Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2025, Vol. 22, No. 1, pp. 81-92
Experience of using data from the Meteor-M No. 2 KMSS sensor for cropland monitoring in the south of Khabarovsk Krai
L.V. Illarionova
1 , A.S. Stepanov
2 , K.N. Dubrovin
1 , E.A. Fomina
1 , A.A. Sorokin
1 , A.L. Verkhoturov
1 , V.A. Eliseev
1, 3 1 Computing Center FEB RAS, Khabarovsk, Russia
2 Far Eastern Agricultural Research Institute, Khabarovsk, Russia
3 National Research University Higher School of Economics, Moscow, Russia
Accepted: 29.11.2024
DOI: 10.21046/2070-7401-2025-22-1-81-92
The paper presents the results of using the data of the multizone satellite imagery complex (KMSS) on board the Meteor-M No. 2 satellite for crop mapping in the south of Khabarovsk Krai. The study used 2021–2023 data on crop rotation in Khabarovsk District with a total crop area of more than 21,000 hectares divided between fields of the following 5 classes: soybean, grains, buckwheat, perennial grasses and fallow land. A series of composite images with a spatial resolution of 60 m obtained from KMSS data from May to September of each year were considered. Averaged statistical time series of Normalized Difference Vegetation Index (NDVI) were constructed for individual fields of each class. The indicators (maximum value, day of maximum) and their variability were calculated. A pixel-by-pixel classification based on machine learning using the Random Forest algorithm was carried out and the following estimates were obtained: overall accuracy 0.95, F1 measure 0.87. The accuracy of determining the pixels of soybean, grains, buckwheat, perennial grasses and fallow land was, respectively, 0.98, 0.84, 0.76, 0.83 and 0.93. In general, the obtained results allow considering KMSS images useful in solving problems of cropland classification, including in the territory of Khabarovsk Krai.
Keywords: classification, machine learning, cropland, Khabarovsk Krai, KMSS, monitoring
Full textReferences:
- Kashnitskii A. V., Loupian E. A., Plotnikov D. E., Tolpin V. A., Analysis of the possibility of using different spatial resolution data for objects monitoring, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2023, V. 20, No. 2, pp. 60–74 (in Russian), DOI: 10.21046/2070-7401-2023-20-2-60-74.
- Kirsanov A. D., Komarov A. A., Using the NDVI index to assess the development of perennial grasses under conditions of spatial and temporal heterogeneity, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2024, V. 21, No. 2, pp. 143–155 (in Russian), DOI: 10.21046/2070-7401-2024-21-2-143-155.
- Loupian E. A., Proshin A. A., Bourtsev M. A. et al., Experience of development and operation of the IKI-Monitoring center for collective use of systems for archiving, processing and analyzing satellite data, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2019, V. 16, No. 3, pp. 151–170 (in Russian), DOI: 10.21046/2070-7401-2019-16-3-151-170.
- Panov D. Yu., Sakharova E. Yu., Romas’ko V. Yu., Rublev I. V., Forecasting the expected yield of grain crops based on the data of the Meteor-M spacecraft No. 2-2, Materialy 21-i Mezhdunarodnoi konferencii “Sovremennye problemy distancionnogo zondirovaniya Zemli iz kosmosa” (Proc. 21 th Intern. Conf. “Current Problems in Remote Sensing of the Earth from Space”), Moscow: IKI RAS, 2023, p. 393 (in Russian), DOI: 10.21046/21DZZconf-2023a.
- Plotnikov D. E., Kolbudaev P. A., Zhukov B. S. et al., The collection of multispectral KMSS-M (Meteor-M No. 2) satellite data aimed at quantitative assessment of the Earth surface, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2020, V. 17, No. 7, pp. 276–282 (in Russian), DOI: 10.21046/2070-7401-2020-17-7-276-282.
- Plotnikov D. E., Kolbudaev P. A., Yolkina E. S. et al., Remote assessment of biophysical characteristics of vegetation cover based on Meteor-M satellite system (KMSS) data and neural network inversion of the RT model, Materialy 21-i Mezhdunarodnoi konferencii “Sovremennye problemy distancionnogo zondirovaniya Zemli iz kosmosa” (Proc. 21 th Intern. Conf. “Current Problems in Remote Sensing of the Earth from Space”), Moscow: IKI RAS, 2023, p. 100 (in Russian), DOI: 10.21046/21DZZconf-2023a.
- Sidorenkov V. M., Astapov D. O., Rybkin E. S. et al., Possibilities of using the Meteor-M satellite images for determining quantitative and qualitative forests characteristics, Forestry information, 2022, No. 2, pp. 5–12 (in Russian), DOI: 10.24419/LHI.2304-3083.2022.2.0.
- Shatrova K. V., Maglinets Yu. A., Tsibulsky G. M., The model of submission of information on the state and dynamics of lands of agricultural purpose, J. Siberian Federal University. Engineering and Technologies, 2014, V. 7, No. 8, pp. 984–989 (in Russian).
- Blickensdörfer L., Schwieder M., Pflugmacher D. et al., Mapping of crop types and crop sequences with combined time series of Sentinel-1, Sentinel-2 and Landsat-8 data for Germany, Remote Sensing of Environment, 2022, V. 269, Article 112831, DOI: 10.1016/j.rse.2021.112831.
- Dubrovin K., Verkhoturov A., Stepanov A., Aseeva T., Multi-year cropland mapping based on remote sensing data: A case study for the Khabarovsk Territory, Russia, Remote Sensing, 2024, V. 16, No. 9, Article 1633, DOI: 10.3390/rs16091633.
- Erdanaev E., Kappas M., Wyss D., Irrigated crop types mapping in Tashkent Province of Uzbekistan with remote sensing-based classification methods, Sensors, 2022, V. 22, Article 5683, DOI: 10.3390/s22155683.
- Gomez C., White J. C., Wulder M. A., Optical remotely sensed time series data for land cover classification: A review, ISPRS J. Photogrammetry and Remote Sensing, 2016, V. 116, pp. 55–72, DOI: 10.1016/j.isprsjprs.2016.03.008.
- Song X.-P., Huang W., Hansen M. C., Potapov P., An evaluation of Landsat, Sentinel-2, Sentinel-1 and MODIS data for crop type mapping, Science of Remote Sensing, 2021, V. 3, Article 100018, DOI: 10.1016/j.srs.2021.100018.