The development of digital models of the soil cover in the western part of Bol’shezemel’skaya tundra

The methods of digital mapping are promising for creating soil maps on difficultly accessible territories. This study was aimed at searching of optimal approaches for digital mapping of the soil cover in poorly studied western part of the Bol’shezemel’skaya tundra on different scales. Medium-scale (1 : 200 000) and small-scale (1 : 1 M) soil maps served as the source of initial information about soils of this region; actual information of the state of the territory was obtained from remote sensing data (Landsat 8 scenes, Aug. 14, 2013) and digital elevation model ASTER GDEM v.2. After extraction of information and the choice of predictors, the analysis of digital soil cover models obtained with the use of different algorithms – Random Forest (RF), Multinomial Logistic Regression (MLR) and Linear Discriminant Analysis (LDA) – was performed. The coefficient of agreement between the newly developed digital models and the initial paper-based soil maps (kappa) was calculated. This test demonstrated that the RF algorithm ensures the best results, so the final digital maps were obtained using it. Averaged kappa values for the compared small- and medium-scale models were as follows: RF – 0.39 and 0.36; MLR – 0.31 and 0.31; and LDA – 0.28 and 0.18, respectively. After the preliminary correction of the initial medium-scale map, the kappa values somewhat increased (RF – 0.39, MLR – 0.35, LDA – 0.30). At the stage of evaluation of digital soil maps obtained with the use of RF algorithm, these maps and the initial soil maps were compared with independent point-size terrain data. The degree of agreement between these data and the new digital soil maps proved to be no less than that for the initial maps. For the initial and digital small-scale maps, it reached 24 and 26 %, respectively; for the initial and digital medium-scale maps, 54 and 43 %, respectively. After the preliminary correction of the initial medium-scale map, the degree of agreement between the digital model and terrain data improved considerably and reached 61 %. This method of digital soil mapping on the basis of analogous data seems to be optimal.

digital soil maps, tundra-taiga ecotone, remote sensing data, Landsat 8, ASTER GDEM, LWCI, NDVI, MNDWI, Random Forest, map evaluation

1. Vekshina V.N., Poisk i verifikatsiya prediktorov pochvoobrazovaniya v lesotundrovoy zone po distantsionnyim dannyim (Search for and verification of soil predictors in the forest-tundra zone on the basis of remote sensing data), Collection of short abstracts of the III Youth Conference Pochvovedenie: Gorizontyi Buduschego 2019 (Proc. Youth Conf. Soil Science: Horizons of the Future 2019), Moscow: V.V. Dokuchaev Soil Science Institute, 2019 [in print].

2. VSEGEI, Vserossiiskiy nauchno-issledovatel’skiy geologicheskiy institut im. A.P Karpinskogo (All-Russian State Research Institute named after Karpinsky), URL: http://www.vsegei.

3. Gerasimov I.P., Egorov V.V., Ivanova E.N., Rozov N.N. (Eds.), USSR State Soil Map, scale 1 : 1 M, Sheet Q-39, Nar’yan-Mar, GUGK, factory No. 4, 1977.

4. Gerasimov I.P., Egorov V.V., Ivanova E.N., Rozov N.N. (Eds.), USSR State Soil Map, scale 1 : 1 M, Sheet Q-40, Pechora, GUGK, factory No. 10, 1982.

5. Dokuchayev P.M., Postroyeniye tsifrovoy pochvennoy karty i kartogrammy ugleroda s ispolzovaniyem metodov tsifrovogo pochvennogo kartografirovaniya (na primere Vyatsko-Kamskoy provintsii dernovo- podzolistykh pochv yuzhnoy taygi): Diss. … kand. biol. nauk (Construction of a digital soil map and carbon map using digital soil mapping methods (by the example of the Vyatka-Kama province of sod-podzolic soils of the southern taiga), Cand. boil. sci. thesis), Moscow: MSU, 2017, 206 p.

6. Zhogolev A.V., Aktualizatsiya regionalnykh pochvennykh kart na osnove sputnikovykh i geoinformatsionnykh tekhnologiy (na primere Moskovskoy oblasti): Diss. … kand agric. nauk (Updating regional soil maps based on satellite and geographic information technologies (by the example of Moscow region), Cand. agric. sci. thesis), Moscow: V.V. Dokuchaev Soil Science Institute, 2016, 203 p.

7. Zaboeva I.V., Ignatenko I.V., Kazakov V.G., Popov V.A., Rubtsov M.D., Rudneva E.N., USSR State Soil Map, Ob’yasnitel’naya zapiska k listu “Nar’yan-Mar” Q -39 (explanatory note to the sheet “Nar’yan-Mar” Q -39), Moscow: V.V. Dokuchaev Soil Science Institute, 1984, 62 p.

8. Kaverin D.A., Shakhtarova O.V., Pastukhov A.V., Mazhitova G.G., Lapteva E.M., Sostavleniye krupnomasshtabnykh pochvennykh kart klyuchevykh uchastkov v tundre i lesotundre severo-vostoka Evropeyskoy Rossii (The large-scale soil maps mapping for key areas in the tundra and forest-tundra of the north-east of European Russia), Geography and Natural Resources, 2012, No. 3, pp.140–146.

9. Konyushkova M.V., Kozlov D.N., Avtomatizirovannyy analiz rasprostraneniya temnotsvetnykh chernozemovidnykh pochv v severnom Prikaspii po dannym kosmicheskoy syemki (na primere Dzhanybekskogo statsionara) (Automated analysis of the distribution of dark-colored chernozem-like soils in the northern Caspian region according to satellite imagery (by the example of the Dzhanybek station)), Arid ecosystems, 2010, Vol. 16, No. 5, pp. 46–56.

10. Lavrinenko I.A., Geobotanicheskoe rajonirovanie Bol’shezemel’skoy tundry i prilegayushchih territoriy. Geobotanicheskoe kartografirovanie (Geobotanical mapping), St. Petersburg: Iz-vo RAS Botanical Institute named after V.L. Komarov, 2013, pp. 74–92.

11. Nauchno-prikladnoy spravochnik po klimatu SSSR (Scientific reference book on climatology of the USSR), Ser. 3, Iss. 1, Arkhangelsk and Volgograd region, Komi ASSR, 1989, Book 1, Leningrad: Gidrometeoizdat, 485 p.

12. Osadchaya G.G., Tumel’N.V., Lokal’nye landshafty kak indikatory geokriologicheskoj zonal’nosti (na primere Evropejskogo severo-vostoka) (Local landscapes as indicators of permafrost zonality (by the example of the European Northeast)), Earth Cryosphere, 2012, Vol. XVI, No. 3, pp. 62–71.

13. Kreida N.A., Soil map, scale 1 : 200,000, Sheet Q-39-V, VI Nar’yan-Mar, Moscow, 1958.

14. Savin I.Yu., Ispolzovaniye sputnikovykh dannykh dlya sostavleniya pochvennykh kart: sovremennyye tendentsii i problemy (Using satellite data for soil mapping: current trends and challenges), Modern problems of remote sensing of the Earth from space, 2016, Vol. 13, No. 6, pp. 29–39.

15. Savin I.Yu., Ovechkin S.V., Ob obnovlenii Srednemasshtabnykh pochvennykh kart (About Upgrading Medium scale Soil Maps), Pochvovedeniye, 2014, No. 10, pp. 1184–1192.

16. Savin I.Yu., Simakova M.S., Sputnikovyye tekhnologii dlya inventarizatsii i monitoringa pochv v Rossii (Satellite technologies for soil inventory and monitoring in Russia), Modern problems of remote sensing of the Earth from space, 2012, Vol. 9, No. 5, pp. 104–115.

17. Sukhacheva E.Yu., Aparin B.F., Andreyeva T.A., Kazakov E.E., Lazareva M.A., Printsipy i metody sozdaniya tsifrovoy srednemasshtabnoy pochvennoy karty Leningradskoy oblasti (Principles and methods for creating a digital medium-scale soil map of the Leningrad Region), Bulletin of St. Petersburg State University, Earth sciences, 2019, Vol. 64, No. 1, pp. 100–113.

18. Abbaszadeh Afshar F., Ayoubi S., Jafari A., The extrapolation of soil great groups using multinomial logistic regression at regional scale in arid regions of Iran, Geoderma, 2018, Vol. 315, pp. 36–48.

19. Abdel-Kader F., Digital soil mapping at pilot sites in the northwest coast of Egypt: A multinomial logistic regression approach, The Egyptian Journal of Remote Sensing and Space Sciences, 2011, Vol. 14, pp. 29–40, DOI: 10.1016/j.ejrs.2011.04.001.

20. Arrouays D., McKenzie N., Hempel J., de Forges A.R., McBratney A. (Eds.), GlobalSoilMap: Basis of the Global Spatial Information System, CRC Press, Balkema, 2014, 494 p.

21. ASTERGDEMv. 2. URL: http://viewfinderpanoramas.org/dem1d.html.

22. Cohen J., A coefficient of agreement for nominal scales, Educ. Psychol. Measurement, 1960, Vol. 20, pp. 37–46.

23. Cohen J., Weighted kappa: Nominal scale agreement with provision for scaled disagreement or partial credit, Psychol. Bull., 1968, Vol. 70, pp. 213–220.

24. Dharumarajan S., Hegde R., Singh S.K., Spatial prediction of major soil properties using random forest techniques – a case study in semi-arid tropics of South India, Geoderma Reg., 2017, Vol. 10, pp. 154–162.

25. Grimm R, Behrens T., Märker M., Elsenbeer H., Soil organic carbon concentrations and stocks on Barro Colorado Island—digital soil mapping using random forests analysis, Geoderma, 2008, Vol. 146, pp. 102–113.

26. Jeune W., Francelino M.R., Eliana de Souza, Elpídio Inácio Fernandes Filho, Rocha G.C., Multinomial logistic regression and random forest classifiers in digital mapping of soil classes in western Haiti, Rev. Bras. Ciênc. Solo, 2018, Vol. 42, pp. 1–20.

27. Kempen B., Brus D.J., Heuvelink G.B.M., Stoorvogel J.J., Updating the 1:50,000 Dutch soil map using legacy soil data: a multinomial logistic regression approach, Geoderma, 2009, Vol. 151, pp. 311–326.

28. Landis J.R., Koch G.G., The measurement of observer agreement for categorical data, Biometrics, 1977, Vol. 33, No. 1, pp. 159–174, DOI: 10.2307/2529310.

29. Meier M., de Souza E., Francelino M.R., Digital Soil Mapping Using Machine Learning Algorithms in a Tropical Mountainous Area, Rev. Bras. Ciênc. Solo, 2018, Vol. 42, pp. 1–22.

30. McBratney A.B., Mendonça Santos M.L., MinasnyB., On Digital Soil Mapping, Geoderma, 2003, Vol. 117, pp. 3–52.

31. Nathan P., Odgers N.P., Wei Sun, McBratney A.B., Minasny B., Clifford D., Disaggregating and harmonising soil map units through resampled classification trees, Geoderma, 2014, Vol. 214–215, pp. 91–100, DOI: 10.1016/j.geoderma.2013.09.024.

32. Pahlavan-Rad M.R., Khormali F., Toomanian N., Brungard C. W., Kiani F., Komaki C.B., Bogaert P., Legacy soil maps as a covariate in digital soil mapping: A case study from Northern Iran, Geoderma, 2016, Vol. 279, pp. 141–148.

33. Piccini C., Marchetti A., Napoli R., Rivieccio R., Multinomial logistic regression with soil diagnostic features and land surface parameters for soil mapping of Latium (Central Italy), Geoderma, 2018, Vol. 352, pp. 385–394, DOI: 10.1016/j.geoderma.2018.09.037.

34. Stum A.K., Boettinger M.A., WhiteR.D., Ramsey R.D., Random Forests Applied as a Soil Spatial Predictive Model in Arid Utah, Digital Soil Mapping, Springer, Dordrecht, The Netherlands, 2010, pp 179–190.

35. Vågen T.G., Winowiecki L.A., Tondoh J.E., Desta L.T., Gumbricht T., Mapping of soil properties and land degradation risk in Africa using MODIS reflectance, Geoderma, 2016, Vol. 263, pp. 216–225.