ISSN 2070-7401 (Print), ISSN 2411-0280 (Online)
Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa


Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2023, Vol. 20, No. 2, pp. 155-165

Recognition of crops in Khabarovsk Krai using NDVI and EVI

L.V. Illarionova 1 , A.S. Stepanov 2 , E.A. Fomina 1 
1 Computing Center FEB RAS, Khabarovsk, Russia
2 Far Eastern Agricultural Research Institute, Khabarovsk, Russia
Accepted: 15.03.2023
DOI: 10.21046/2070-7401-2023-20-2-155-165
The development of approaches to the identification and classification of crops at the regional level is one of the most important tasks of digital farming. The solution of this problem using remote sensing data is especially important for the southern part of Far East, which is due to differences in the timing of sowing, harvesting, the duration of the vegetation phases of crops in the macroregion in comparison with the western part of the Russian Federation, and, accordingly, a decrease in the accuracy of existing algorithms. To carry out the classification, data on the crop rotation of agricultural fields of the Khabarovsk region with a total area of more than 4000 hectares were used, 8 classes of arable land were studied. We reviewed 37 multispectral images with a resolution of 20 m obtained from Sentinel 2A/B satellites from April to October 2021. For each of the pixels, time series of NDVI (Normalized Difference Vegetation Index) and EVI (Enhanced Vegetation index) values were formed, and approximate seasonal variation curves were constructed using the Fourier function. The best machine learning classification results were achieved using Random Forest, with an overall accuracy of 95 %. There were no significant differences in the accuracy of classification when using the values of different indices as input data — NDVI and EVI. According to the results of cross-validation, it was found that the accuracy of recognition of the main classes is at a high level: the error in determining the classes of soy, buckwheat, fallow, steam and perennial grasses did not exceed 10 %. The results obtained confirmed the possibility of using NDVI and EVI to classify arable lands in the southern part of Far East, while the curves of the seasonal course of this particular region should be considered as a base, which is due to the peculiarities of the vegetation cycles of crops.
Keywords: classification, recognition, arable land, vegetation index, Far East, machine learning, approximation
Full text


  1. Arzamastseva N. V., Prokhorova N. V., Khamidova L. L., Problem of the accuracy and completeness of information on the state and use of agricultural land, Izvestiya Timiryazevskoi sel’skokhozyaistvennoi akademii, 2021, No. 3, pp. 119–128 (in Russian), DOI: 10.26897/0021-342X-2021-3-119-128.
  2. Bulanov K. A., Denisov P. V., Lupyan E. A., Martyanov A. S., Sereda I. I., Troshko K. A., Tolpin V. A., Bartalev S. A., Khvostikov S. A., Remote sensing unit of Integrated Federal Information System on Agricultural Lands, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2019, Vol. 16, No. 3, pp. 171–182 (in Russian), DOI: 10.21046/2070-7401-2019-16-3-171-182.
  3. Loupian E., Savin I., Bartalev S., Tolpin V., Balashov I., Plotnikov D., Satellite service for vegetation monitoring VEGA, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2011, Vol. 8, No. 1, pp. 190–198 (in Russian).
  4. Loupian E. A., Bartalev S. A., Tolpin V. A., Zharko V. O., Krasheninnikova Yu. S., Oksyukevich A. Yu., VEGA satellite service applications in regional remote monitoring systems, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2014, Vol. 11, No. 3, pp. 215–232 (in Russian).
  5. Miklashevich T. S., Bartalev S. A., Plotnikov D. E., Interpolation algorithm for the recovery of long satellite data time series of vegetation cover observation, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2019, Vol. 16, No. 6, pp. 143–154 (in Russian), DOI: 10.21046/2070-7401-2019-16-6-143-154.
  6. Plotnikov D. E., Kolbudaev P. A., Bartalev S. A., Loupian E. A., Automated annual cropland mapping from reconstructed time series of Landsat data, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2018, Vol. 15, No. 2, pp. 112–127 (in Russian), DOI: 10.21046/2070-7401-2018-15-2-112-127.
  7. Yakushev V. P., Zakharyan Yu. G., Blokhina S. Yu., Current problems and prospects for the use of remote sensing of the Earth in agriculture, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2022, Vol. 19, No. 1, pp. 287–294 (in Russian), DOI: 10.21046/2070-7401-2022-19-1-287-294.
  8. Bartalev S., Egorov V., Loupian E., Khvostikov S., A new locally-adaptive classification method LAGMA for large-scale land cover mapping using remote-sensing data, Remote Senseng Letters, 2014, Vol. 5, No. 1, pp. 55–64, DOI: 10.1080/2150704X.2013.870675.
  9. Bellon B., Begue A., Lo Seen D., Lebourgeois V., Evangelista B. A., Simoes M., Ferraz R., Improved regional-scale Brazilian cropping systems’ mapping based on a semi-automatic object-based clustering approach, Intern. J. Applied Earth Observation and Geoinformation, 2018, Vol. 68, pp. 127–138, DOI: 10.1016/j.jag.2018.01.019.
  10. Chen Y., Lu D., Moran E., Batistella M., Dutra L., Del’Arco L., da Silva R., Huang J., Luiz A., de Oliveira M., Mapping croplands, cropping patterns, and crop types using MODIS time-series data, Intern. J. Applied Earth Observation and Geoinformation, 2018, Vol. 69, pp. 133–147, DOI: 10.1016/j.jag.2018.03.005.
  11. Griffiths P., Nendel C., Hostert P., Intra-annual reflectance composites from Sentinel 2 and Landsat for national-scale crop and land cover mapping, Remote Sensing of Environment, 2019, Vol. 220, pp. 135–151, DOI: 10.1016/j.rse.2018.10.031.
  12. Feyisa G. L., Palao L. K., Nelson A., Gumma M. K., Paliwal A., Win K. T., Nge K. H., Johnson D. E., Characterizing and mapping cropping patterns in a complex agro-ecosystem: An iterative participatory mapping procedure using machine learning algorithms and MODIS vegetation indices, Computers and Electronics in Agriculture, 2020, Vol. 175, Art. No. 105595, DOI: 10.1016/j.compag.2020.105595.
  13. Hao P., Tang H., Chen Z., Meng Q., Kang Y., Early-season crop type mapping using 30-m reference time series, J. Integrative Agriculture, 2020, Vol. 19, No. 7, pp. 1897–1911, DOI: 10.1016/S2095-3119(19)62812-1.
  14. Liu J., Shang J., Qian B., Huffman T., Zhang Y., Dong T., Jing Q., Martin T., Crop yield estimation using time-series MODIS data and the effects of cropland masks in Ontario, Canada, Remote Sensing, 2019, Vol. 11, Art. No. 2419, DOI: 10.3390/rs11202419.
  15. Tolpin V., Loupian E., Bartalev S., Plotnikov D., Matveev A., Possibilities of agricultural vegetation condition analysis with the “VEGA” satellite service, Atmospheric and Oceanic Optics, 2014, Vol. 27, pp. 581–586.
  16. Tufail R., Ahmad A., Javed M., Sajid R., A machine learning approach for accurate crop type mapping using combined SAR and optical time series data, Advances in Space Research, 2021, Vol. 69, Issue 1, pp. 331–346, DOI: 10.1016/j.asr.2021.09.019.
  17. Yan S., Yao X., Zhu D., Liu D., Zhang L., Yu G., Gao B., Yang J., Yun W., Large-scale crop mapping from multi-source optical satellite imageries using machine learning with discrete grids, Intern. J. Applied Earth Observation and Geoinformation, 2021, Vol. 103, Art. No. 102485, DOI: 10.1016/j.jag.2021.102485.
  18. Zhang H., Kang J., Xu X., Zhang L., Accessing the temporal and spectral features in crop type mapping using multi-temporal Sentinel 2 imagery: A case study of Yi’an County, Heilongjiang province, China, Computers and Electronics in Agriculture, 2020, Vol. 176, Art. No. 105618, DOI: 10.1016/j.compag.2020.105618.