Affiliation:
1. Institute for Information Transmission Problems. A.A. Kharkevich RAS
Abstract
The paper considers the problem of classification of agricultural crops. As is known, to solve this problem, it is much more efficient to use not instantaneous remote sensing data or calculated vegetation indices, but their historical series. Time series formed by index values for a fixed spatial point at different dates are characterized by a high level of missing values, caused primarily by cloudiness on some dates. A study of known methods of time series approximation has been carried out. The question of whether reducing the dimensionality of the approximated time series can improve the quality of crops classification is also investigated. In the experimental part of the work, NDVI time series calculated from the Sentinel-2 multispectral satellite data were used. The classification of corn, sunflower, wheat and soybeans was studied. The paper shows that UMAP usage for dimensionality reduction leads to 1.5 times increase of classification quality in terms of average the F1-measure compared to using the original dimension data. A new crop classification method based on cubic spline approximation of NDVI time series, extraction of features of low dimension by the UMAP algorithm and their classification by the k nearest neighbors method is proposed.
Publisher
The Russian Academy of Sciences
Reference29 articles.
1. Bartalev S.A., Lupyan E.A., Nejshtadt I.A., Savin I.Yu. Klassifikatsiya nekotorykh tipov sel’skokhozyaistvennykh posevov v yuzhnykh regionakh Rossii po sputnikovym dannym MODIS [Classification of some types of agricultural crops in the southern regions of Russia according to MODIS satellite data.]. Issledovanie Zemli iz kosmosa [Earth exploration from space]. 2006. V. 3. P. 68–75 (in Russian).
2. Bakhtadzel N., Maximov E., Maximova N., Donchan D., Kuznetsov D., Zakharov E. Intelligent Management Systems for Digital Farming. Part 1. Informacionnye tekhnologii i vychislitel’nye sistemy [Information technologies and computing systems]. 2020. V. 2. P. 99–111. https://doi.org/10.14357/20718632200208
3. Blokhina S.Yu. The application of remote sensing in precision agriculture. Vestnik of the Russian agricultural science. 2018. (5). P. 10–16 (in Russian). https://doi.org/10.30850/vrsn/2018/5/10-16
4. Bocharov D.A., Nikolaev D.P., Pavlova M.A., Timofeev V.A. Cloud Shadows Detection and Compensation Algorithm on Multispectral Satellite Images for Agricultural Regions. JCTE.2022. V. 67. № 6. P. 728–739. https://doi.org/10.1134/S1064226922060171
5. Vorob’eva N.S., Chernov A.V. Approksimatsiya vremennykh ryadov NDVI v zadache rannego raspoznavaniya vidov sel’skokhozyaistvennykh kul’tur po kosmicheskim snimkam [Approximation of NDVI time series in the problem of early recognition of crop species from satellite images]. Sbornik trudov III mezhdunarodnoi konferentsii i molodezhnoi shkoly “Informatsionnye tekhnologii i nanotekhnologii” (ITNT-2017)-Samara: Novaya tekhnika [Proceedings of the III International Conference and Youth School “Information Technology and Nanotechnology” (ITNT-2017) – Samara: New technology]. Samara. 2017. P. 390–399 (in Russian).