Журнал

About Editorial Board Information for authors and reviewers Publication ethics Contacts User Account: send / review a manuscript
Archive
Volume 23, 2026
Number 1
Volume 22, 2025
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 21, 2024
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
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, 2026, V. 23, No. 1, pp. 178-193

Mapping of soil acidity of Cis-Salair drained plain soils using archival data and the Random Forest algorithm

N.V. Gopp 1 
1 Institute of Soil Science and Agrochemistry SB RAS, Novosibirsk, Russia
Accepted: 20.11.2025
DOI: 10.21046/2070-7401-2026-23-1-178-193
The results of digital mapping of acidity (pH-H2O) in a 0–30 cm soil layer of the Cis-Salair drained plain (Toguchinsky District, Novosibirsk Region, Russia) are presented using archived soil data, 9 sets of predictors and the Random Forest (RF) algorithm implemented on the Google Earth Engine online platform. Archival data on soil pH for the period from 1983 to 1994 were obtained from the research materials of ZapSibNIIgiprozem (West Siberian State Scientific Research and Design and Survey Institute for Land Management). The simulation was carried out based on a different number of predictors in the set: 92 (all); 37 (relief); 26 (climate); 17 (vegetation); 10 (soil properties); 2 (spatial position); 10 (2 dominant predictors from each group of soil formation factors); 22 (5 dominant predictors from each group of soil formation factors); 42 (10 dominant predictors from each group of soil formation factors). The training dataset (TD) contained information on pH-H2O in the 0–30 cm soil layer for 612 soil profiles, and the validation dataset (VD) for 110 soil profiles. The values of the determination coefficients for models with different sets of predictors for the training sample (R2TD) were in the range of 0.70–0.86, which demonstrates high explanatory power of the models. However, the values of the determination coefficients in the validation sample (R2VD) varied in the range 0.05–0.28, which indicates a weak generalizing ability of models based on independent/new data, i.e. the model explains the variation in soil acidity slightly better than the average value. Reducing the number of predictors in the models to 42 and 22 did not lead to a significant increase in R2TD (0.85 and 0.84, respectively) and R2VD (0.25 and 0.28, respectively) compared with the model with 92 predictors (R2TD = 0.86; R2VD = 0.23). A comparison of all models showed that the model with 22 predictors has the best modeling efficiency indicators: R2TD = 0.84; R2VD = 0.28; RMSEVD = 0.44 (Root Mean Square Error); MAPEVD = 4.8 (Mean Absolute Percentage Error); MAEVD = 0.29 (Mean Absolute Error). The values of pH-H2O of soils ranged from 4.6–8.8. According to the map, the studied soils belong to groups with strongly acidic (5.0–6.0), slightly acidic (6.0–6.5), neutral (6.5–7.5) and slightly alkaline (7.5–8.5) reactions. Highly acidic and slightly acidic soils were found in the soils of the northern, western and southern parts of the Toguchinsky district, whereas the soils of the eastern and partly central parts of the region were characterized by a neutral and slightly alkaline reactions.
Keywords: predictors, SAGA GIS, FABDEM, Landsat-5 TM, SoilGrids, WorldClim, Western Siberia
Full text

References:

  1. Afanas’ev V. N., Tsypin A. P., Ehkonometrika v pakete STATISTICA: uchebnoe posobie po vypolneniyu laboratornykh rabot (Econometrics in STATISTICA package: A textbook on laboratory work), Orenburg: GOU OGU, 2008, 204 p. (in Russian).
  2. Val’kov V. F., Kazeev K. Sh., Kolesnikov S. I., Pochvovedenie: uchebnik dlya vuzov (Soil science: A guidebook for universities), Moscow, Rostov-on-Don: IKTs “MarT”, 2004, 496 p. (in Russian).
  3. Klebanovich N. V., Dynamics of indicators of soil acidity after liming, BarSU Herald. Ser.: Biological Sciences. Agricultural Sciences, 2015, No. 3, pp. 99–105 (in Russian).
  4. Lukin S. V., Monitoring of fertility of agricultural soils in southwestern Central Black Earth Region of Russia, Agricultural Chemistry, 2021, No. 3, pp. 3–14 (in Russian), DOI: 10.31857/S000218812103011X.
  5. Pochvenno-klimaticheskii atlas Novosibirskoi oblasti (Soil and climatic atlas of the Novosibirsk oblast), Novosibirsk: Nauka, Sibirskoe otdelenie, 1978, 122 p. (in Russian).
  6. Shirokikh I. T., Shirokikh A. A., Rodina N. A., Polyanskaya L. M., Burkanova O. A., Effects of soil acidity and aluminum on the structure of microbial biomass in the rhizosphere of barley, Eurasian Soil Science, 2004, V. 37, No. 8, pp. 839–843.
  7. Adeniyi O. D., Brenning A., Bernini A. et al., Digital mapping of soil properties using ensemble machine learning approaches in an agricultural lowland area of Lombardy, Italy, Land, 2023, V. 12, Iss. 2, Article 494, DOI: 10.3390/land12020494.
  8. Brieman L., Random Forests, Machine Learning, 2001, V. 45, pp. 5–32, DOI: 10.1023/A:1010933404324.
  9. Conrad O., Bechtel B., Bock M. et al., System for automated geoscientific analyses (SAGA) v. 2.1.4, Geoscientific Model Development, 2015, V. 8, pp. 1991–2007, DOI: 10.5194/gmd-8-1991-2015.
  10. Dal Molin Ribeiro M. H., dos Santos Coelho L., Ensemble approach based on bagging, boosting and stacking for short-term prediction in agribusiness time series, Applied Soft Computing, 2020, V. 86, Article 105837, DOI: 10.1016/j.asoc.2019.105837.
  11. Defourny P., Lamarche C., Bontemps S. et al., Land cover climate change initiative — product user guide. Version 2.0, European Space Agency, 2017, 105 p., http://maps.elie.ucl.ac.be/CCI/viewer/download/ESACCI-LC-Ph2-PUGv2_2.0.pdf.
  12. Fantappiè M., L’Abate G., Schillaci C., Costantini E. A. C., Digital soil mapping of Italy to map derived soil profiles with neural networks, Geoderma Regional, 2023, V. 32, Article e00619, DOI: 10.1016/j.geodrs.2023.e00619.
  13. Fick S. E., Hijmans R. J., WorldClim 2: new 1-km spatial resolution climate surfaces for global land areas, Intern. J. Climatology, 2017, V. 37, pp. 4302–4315, DOI: 10.1002/joc.5086.
  14. Gelsleichter Y. A., Costa E. M., Cunha dos Anjos L. H., Tosta Marcondes R. A., Enhancing Soil Mapping with Hyperspectral Subsurface Images generated from soil lab Vis-SWIR spectra tested in southern Brazil, Geoderma Regional, 2023, V. 33, Article e00641, DOI: 10.1016/j.geodrs.2023.e00641.
  15. Gorelick N., Hancher M., Dixon M. et al., Google Earth Engine: Planetary-scale geospatial analysis for everyone, Remote Sensing of Environment, 2017, V. 202, pp. 18–27, DOI: 10.1016/j.rse.2017.06.031.
  16. Hawker L., Uhe P., Paulo L. et al., A 30 m global map of elevation with forests and buildings removed, Environmental Research Letters, 2022, V. 17, No. 2, Article 024016, DOI: 10.1088/1748-9326/ac4d4f.
  17. Heung B., Ho H. C., Zhang J. et al., An overview and comparison of machine-learning techniques for classification purposes in digital soil mapping, Geoderma, 2016, V. 265, pp. 62–77, DOI: 10.1016/j.geoderma.2015.11.014.
  18. Huang H., Liu Y., Liu Y. et al., Digital mapping of soil pH and driving factor analysis based on environmental variable screening, Sustainability, 2025, V. 17, Iss. 7, Article 3173, DOI: 10.3390/su17073173.
  19. Malone B. P., McBratney A., Minasny B., Laslett G. M., Mapping continuous depth functions of soil carbon storage and available water capacity, Geoderma, 2009, V. 154, pp. 138–152, DOI: 10.1016/j.geoderma.2009.10.007.
  20. Poggio L., de Sousa L. M., Batjes N. H. et al., SoilGrids 2.0: producing soil information for the globe with quantified spatial uncertainty, SOIL, 2021, V. 7, pp. 217–240, DOI: 10.5194/soil-7-217-2021.
  21. Suleymanov A., Abakumov E., Polyakov V. et al., Estimation and mapping of soil pH in urban landscapes, Geoderma Regional, 2025, V. 40, Article e00919, DOI: 10.1016/j.geodrs.2025.e00919.
  22. World Reference Base for Soil Resources 2006: A framework for international classification, correlation and communication, World Soil Resources Reports No. 103, Rome: FAO, 2006, 145 p., https://www.fao.org/3/a0510e/a0510e.pdf.