Журнал

About Editorial Board Information for authors and reviewers Publication ethics Contacts User Account: send / review a manuscript
Archive
Volume 21, 2024
Number 1 Number 2 Number 3 Number 4 Number 5
Volume 20, 2023
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 19, 2022
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 18, 2021
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 17, 2020
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 16, 2019
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 15, 2018
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 14, 2017
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 13, 2016
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 12, 2015
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 11, 2014
Number 1 Number 2 Number 3 Number 4
Volume 10, 2013
Number 1 Number 2 Number 3 Number 4
Volume 9, 2012
Number 1 Number 2 Number 3 Number 4 Number 5
Volume 8, 2011
Number 1 Number 2 Number 3 Number 4
Volume 7, 2010
Number 1 Number 2 Number 3 Number 4
Issue 6, 2009
Volume 1 Volume 2
Issue 5, 2008
Volume 1 Volume 2
Issue 4, 2007
Volume 1 Volume 2
Issue 3, 2006
Volume 1 Volume 2
Issue 2, 2005
Volume 1 Volume 2
Issue 1, 2004
Volume 1
Search
Find:
русский
ISSN 2070-7401 (Print), ISSN 2411-0280 (Online)
Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa
CURRENT PROBLEMS IN REMOTE SENSING OF THE EARTH FROM SPACE

  

Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2021, Vol. 18, No. 2, pp. 51-63

Automated classification of the vegetation cover of Mediterranean landscape using spectral-textural and topographic features of high spatial resolution satellite imagery

A. Khatib 1 , V.A. Malinnikov 1 
1 Moscow State University of Geodesy and Cartography, Moscow, Russia
Accepted: 25.02.2021
DOI: 10.21046/2070-7401-2021-18-2-51-63
The paper considers the results of assessing the reliability of the automated classification of Mediterranean vegetation by random forest and maximum likelihood algorithms using several spectral, texture and topographic features extracted from high spatial resolution multispectral satellite images Landsat (OLI) and digital elevation model (ASTER GDEM 2). The study shows that from a large number of various spectral-textural and topographic features, it is possible to select, with the random forest algorithm, a set of 20 most informative features the use of which increases the overall classification accuracy of vegetation cover by 3.7 % compared to the use of all 36 features. The overall accuracy of vegetation cover classification by random forest and maximum likelihood algorithms using a set of 20 most informative features is 87.3% and 86.4 %, respectively, and this difference in classification reliability is statistically significant at 10% and 5 % significance levels according to the McNemar statistical test based on the Chi-square distribution with Yates’ correction for continuity. At the same time, the estimate of the minimum classification accuracy of all the identified classes of vegetation cover shows that the use of the random forest algorithm gives more reliable results than the maximum likelihood algorithm. This demonstrates the effectiveness of using the random forest algorithm to classify the Mediterranean vegetation, taking into account spectral and topographic features, which is consistent with the results of studies carried out in other territories of the Mediterranean region.
Keywords: automated classification, multispectral space images, digital elevation model, vegetation cover, Mediterranean region, random forest, maximum likelihood, textural features, topographic features, feature importance, McNemar’s test, statistical significance
Full text

References:

  1. Bartalev S. A., Loupian E. A., R&D on methods for satellite monitoring of vegetation by the Russian Academy of Sciences’ Space Research Institute, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2013, Vol. 10, No. 1, pp. 197–214 (in Russian).
  2. 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. (in Russian).
  3. Gavrilyuk E. A., Plotnikova A. S., Plotnikov D. E., Land cover mapping of the Pechora-Ilych Nature Reserve and its vicinity based on reconstructed multitemporal Landsat satellite data, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2018, Vol. 15, No. 5, pp. 141–153 (in Russian).
  4. Malinnikov V. A., Stetsenko A. F., Altynov A. E., Popov S. M., Monitoring prirodnoi sredy aerokosmicheskimi sredstvami (Monitoring the natural environment by aerospace tools), Moscow: MIIGAIK, 2008, 145 p. (in Russian).
  5. Marchukov V. S., Stytsenko E. A., Interpretation of vegetation using spectral-temporal characteristics, Issledovanie Zemli iz kosmosa, 2012, No. 1, pp. 77–88 (in Russian).
  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).
  7. Savinykh V. P., Malinnikov V. A., Tsypina E. M., Sladkopevtsev S. A., Geografiya iz kosmosa (Geography from space), Moscow: MIIGAIK, 2000, 244 p. (in Russian).
  8. Stytsenko E. A., Evaluation of the possibilities to classify agricultural lands using multi-seasonal satellite data processing, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2017, Vol. 14, No. 5, pp. 172–183 (in Russian).
  9. Terekhin E. A., The efficiency of spectral vegetation indices for interpretation agricultural vegetation, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2012, Vol. 9, No. 4, pp. 243–248 (in Russian).
  10. Khatib A., Malinnikov V. A., Interpretation of Mediterranean vegetation in multi-channel space images using digital elevation model data, Izvestiya vuzov ”Geodesy and Aerophotosurveying”, 2019, Vol. 63, No. 4, pp. 432‒439 (in Russian).
  11. Chaban L. N., Metody i algoritmy raspoznavaniya obrazov v avtomatizirovannom deshifrirovanii dannykh distantsionnogo zondirovaniya (Pattern recognition methods and algorithms in automated decrypting of remote sensing data), Moscow: MIIGAIK, 2016, 77 p. (in Russian).
  12. Chistyakov S. P., Random forests: an overview, Trudy Karel’skogo nauchnogo tsentra RAN, 2013, No. 1, pp. 117‒136 (in Russian).
  13. Aaron E., Timothy A., Fang F., Implementation of machine-learning classification in remote sensing: an applied review, Intern. J. Remote Sensing, 2018, Vol. 39, No. 9, pp. 2784–2817.
  14. Belgiu M., Dragut L., Random forest in remote sensing: A review of applications and future directions, ISPRS J. Photogrammetry and Remote Sensing, 2016, Vol. 114, pp. 24–31.
  15. Breiman L., Random Forests, Machine Learning, 2001, Vol. 45, pp. 5–32.
  16. Campbell J., Wynne R., Introduction to Remote Sensing, Fifth Edition, New York: The Guilford Press, 2011, 662 p.
  17. Chen J., Chen Jin, Liao A., Cao X., Chen L., Chen X., He C., Han G., Peng S., Lu M., Zhang W., Tong X., Mills J., Global land cover mapping at 30 m resolution: A POK-based operational approach, ISPRS J. Photogrammetry and Remote Sensing, 2015, Vol. 103, pp. 7–27.
  18. Congalton R., A Review of Assessing the Accuracy of Classifications of Remotely Sensed Data, Remote Sensing of Environment, 1991, Vol. 37, No. 1, pp. 35–46.
  19. Corcoran J., Knight J., Gallant A., Influence of Multi-Source and Multi-Temporal Remotely Sensed and Ancillary Data on the Accuracy of Random Forest Classification of Wetlands in Northern Minnesota, Remote Sensing, 2013, Vol. 5, No. 7, pp. 3212–3238.
  20. Elumnoh A., Shrestha R., Application of DEM Data to Landsat Image Classification: Evaluation in a Tropical Wet-Dry Landscape of Thailand, Photogrammetric Engineering and Remote Sensing, 2000, Vol. 66, No. 3, pp. 297–304.
  21. Foody G., Thematic Map Comparison: Evaluating the Statistical Significance of Differences in Classification Accuracy, Photogrammetric Engineering and Remote Sensing, 2004, Vol. 70, No. 5, pp. 627–633.
  22. Frank T., Mapping Dominant Vegetation Communities in the Colorado Rocky Mountain Front Range with Landsat Thematic Mapper and Digital Terrain Data, Photogrammetric Engineering and Remote Sensing, 1988, Vol. 54, No. 12, pp. 1727–1734.
  23. Franklin S., Terrain Analysis from Digital Patterns in Geomorphometry and Landsat MSS Spectral Response, Photogrammetric Engineering and Remote Sensing, 1987, Vol. 53, No. 1, pp. 59–65.
  24. Gounaridis D., Apostolou A., Koukoulas S., Land cover of Greece, 2010: a semi-automated classification using random forests, J. Maps, 2016, Vol. 12, No. 5, pp. 1055–1062.
  25. Hansen M., Potapov P., Moore R., Hancher M., Turubanova S., Tyukavina A., Thau D., Stehman S., Goetz S., Loveland T., Kommareddy A., Egorov A., Chini L., Justice C., Townshend J., High-Resolution Global Maps of 21st-Century Forest Cover Change, Science, 2013, Vol. 342, No. 6160, pp. 850–853.
  26. Haralick R., Shanmugam K., Dinstein I., Textural features for image classification, IEEE Trans. Systems, Man, and Cybernetics, 1973, Vol. 3, No. 6, pp. 610–621.
  27. Janssen L., Jaarsma M., van der Linden E., Integrating Topographic Data with Remote Sensing for Land-Cover Classification, Photogrammetric Engineering and Remote Sensing, 1990, Vol. 56, No. 11, pp. 1503–1506.
  28. Jin Y., Liu X., Chen Y., Liang X., Land-cover mapping using Random Forest classification and incorporating NDVI time-series and texture: a case study of central Shandong, Intern. J. Remote Sensing, 2018, Vol. 39, No. 23, pp. 1–21.
  29. Krishna B., Improving Landsat and IRS Image Classification: Evaluation of Unsupervised and Supervised Classification through Band Ratios and DEM in a Mountainous Landscape in Nepal, Remote Sensing, 2009, Vol. 1, No. 4, pp. 1257–1272.
  30. Rodriguez-Galiano V., Ghimire B., Rogan J., Chica-Olmo M., Rigol-Sanchez J., An assessment of the effectiveness of a random forest classifier for land-cover classification, ISPRS J. Photogrammetry and Remote Sensing, 2012, Vol. 67, pp. 93–104.
  31. State of Mediterranean Forests, FAO, 2013, 173 p.
  32. Sundseth K., Natura 2000 in the Mediterranean Region, Luxembourg: Office for Official Publications of the European Communities, 2009, 12 p.
  33. Zanter K., Landsat 8 Surface Reflectance Code (LASRC) Product Guide, Department of the Interior U. S., 2018, 34 p.