Retrospective regional level land cover map for Ukraine: methodology of development and results analysis

1Kussul, N, 2Shelestov, A, 3Skakun, S, 4Basarab, R, 2Yaylimov, B, 5Lavreniuk, MS, 6Kolotii, A, 2Yashchuk, D
1Space Research Institute of the National Academy of Science of Ukraine and the National Space Agency of Ukraine, Kyiv, National Technical University of Ukraine «Kyiv Polytechnic Institute», Kyiv, Ukraine
2Space Research Institute of the National Academy of Science of Ukraine and the National Space Agency of Ukraine, Kyiv, Ukraine, National University of Life and Environmental Sciences of Ukraine, Kyiv, Ukraine
3Integration-Plus LTD
4Space Research Institute of the National Academy of Sciences of Ukraine and the State Space Agency of Ukraine, Kyiv, Integration-Plus LTD, Kyiv, Ukraine
5Space Research Institute of the National Academy of Sciences of Ukraine and the National Space Agency of Ukraine, Kyiv, Taras Shevchenko National University of Kyiv, Kyiv, Ukraine
6Space Research Institute of the National Academy of Science of Ukraine and the National Space Agency of Ukraine, Kyiv, National University of Life and Environmental Sciences of Ukraine, Kyiv, Ukraine
Kosm. nauka tehnol. 2015, 21 ;(3):31–39
https://doi.org/10.15407/knit2015.03.031
Publication Language: Ukrainian
Abstract: 

This paper presents the methodology of retrospective land cover mapping for Ukrainian territory. Proposed methodology is based on intelligent processing techniques of satellite data, namely neural network classification of time series of Landsat-4, Landsat-5, Landsat-7 imagery (with 30m spatial resolution). As the result of its implementation we've obtained land cover maps for all Ukrainian territory over 1990, 2000 and 2010 years with the average accuracy of 95 % (produced on independent test set)

Keywords: classification, mapping, neural networks, remote sensing, satellite imagery
References: 

1.  Geoportal ESA CCI Land Cover products: a new generation of satellite-derived global land cover products. Retrieved from http://maps.elie.ucl.ac.be/CCI/viewer/index.php

2. Geoportal Geologichnoi' sluzhby SShA  (United States Geological Survey).  Retrieved from http://earthexplorer.usgs.gov

3. State Statistics Service of Ukraine: Statistical Yearbook of Ukraine for 2010, 560 p. (TOV «Avgust Trejd», Kyiv, 2011) [in Ukrainian].

4.  Lyalko V. I. (Ed.)  Earth systems change over Eastern Europe,  582 p. (Kiev, 2010) [in Russian].

5.  Skakun S. V., Shelestov A. Ju., Jajlymov B. Ja. et al. Classification of agricultural crops using satellite data time series. Induktyvne modeljuvannja skladnyh system. Issue 6,  157—166 (2014) [in Ukrainian].

6.  Chander G., Markham B., Helder D. Summary of current radiometric calibration coefficients for Landsat MSS, TM, ETM+, and EO-1 ALI sensors.  Remote Sens. Environ.   113, 893—903 (2009)

7. Chen J., Liao A., Cao X., et al. Global land cover mapping at 30m resolution: A POK-based operational approach.  ISPRS J. Photogrammetry and Remote Sens.  103, 7—27 (2015)

8. Foody G. Status of land cover classification accuracy assessment.  Remote Sens. Environ.  80 (1), 185—201 (2002)

9. Gallego J., Kussul N., Skakun S., et al. Efficiency assessment of using satellite data for crop area estimation in Ukraine. Int. J. Appl. Earth Observation and Geoinform. 29, 22—30 (2014)

10. Giria C., Pengrab B., Longc J., Lovelanda T. R. Next generation of global land cover characterization, mapping, and monitoring.  Int. J. Appl. Earth Observation and Geoinform.  25, 30—37 (2013)

11. Kussul N., Skakun S., Shelestov A., et al. Crop clasification in Ukraine using satellite optical and SAR images.  Models and Analyses.  2 (2), 118—128 (2013)

12. Kussul N., Skakun S., Shelestov A., Lavreniuk M. Large scale crop classification in Ukraine using multi-temporal Landsat-8 images with missing data.  American Geophysical Union Fall Meeting (AGU 2014), (San Francisco, USA, December 15-19, 2014)

13. Kussul N., Shelestov A., Skakun S. Grid and sensor web technologies for environmental monitoring.  Earth Sci. Inform.  2, (1-2). 37—51 (2009).

14. Kussul N., Shelestov A., Skakun S. Technologies for satellite data processing and management within international disaster monitoring projects.  Grid and Cloud Database Management, Fiore S., Aloisio G. (Eds.),  279—306 (Springer, 2011).

15. Lavreniuk M., Kussul N., Skakun S.  Integrated use of multi-temporal SAR and optical satellite imagery for crop mapping in Ukraine.  American Geophysical Union Fall Meeting (AGU 2014). (San Francisco, USA, December 15—19, 2014)

16. Lucas survey European statisticians monitor territory.  Retrieved from http://www.uni-mannheim.de/edz/pdf/eurostat/03/KS-AZ-03-001-EN-N-EN.pdf

17. Olofsson P., Foody G. M., Herold M., et al. Good practices for estimating area and assessing accuracy of land change.  Remote Sens. Environ.  148, 42—57 (2014).

18. Sánchez J. S., Barandela R., Marqués A. I. Analysis of new techniques to obtain quality training sets.  Pattern Recognit Lett. 24 (7), 1015—1022 (2003)

19. Shelestov A., Kussul N., Skakun S. Grid technologies in monitoring systems based on satellite data.  J. Automation and Inform. Sci.  38 (3),  69—80 (2006).

20. Skakun S., Kussul N., Basarab R. Dealing with missing data in remote sensing images within land and crop classification.  40th COSPAR Scientific Assembly, (2—10 August 2014, in Moscow, Russia)  P. 3—14 (2014).

21. Skakun S., Kussul N., Basarab R. Restoration of missing data due to clouds on optical satellite imagery using neural networks.  ESA SENTINEL-2 for Science Workshop, ESA-ESRIN, Frascati, Rome, Italy, 20-22 May 2014. Available at: http://seom.esa.int/S2forScience2014/files/05_S2forScience-MethodsI_KUSSUL.pdf

22. Skakun S. V., Basarab R. M. Reconstruction of missing data in time-series of optical satellite images using self-organizing Kohonen Maps. J. Automation and Inform. Sci.  46 (12), 19—26 (2014)

23. Warmerdam F. The geospatial data abstraction library. Open Source Approaches in Spatial Data Handling, Eds.: G.B. Hall, M.G. Leahy. Vol. 2, P. 87—104 (Springer, Berlin, 2008)