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


Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2018, Vol. 15, No. 5, pp. 154-166

Identification of forest stands and dominant tree species in Penza Region using Sentinel-2 imagery

E.A. Kurbanov 1 , O.N. Vorobev 1 , S.A. Menshikov 1 , L.N. Smirnova 1 
1 Volga State University of Technology, Center of Sustainable Forest Management and Remote Sensing, Yoshkar-Ola, Russia
Accepted: 16.10.2018
DOI: 10.21046/2070-7401-2018-15-5-154-166
Satellite monitoring is essential activity to be carried out in compliance with the requirements of forest legislation, and to provide forest management and inventory. We assessed the suitability of using Sentinel-2 satellite images of the European Space Agency for mapping the tree species structure of forest stands in the Penza Region of Russian Federation. The authors analysed the results of three classification technics: Spectral Angle Mapper (SAM), Support Vector Machines (SVM) and Maximum Likelihood Classification (MLC). During two field seasons of 2016–2017 278 test sites were established in the area of investigated forest districts, most of which (60 %) were used to create training samples for the classification. Eleven thematic classes of forest cover were distinguished on the investigated territory using the method of Spectral Mixed Analyses and the field sample plots. Comparison of the user’s and producer’s accuracy statistics for the newly obtained thematic maps of the forest cover on the territory of Kirillovskoe-Podvyshenskoye and Olshanskoye forestry districts shows that the supervised MLC classification has better accuracy for the majority of chosen land cover classes. This is also confirmed by the classification’s overall accuracy (0.81%) and the Kappa coefficient (0.76) on the maps of the Kirillovskoe-Podvyshenskoye forestry district, as well as the overall accuracy (0.76 %) and the Kappa coefficient (0.72) for the Olshanskoye forestry district of Penza Region. We have found evidence that for the thematic classification of forest cover with the use of Sentinel-2 satellite images, the age groups of forest stand should be taken into account, which makes it possible to distinguish between two classes of pine forests, as well as the class of young plantations of coniferous and deciduous species. The results of the thematic classification and analysis of the satellite data demonstrate a great potential of Sentinel images, having high spatial and temporal resolution, for mapping, forest management and forest inventory of the Russian Federation.
Keywords: remote sensing, Sentinel-2, image classification, thematic mapping, forest cover, Penza Region, state forest inventory
Full text


  1. Bartalev S. A., Egorov V. A., Zharko V. O., Loupian E. A., Plotnikov D. E., Khvostikov S. A., Shabanov N. V., Sputnikovoe kartografirovanie rastitel’nogo pokrova Rossii (Land cover mapping over Russia using Earth observation data), Moscow: IKI RAN, 2016, 208 p.
  2. Bartalev S. A., Stytsenko F. V., Khvostikov S. A., Loupian E. A., Metodologiya monitoringa i prognozirovaniya pirogennoi gibeli lesov na osnove dannykh sputnikovykh nablyudenii (Methodology of post-fire tree mortality monitoring and prediction using remote sensing data), Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2017, Vol. 14, No. 6, pp. 176–193.
  3. Vorob’ev O. N., Kurbanov E. A., Distantsionnyi monitoring vosstanovitel’noi dinamiki rastitel’nosti na garyakh Mariiskogo lesnogo Zavolzh’ya (Remote monitoring of vegetation regeneration dynamics on burnt areas in Mari forest Zavolzhje), Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2017, Vol. 14, No. 2, pp. 124–134.
  4. Elsakov V. V., Marushchak I. O., Spektrozonal’nye sputnikovye izobrazheniya v vyyavlenii trendov klimaticheskikh izmenenii lesnykh fitotsenozov zapadnykh sklonov pripolyarnogo Urala (Spectrazonal satellite images in estimation of climatic trends of forest vegetation on west slopes of subpolar Ural), Komp’yuternaya optika, 2011, Vol. 35, No. 2, pp. 281–286.
  5. Zharko V. O., Bartalev S. A., Egorov V. A., Issledovanie vozmozhnostei otsenki zapasov drevesiny v lesakh Primorskogo kraya po dannym sputnikovoi sistemy Proba-V (Investigation of forest growing stock volume estimation possibilities over Russian Primorsky Krai region using Proba-V satellite data), Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2018, Vol. 15, No. 1, pp. 157–168.
  6. Zhirin V. M., Knyazeva S. V., Eidlina S. P., Zukert N. V., Sezonnaya informativnost’ mnogospektral’nykh kosmicheskikh snimkov vysokogo razresheniya pri izuchenii porodno-vozrastnoi dinamiki lesov (Seasonal informative properties of multispectral high resolution space images for studying of forest species and age dynamics), Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2012, Vol. 9, No. 1. pp. 87–94.
  7. Ivanov A. I., Vlasov A. S., Vlasova T. G., Sashenkova S. A., Drevesnye rasteniya Penzenskoi oblasti (Woody plants of Penza oblast), Penza: RIO PGSKhA, 2012, 299 p.
  8. Kozoderov V. V., Dmitriev E. V., Modeli raspoznavaniya i otsenki sostoyaniya lesnoi rastitel’nosti po giperspektral’nym dannym distantsionnogo zondirovaniya (Models of pattern recognition and parameters estimation for forests using hyper-spectral remote sensing data), Issledovaniya Zemli iz kosmosa, 2017, No. 6, pp. 78–88.
  9. Kurbanov E. A. Vorob’ev O. N., Lezhnin S. A., Gubaev A. V., Polevshchikova Yu. A., Tematicheskoe kartirovanie rastitel’nogo pokrova po sputnikovym snimkam: validatsiya i otsenka tochnosti (Thematic mapping of vegetation cover by satellite images: validation and accuracy assessment), Ioshkar-Ola: Povolzhskii gosudarstvennyi tekhnologicheskii universitet, 2015, 126 p.
  10. Terekhin E. A., Primenenie dannykh sputnikovoi sʺemki dlya analiza mnogoletnikh izmenenii v lesakh Belgorodskoi oblasti (Using remote sensing data for the analysis of long-term changes in the forests of the Belgorod region), Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2013, Vol. 10, No. 2, pp. 70–80.
  11. Clark M. L., Roberts D. A., Ewel J. J., Clark D. B., Estimation of tropical rain forest aboveground biomass with small-footprint lidar and hyperspectral sensors, Remote Sensing of Environment, 2011, Vol. 115. pp. 2931–2942.
  12. Cutler M. E. J., Boyd D. S., Foody G. M., Vetrivel A., Estimating tropical forest biomass with a combination of SAR image texture and Landsat TM data: An Assessment of Predictions Between Regions, ISPRS J. Photogrammetry and Remote Sensing, 2012, Vol. 70, pp. 66–77.
  13. Frampton W. J., Dash J., Watmough G., Milton E. J., Evaluating the capabilities of Sentinel-2 for quantitative estimation of biophysical variables in vegetation, ISPRS J. Photogrammetry and Remote Sensing, 2013, Vol. 82, pp. 83–92.
  14. 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, Vol. 116, pp. 55–72.
  15. Hill M. J., Vegetation index suites as indicators of vegetation state in grassland and savanna: An analysis with simulated Sentinel 2 data for a North American transect, Remote Sensing of Environment, 2013, Vol. 137, pp. 94–111.
  16. Immitzer M., Vuolo F., Atzberger C., First Experience with Sentinel-2 Data for Crop and Tree Species Classifications in Central Europe, Remote Sensing, 2016, Vol. 8, pp. 1–27.
  17. Kane V. R., McGaughey R. J., Bakker J. D., Gersonde R. F., Lutz J. A., Franklin J. F., Comparisons between field- and LiDAR-based measures of stand structural complexity, Canadian J. Forest Research, 2010, Vol. 40, pp. 761–773.
  18. Kangas A., Gobakken T., Puliti S., Hauglin M., Næsset E., Value of airborne laser scanning and digital aerial photogrammetry data in forest decision making, Silva Fennica, 2018, Vol. 52, No. 1, Article ID 9923.
  19. Kuemmerle T., Röder A., Hill J., Separating grassland and shrub vegetation by multidate pixel-adaptive spectral mixture analysis, Intern. J. Remote Sensing, 2006, Vol. 27, pp. 3251–3271.
  20. Kupkova L., Cervena L., Sucha R., Jakesova L., Classification of tundra vegetation in the Krkonose Mts. National Park using APEX, AISA Dual and Sentinel-2A data, European J. Remote Sensing, 2017, Vol. 50, pp. 29–46.
  21. Laurin G. V., Puletti N., Hawthorne W., Liesenberg V., Corona P., Papale D., Chen Q., Valentini R., Discrimination of tropical forest types, dominant species, and mapping of functional guilds by hyperspectral and simulated multispectral Sentinel-2 data, Remote Sensing of Environment, 2016, Vol. 176, pp. 163–176.
  22. Loboda T., Krankina O., Savin I., Kurbanov E., Joanne H., Land Management and the Impact of the 2010 Extreme Drought Event on the Agricultural and Ecological Systems of European Russia, In: Land-Cover and Land-Use Changes in Eastern Europe after the Collapse of the Soviet Union in 1991, Springer, 2017, pp. 173–192.
  23. Lu D., Li G., Moran E., Dutra L., Batistella M., The roles of textural images in improving land-cover classification in the Brazilian Amazon, Intern. J. Remote Sensing, 2014, Vol. 35, pp. 8188–8207.
  24. Rujoiu-Mare M. R., Olariu B., Mihai B. A., Nistor C., Savulescu I., Land cover classification in Romanian Carpathians and Subcarpathians using multi-date Sentinel-2 remote sensing imagery, European J. Remote Sensing, 2017, Vol. 50, pp. 496–508.
  25. Seetharaman K., Palanivel N., Texture characterization, representation, description, and classification based on full range Gaussian Markov random field model with Bayesian approach, Intern. J. Image and Data Fusion, 2013, Vol. 4, pp. 342–362.
  26. Verrelst J., Munoz J., Alonso L., Delegido J., Rivera J. P., Camps-Valls G., Moreno J., Machine learning regression algorithms for biophysical parameter retrieval: Opportunities for Sentinel-2 and-3, Remote Sensing of Environment, 2012, Vol. 118, pp. 127–139.