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


Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2016, Vol. 13, No. 5, pp. 157-166

Mapping of the North-West Caucasus dark-coniferous forests with neural network approach

A.F. Komarova 1, 2 , N.V. Kuksina 3, 2 , A.G. Zudkin 1 
1 Greenpeace Russia, Moscow, Russia
2 M.V. Lomonosov Moscow State University, Moscow, Russia
3 Transparent World, Moscow, Russia
Accepted: 17.07.2016
DOI: 10.21046/2070-7401-2016-13-5-157-166
The article discusses mapping of fir- and spruce-dominated forests through the North-West Caucasus (Adygeya Republic and the southern districts of Krasnodarsky Kray and Karachaevo-Cherkessiya Republic). The project was aimed to mapping the coniferous-dominated forests and assessing the accuracy of the result; it was based on hierarchical approach, Landsat TM images, neural network method and field data. The neural network method is described in detail in the Methods section. The result was validated using the regular 2x2-kilometers network, standard error matrix and kappa. Accuracy comparing to regular network was estimated at 95.9% (kappa 0.81). Dark-coniferous forests occupy 236.9 KHa (about 12% of total region’s forests). The biggest areas of coniferous forests are concentrated in Krasnodar Region due to its vast territory, while Adygeya and Karachaevo-Cherkessiya are leading in terms of relative area of coniferous forests. The presented methodology is based on available data and software and can be reproduced in other regions. The results are useful for mapping and characterization of forest type groups or for analysis of topographic factors of coniferous forests distribution.
Keywords: Abies nordmanniana, Picea orientalis, North-West Caucasus, remote sensing, satellite images, hierarchical approach, Landsat, neural networks
Full text


  1. Bebiya S.M., Pikhtovye lesa Kavkaza, ikh ispol'zovanie i okhrana: Avtoref. diss. dokt. biol. nauk (Caucasian fir forests, the management and conservation: syn. doct. biol. sci. thesis), Moscow, 1999, 64 p.
  2. Bebiya S.M., Pikhtovye lesa Kavkaza (Caucasian fir forests, the management and conservation), Moscow: Izd-vo Mosk. gos. un-ta lesa, 2002, 237 p.
  3. Gerasimov M.V., Kavkazskaya pikhta (Caucasian fir), Moscow-Leningrad: Goslestekhizdat, 1948.
  4. Kurbanov E.A., Vorob'ev O.N., Gubaev A.V., Lezhnin S.A., Polevshchikova Yu.A., Demisheva E.N. Chetyre desyatiletiya issledovanii lesov po snimkam Landsat (Four decades of forest research with the use of Landsat images), Vestnik Povolzhskogo gos. tekh. un-ta. Ser.: Les. Ekologiya. Prirodopol'zovanie, 2014, No. 1, pp. 18−32.
  5. Malysheva N.V., Avtomatizirovannoe deshifrirovanie aerokosmicheskikh izobrazhenii lesnykh nasazhdenii (Automated decoding of aerospace images of forests), Moscow, 2012, 154 p.
  6. Orlov A.Ya., Temnokhvoinye lesa Severnogo Kavkaza (Coniferous forests of North Caucasus), Moscow, 1951, 256 p.
  7. Rysin L.P., Man'ko Yu.I., Bebiya S.M., Pikhtovye lesa Rossii (Fir forests of Russia), Moscow, 2012, 230 p.
  8. Tematik Pro. Modul' tematicheskoi interpretatsii dannykh distantsionnogo zondirovaniya. Rukovodstvo pol'zovatelya (Thematic mapping extension for remote sensed data. User guide), Moscow, 2011, 225 p.
  9. Tembotova F.A., Pshegusov R.Kh., Tlupova Yu.M., Lesa severnogo makrosklona Tsentral'nogo Kavkaza (el'brusskii i terskii varianty poyasnosti) (The forests of North Macroslope of Central Caucasus (Elbrus’s and Terek’s altitudinal zonality variants), In: Raznoobrazie i dinamika lesnykh ekosistem Rossii, Moscow, 2012, pp. 227−251.
  10. Banskota A., Kayastha N., Falkowski M., Wulder M.A., Froese R.E., White J.C., Forest monitoring using Landsat time-series data: A review, Canadian Journal of Remote Sensing, 2014, Vol. 40, No. 5, pp. 362−384.
  11. Fassnacht K.S., Cohen W.B., Spies T.A. Key issues in making and using satellite-based maps in ecology: A primer, Forest Ecology and Management, 2006, Vol. 222, No. 1, pp. 167−181.
  12. Joshi C., De Leeuw J., Skidmore A.K., Van Duren I.C., Van Oosten H., Remotely sensed estimation of forest canopy density: A comparison of the performance of four methods, International Journal of Applied Earth Observation and Geoinformation, 2006, No. 8(2), pp. 84−95.
  13. McRoberts R.E., Cohen W.B., Næsset E., Stehman S.V., Tomppo E.O., Using remotely sensed data to construct and assess forest attribute maps and related spatial products, Scandinavian Journal of Forest Research, 2010, Vol. 25:4, pp. 340−367.
  14. Rogan J., Franklin J., Stow D., Miller J., Woodcock C., Roberts D., Mapping land-cover modifications over large areas: A comparison of machine learning algorithms, Remote Sensing of Environment, 2008, No. 112(5), pp. 2272−2283.
  15. Solomeshch A., Mirkin B., Ishbirdin A., Golub V., Saitov M., Zhuravliova S., Rodwell J., Red Data Book of Plant Communities in the former USSR, Birmingham, 1997, 69 p.
  16. Stefanidou A., Dragozi E., Tompoulidou M., Gitas I.Z., Forest/Non Forest mapping using Landsat Thematic Mapper Imagery and Artificial Neural Networks (ANNs), Vestnik of Volga State Univ. of Tech.. Ser.: Forest. Ecology. Nature Management, 2015, No. 1 (25), pp. 22−33.
  17. Townsend P.A., Walsh S.J. Remote sensing of forested wetlands: application of multitemporal and multispectral satellite imagery to determine plant community composition and structure in southeastern USA, Plant Ecology, 2001, Vol. 157, No. 2, pp. 129−149.