2518-1092Research result. Information technologies2518-109210.18413/2518-1092-2020-5-2-0-32072INFORMATION SYSTEM AND TECHNOLOGIESALGORITHM OF MULTI-SPECTRAL SATELLITE  DATA PREPARATION FOR AGRICULTURAL CROP  CLASSIFICATIONALGORITHM OF MULTI-SPECTRAL SATELLITE  DATA PREPARATION FOR AGRICULTURAL CROP  CLASSIFICATIONKononovViktor MitrofanovichKononovViktor Mitrofanovichkononov@1cps.ruAsadullaevRustam GennadievichAsadullaevRustam Gennadievichasadullaev@bsu.edu.ruKuzmenkoNikolay IvanovichKuzmenkoNikolay Ivanovichn.kuzmenko31@yandex.ru20205200

The article describes a developed algorithm of multispectral satellite data preprocessing for agricultural crop classification. The procedure for downloading data from the Copernicus Sentinel-2 satellite from the SentinelHub resource at the geographical coordinates from the shape file with ability to specify parameters that reflect the target data acquisition date is formalized. The algorithm of data preprocessing and augmentation to the format required for analysis by mathematical models of machine learning is described. 

The article describes a developed algorithm of multispectral satellite data preprocessing for agricultural crop classification. The procedure for downloading data from the Copernicus Sentinel-2 satellite from the SentinelHub resource at the geographical coordinates from the shape file with ability to specify parameters that reflect the target data acquisition date is formalized. The algorithm of data preprocessing and augmentation to the format required for analysis by mathematical models of machine learning is described. 

data classificationmachine learninganalysis of multidimensional datasatellite imagesagricultural cropsCopernicus Sentineldata classificationmachine learninganalysis of multidimensional datasatellite imagesagricultural cropsCopernicus SentinelСписок литературы1. Komarova A., Zhuravleva I., Yablokov V. Open-source multispectral remote sensing data for the investigation of plant communities // Principy ekologii. 2016. No. 1 (17). P. 40‒71.2. Gercz Zh.V., Pulatov A.S., Mirshadiev M.M. Spatio-temporal assessment of cover crops in Uzbekistan using remote sensing time series // Aktualnye voprosy nauki. 2015. No. 22. P 66-75.3. Chursin I. N., Philippov D. V., Gorokhova I. N. Practice in the recognition of crops on multispectral high-resolution satellite imagery // Vestnik kompiuternykh i informatsionnykh tekhnologii. 2018. No. 11 (173).P. 22-27.4. Viskovic L., Kosovic I. N., Mastelic T. Crop Classification using Multi-spectral and Multitemporal Satellite Imagery with Machine Learning // 2019 International Conference on Software, Telecommunications and Computer Networks (SoftCOM), Split, Croatia, 2019. P. 1-5.5. Rustowicz R. M. Crop Classification with Multi-Temporal Satellite Imagery // Stanford Project Posters and Reports, Fall 20176.  Kamilaris A., Prenafeta-Boldú, F. X. Deep Learning in Agriculture: A Survey // Computers and Electronics in Agriculture. 2018. No. 147 (1). P. 70-90.7. Shibendu R. Exploring machine learning classification algorithms for crop classification using Sentinel 2 data // ISPRS – International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2019. Vol. XLII-3/W6. P. 573-578.8. Brandt J. Spatio-temporal crop classification of low-resolution satellite imagery with capsule layers and distributed attention. 2019. URL: https://arxiv.org/pdf/1904.10130v1.pdf (date of the application: 15.04.2020)9. The Copernicus Sentinel-2 mission URL: https://sentinels.copernicus.eu/web/sentinel/missions/sentinel-2 (date of the application: 15.04.2020)10. Sentinel Hub URL: https://docs.sentinel-hub.com/ (date of the application: 15.04.2020)