Classification of crops by NDVI time series of reduced dimensionality

Author:

Pavlova M. A.1,Sidorchuk D. S.1,Bocharov D. A.1

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).

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3