DOI: 
10.22389/0016-7126-2022-985-7-25-38
1 Yamashkin S.A.
2 Yamashkin A.A.
Year: 
№: 
985
Pages: 
25-38

National Research Ogarev Mordovia State University

1, 
2, 
Abstract:
The authors describe an approach aimed at improving the efficiency of machine learning models in solving the task of classifying metageosystems, which enables overcoming the limitations imposed on the use of convolutional neural network ones. The presented solution is based on the use of superficial fully connected patterns trained on a set of information territorial descriptors to be integrated based on data from different sources. A technique for constructing a complex territorial descriptor, calculated on the basis of satellite imagery data, a digital elevation model and an electronic landscape map, was developed, which makes it possible to achieve classification accuracy comparable to that of convolutional models within a specific task. An advantage of the approach proposed in the article for enhancing the efficiency of machine learning models in solving the task of classifying metageosystems is the stability of the developed solution in the face of labeled data shortage as well as the possibility of reuse in the study of new territorial systems, subject to additional training and fine tuning. The proposed method can be used to solve the task of automated monitoring the changes in the land use structure and geophysical envelope as well as automated validation of digital maps of a significant territorial coverage.
The study was supported by the Russian Science Foundation, grant No. 22-27-00651 (https://rscf.ru/en/project/22-27-00651/).
References: 
1.   Myasnikov V. V. Opisanie izobrazhenii s ispol'zovaniem model'no-orientirovannykh deskriptorov. Komp'yuternaya optika, 2017, no. 41 (6), pp. 888–896. DOI: 10.18287/2412-6179-2017-41-6-888-896.
2.   Sergeev V. V., Yuz'kiv R. R. Parametricheskaya model' avtokorrelyatsionnoi funktsii kosmicheskikh giperspektral'nykh izobrazhenii. Komp'yuternaya optika, 2016, no. 40 (3), pp. 416–421.
3.   Sochava V.B. Vvedenie v uchenie o geosistemah. Novosibirsk: Nauka, 1978, 320 p.
4.   Bengio Y., LeCun Y. (2007) Scaling learning algorithms towards AI. Large-scale kernel machines, no. 34 (5), pp. 1-41.
5.   Chollet F. (2017) Xception: Deep learning with depthwise separable convolutions. Proceedings of the IEEE conference on computer vision and pattern recognition. Honolulu, USA. pp. 1251-1258. DOI: 10.1109/CVPR.2017.195.
6.   Ioffe S., Szegedy C. (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv: 1502.03167 [cs. LG]. URL: arxiv.org/pdf/1502.03167.pdf (accessed: 26.04.2022).
7.   Jaakkola T., Haussler D. (1998) Exploiting generative models in discriminative classifiers. Advances in neural information processing systems, no. 11, pp. 487Р493.
8.   LeCun Y., Bengio Y., Hinton G. (2015) Deep learning. Nature, no. 521 (7553), pp. 436. DOI: 10.1038/nature14539.
9.   S?nchez J., Perronnin F., Mensink T., Verbeek J. (2013) Image classification with the Fisher vector: theory and practice. International journal of computer vision, no. 105 (3), pp. 222Р245. DOI: 10.1007/s11263-013-0636-x.
10.   Schowengerdt R. A. (2006) Remote sensing: models and methods for image processing, 3 ed. Academic Press, Orlando, 843 p.
11.   Urbanowicz R. J., Meeker M., La Cava W., Olson R. S., Moore J. H. (2018) Relief-based feature selection: introduction and review. Journal of biomedical informatics, no. 85, pp. 189Р203. DOI: 10.1016/j.jbi.2018.07.014.
12.   Yamashkin S. A., Yamashkin A. A., Zanozin V. V., Radovanovic M. M., Barmin A. N. (2020) Improving the еfficiency of deep learning methods in remote sensing data analysis: geosystem approach. IEEE Access, no. 8, pp. 179516Р179529. DOI: 10.1109/ACCESS.2020.3028030.
13.   Zhang W., Tang P., Zhao L. (2019) Remote sensing image scene classification using CNN-CapsNet. Remote Sensing, Volume 11, no. 494, DOI: 10.3390/rs11050494.
Citation:
Yamashkin S.A., 
Yamashkin A.A., 
(2022) Classification of metageosystems using machine learning models. Geodesy and cartography = Geodezia i Kartografia, 83(7), pp. 25-38. (In Russian). DOI: 10.22389/0016-7126-2022-985-7-25-38
Publication History
Received: 26.04.2022
Accepted: 08.07.2022
Published: 20.08.2022

Content

2022 July DOI:
10.22389/0016-7126-2022-985-7

QR-code page

QR-код страницы