.1007/978-3-030-01234-2_49.
  8. Chollet F., Xception: Deep learning with depthwise separable convolutions, Proc. 2017 IEEE Conf. Computer Vision and Pattern Recognition (CVPR 2017), 2017, pp. 1800–1807, DOI: 10.1109/CVPR.2017.195.
  9. Deng J., Dong W., Socher R. et al., ImageNet: A large-scale hierarchical image database, Proc. 2009 IEEE Conf. Computer Vision and Pattern Recognition (CVPR 2009), 2009, pp. 248–255, DOI: 10.1109/CVPR.2009.5206848.
  10. He K., Zhang X., Ren S., Sun J., Deep residual learning for image recognition, Proc. 2016 IEEE Conf. Computer Vision and Pattern Recognition (CVPR 2016), 2016, pp. 770–778, DOI: 10.1109/CVPR.2016.90.
  11. Kingma D. P., Ba J., Adam: A method for stochastic optimization, https://arxiv.org/, 2014, 15 p., DOI: 10.48550/arXiv.1412.6980.
  12. Kirillov A., Girshick R., He K., Dollár P., Panoptic Feature Pyramid Networks, Proc. 2019 IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR 2019), 2019, pp. 6392–6401, DOI: 10.1109/CVPR.2019.00656.
  13. Kostianoy A. G., Ginzburg A. I., Lavrova O. Yu. et al., Comprehensive satellite monitoring of Caspian Sea conditions, In: Remote Sensing of the Asian Seas, Barale V., Gade M. (eds.), Cham: Springer Intern. Publ., 2019, pp. 505–521, DOI: 10.1007/978-3-319-94067-0_28.
  14. LeCun Y., Bengio Y., Hinton G., Deep learning, Nature, 2015, V. 521, pp. 436–444, DOI: 10.1038/nature14539.
  15. Long J., Shelhamer E., Darrell T., Fully convolutional networks for semantic segmentation, Proc. 2015 IEEE Conf. Computer Vision and Pattern Recognition (CVPR 2015), 2015, pp. 3431–3440, DOI: 10.1109/CVPR.2015.7298965.
  16. Pan S. J., Yang Q., A survey on transfer learning, IEEE Trans. Knowledge and Data Engineering, 2010, V. 22, No. 10, pp. 1345–1359, DOI: 10.1109/TKDE.2009.191.
  17. Redmon J., Divvala S., Girshick R., Farhadi A., You Only Look Once: Unified, real-time object detection, Proc. 2016 IEEE Conf. Computer Vision and Pattern Recognition (CVPR 2016), 2016, pp. 779–788, DOI: 10.1109/CVPR.2016.91.
  18. Ronneberger O., Fischer P., Brox T., U-Net: Convolutional networks for biomedical image segmentation, In: Medical Image Computing and Computer-Assisted Intervention — MICCAI 2015, Pt. 3, Lecture Notes in Computer Science, V. 9351, Cham: Springer, 2015, pp. 234–241, DOI: 10.1007/978-3-319-24574-4_28.
  19. Simonyan K., Zisserman A., Very deep convolutional networks for large-scale image recognition, https://arxiv.org/, 2014, 14 p., DOI: 10.48550/arXiv.1409.1556.
  20. Zeiler M. D., Fergus R., Visualizing and understanding convolutional networks, In: Proc. 13 th European Conf. Computer Vision — ECCV 2014, Pt. 1, Lecture Notes in Computer Science, V. 8689, Cham: Springer, 2014, pp. 818–833, DOI: 10.1007/978-3-319-10590-1_53.