Izvestiya of Saratov University.

Earth Sciences

ISSN 1819-7663 (Print)
ISSN 2542-1921 (Online)

For citation:

Ogneva M. V., Shlapak P. A., Konopleva A. I. Classification of land based on vegetation cover using deep learning methods for satellite image segmentation. Izvestiya of Saratov University. Earth Sciences, 2026, vol. 26, iss. 3, pp. 176-183. DOI: 10.18500/1819-7663-2026-26-3-176-183, EDN: GSCKZO

This is an open access article distributed under the terms of Creative Commons Attribution 4.0 International License (CC-BY 4.0).
Full text:
download
(downloads: 34)
Language: 
Russian
Heading: 
Geography
Article type: 
Article
UDC: 
502.63:528.854
DOI: 
10.18500/1819-7663-2026-26-3-176-183
EDN: 
GSCKZO

Classification of land based on vegetation cover using deep learning methods for satellite image segmentation

Autors: 
Ogneva Marina V., Saratov State University
Shlapak Pavel Aleksandrovich, Saratov State University
Konopleva Alyona I., Saratov State University
Abstract: 

This paper examines the application of deep learning methods for the automatic segmentation of satellite images with the aim of classifying land cover types based on their degree of vegetation cover. Three-channel satellite images and vector polygons annotated by experts were used as input data, including classes such as fields, fallow land, various types of tree and shrub vegetation, water bodies, and man-made objects. To solve the segmentation problem, the U-Net and DeepLabv3+ architectures were applied with a pre-trained ResNet50 encoder using combined loss functions. As a result of the experiments, the DeepLabv3+model with the ComboLoss function demonstrated the best segmentation quality metrics. The practical outcome of this work was the implementation of a plugin for the QGIS geographic information system, enabling automatic segmentation and vectorization of satellite data. The proposed approach can be used for land monitoring, landscape change analysis, and decision support in the field of natural resource management.

Key words: 
segmentation
deep learning
satellite imagery
remote sensing
U-Net
DeepLabv3+
landuse
agriculture
forest vegetation
Reference: 
  1. Foley J. A., DeFries R., Asner G. P., Barford C., Bonan G., Carpenter S. R., Chapin F. S., Coe M. T., Daily G. C., Gibbs H. K., Helkowski J. H., Holloway T., Howard E. A., Kucharik C. J., Monfreda C., Patz J. A., Prentice I. C., Ramankutty N., Snyder P. K. Global consequences of land use // Science. 2005. Vol. 309, № 5734. P. 570–574. https://doi.org/10.1126/science.1111772
  2. Hansen M. C., Potapov P. V., Moore R., Hancher M., Turubanova S. A., Tyukavina A., Thau D., Stehman S. V., Goetz S. J., Loveland T. R., Kommareddy A., Egorov A., Chini L., Justice C. O., Townshend J. R. G. Highresolution global maps of forest cover change // Science. 2013. Vol. 342, № 6160. P. 850–853. https://doi.org/10.1126/science.1244693, EDN: SOHMPX
  3. Огнева М. В., Шлапак П. А., Васильев А. А., Моисеев Д. С. Автоматическое определение лесных пород методами машинного обучения на основе обработки спутниковых снимков // Известия Саратовского университета. Новая серия. Серия : Науки о Земле. 2025. Т. 25, вып. 3. С. 194–200. https://doi.org/10.18500/1819-7663-2025-25-3-194-200, EDN: QMVWVB
  4. Макаров В. З., Гусев В. А., Шлапак П. А., Решетарова Д. А. Выбор оптимального метода распознавания сельскохозяйственных культур по космоснимкам высокого разрешения (на примере саратовского Заволжья) // Известия Саратовского университета. Новая серия. Серия : Науки о Земле. 2020. Т. 20, вып. 3. С. 162–170. https://doi.org/10.18500/1819-7663-2020-20-3-162-170,EDN: EBJEPG
  5. Kamilaris A., Prenafeta-Boldú F. X. Deep learning in agriculture: A survey // Computers and Electronics in Agriculture. 2018. Vol. 147. P. 70–90. https://doi.org/10.1016/j.compag.2018.02.016, EDN: VFAIQR
  6. Pekel J. F., Cottam A., Gorelick N., Belward A. S. Highresolution mapping of global surface water // Nature. 2016. Vol. 540, № 7633. P. 418–422. https://doi.org/10.1038/nature20584, EDN: YWPJEF
  7. Prishchepov A. V., Radeloff V. C., Baumann M., Kuemmerle T., Müller D. Effects of institutional changes on land use: Agricultural land abandonment during the transition from state-command to marketdriven economies in post-Soviet Eastern Europe // Environmental Research Letters. 2012. Vol. 7, № 2. P. 1–13. https://doi.org/10.1088/1748-9326/7/2/024021, EDN: RIEZJL
  8. Федоров А. В., Шлапак П. А., Муженский Д. А. Исследование линейной эрозии путем создания уточненной цифровой модели рельефа на основе SRTM (на примере территории Хвалынского района Саратовской области) // Известия Саратовского университета. Новая серия. Серия : Науки о Земле. 2020. Т. 20, вып. 1. С. 36–40. https://doi.org/10.18500/1819-7663-2020-20-1-36-40, EDN: WLGHXN
  9. Liakos K. G., Busato P., Moshou D., Pearson S., Bochtis D. Machine learning in agriculture: A review // Sensors. 2018. Vol. 18, № 8. Art. 2674. https://doi.org/10.3390/s18082674
  10. Belgiu M., Drăguţ L. Random forest in remote sensing: A review of applications and future directions // ISPRS Journal of Photogrammetry and Remote Sensing. 2016. Vol. 114. P. 24–31. https://doi.org/10.1016/j.isprsjprs.2016.01.011
  11. Данилов В. А., Морозова В. А., Фёдоров А. В., Шлапак П. А. Открытые данные дистанционного зондирования для выявления археологических объектов // Известия Саратовского университета. Новая серия. Серия : Науки о Земле. 2024. Т. 24, вып. 3. С. 150–158. https://doi.org/10.18500/1819-7663-2024-24-3-150-158, EDN: AQYZTX
  12. Ronneberger O., Fischer P., Brox T. U-Net: Convolutional networks for biomedical image segmentation // Lecture Notes in Computer Science. 2015. Vol. 9351. P. 234–241. https://doi.org/10.1007/978-3-319-24574-4_28
  13. Chen L. C., Zhu Y., Papandreou G., Schroff F., Adam H. Encoder–decoder with atrous separable convolution for semantic image segmentation // Proceedings of the European Conference on Computer Vision (ECCV). Munich, 2018. P. 833–851. https://doi.org/10.1007/978-3-030-01234-2_49
  14. Kussul N., Lavreniuk M., Skakun S., Shelestov A. Deep learning classification of land cover and crop types using remote sensing data // IEEE Geoscience and Remote Sensing Letters. 2017. Vol. 14, № 5. P. 778– 782. https://doi.org/10.1109/LGRS.2017.2681128, EDN: YYGEJR
  15. Lee S. H., Han K. J., Lee K., Lee K. J., Oh K. Y., Lee M. J. Classification of Landscape Affected by Deforestation Using High-Resolution Remote Sensing Data and DeepLearning Techniques // Remote Sensing. 2020. Vol. 12, № 20. Art. 3372. https://doi.org/10.3390/rs12203372, EDN: LTDPKM
  16. Wagner F. H., Sanchez A., Tarabalka Y., Lotte R. G., Ferreira M. P., Aidar M. P. M., Gloor E., Phillips O. L., Aragão L. E. O. C. Using the U-net Convolutional Network to Map Forest Types and Disturbance in the Atlantic Rainforest with Very High Resolution Images // Remote Sensing in Ecology and Conservation. 2019. Vol. 5, № 4. P. 360–375. https://doi.org/10.1002/rse2.111
  17. He K., Zhang X., Ren S., Sun J. Deep residual learning for image recognition // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, 2016. P. 770–778. https://doi.org/10.1109/CVPR.2016.90
Received: 
09.04.2026
Accepted: 
16.06.2026
Published: 
30.09.2026