Implementation of satelite image classification using PyTorch


  • Mishchenko M.
  • Hnatushenko Vik.
  • Sinher Anastasiia-Dzhei



neural network, satellite image, recognition, deep learning, PyTorch.


This article presents a practical implementation of the satellite image classification task using the PyTorch deep learning library. The aim of the work is to develop a neural network model capable of classifying satellite images into four classes: water, sands, clouds, and greenery. The model is trained using the pre-trained ResNet architecture. The proposed approach allows for automatic classification of satellite images, fa-cilitating the analysis of large amounts of data, and has been tested on Sentinel-2 satellite images acquired from March to August 2023 for parts of Kherson and Mykolaiv regions, Ukraine, and achieved an average accuracy of 95%. The presented research demonstrates the practical use of modern deep learning methods, in particular the PyTorch library, to solve actual problems of satellite image analysis and classification.


Hnatushenko, Vi., Hnatushenko, Vo., Soldatenko, D., Heipke, C. (2023): Enhancing the quality of CNN-based burned area detection in satellite imagery through data augmentation. Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLVIII-1/W2-2023, 1749–1755.

Ortega, M. X., Wittich, D., Rottensteiner, F. , Heipke, C., Feitosa, R. Q., 2023. Using time series image data to improve the generalization capabilities of a CNN - The example of deforestation detection with Sentinel-2. In: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences X-1/W1-2023, pp. 961–970.

KAPLAN, G. &AVDAN, U., 2018: Sentinel-1 and Sentinel-2 Data fusion for wetlands mapping: Balikdami, Turkey. ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. XLII-3. 729-734. 10.5194/isprs-archives-XLII-3-729-2018.

Buyukdemircioglu, M., R. Can, and S. Kocaman. "Deep learning based roof type classification using very high resolution aerial imagery." The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences 43 (2021): 55-60.

Tong, Xin-Yi, et al. "Land-cover classification with high-resolution remote sensing images using transferable deep models." Remote Sensing of Environment 237 (2020): 111322.

Zhou, Yue, et al. "Mmrotate: A rotated object detection benchmark using pytorch." Proceedings of the 30th ACM International Conference on Multimedia. 2022.

Wu, Sen, et al. "On the generalization effects of linear transformations in data augmentation." International Conference on Machine Learning. PMLR, 2020.