Журнал

About Editorial Board Information for authors and reviewers Publication ethics Contacts User Account: send / review a manuscript
Archive
Volume 22, 2025
Number 1 Number 2 Number 3 Number 4
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, 2025, V. 22, No. 3, pp. 121-135

Determination of soil organic matter content in Minsk Region of Belarus using gradient boosting classifiers based on satellite data

A.N. Chervan 1 , B. Zhao 1 
1 Belarusian State University, Minsk, Belarus
Accepted: 17.03.2025
DOI: 10.21046/2070-7401-2025-22-3-121-135
One of key indicators of soil degradation processes in agricultural lands is the loss of soil organic matter (SOM). Therefore, methodologies for monitoring the spatial and temporal distribution of SOM are critically important from both ecological and economic perspectives. Currently, remote sensing data, particularly Sentinel-2 satellite imagery, can be used to estimate SOM content in the surface humus-accumulative horizon of arable soils. Using Sentinel-2 data and field soil mapping data from Belarus, the study aimed to analyze the spatial accuracy of SOM content estimation and the results of automated satellite image interpretation, with a focus on Minsk Region of Belarus. A range of analytical methods was employed, including selection of representative spectral bands as model inputs using Spearman’s correlation analysis and gradient boosting classifiers for GIS-based modeling. The proposed approach was evaluated in terms of achieving high-precision and rapid inversion, as well as spatial analysis of SOM content across genetic soil types. The inversion model accuracy was validated using an independent database. Results of the spatial analysis demonstrated that the model, based on Sentinel-2 imagery in bands B6, B7, B8, B8A and B12, most effectively utilized second-order derivatives. The inversion model achieved the highest accuracy (minimum 93.8 %, average 96.2 %), with an RMSE of 0.31 and a Kappa coefficient of 0.985. The lowest SOM content in arable soils was observed in the Berezino District, whereas the highest SOM levels were found in the Lyuban and Soligorsk districts that are characterized by a significant proportion of hydromeliorated agricultural lands.
Keywords: remote sensing, Sentinel-2, soil organic matter content, remote sensing data, gradient boosting classifier
Full text

References:

  1. Klebanovich N. V., Prokopovich S. N., Kharlamova E. V., Experience of compiling soil maps of Belarus in the international WRB system, Zemlya Belarusi, 2011, No. 2, pp. 41–47 (in Russian).
  2. Lapa V. V., Chernysh A. F., Azarenok T. N. et al., Atlas pochv sel’skokhozyastvennykh zemel’ Respubliki Belarus’ (Atlas of agricultural soils of the Republic of Belarus), Minsk: IVC Minfina, 2017, 170 p. (in Russian).
  3. Romanova T. A., Diagnostika pochv Belarusi i ikh klassifikatsiya v sisteme FAO-WRB (Diagnostics of soils of Belarus and their classification in the FAO-WRB system), Minsk: Institute of Soil Science and Agrochemistry of the National Academy of Sciences of Belarus, 2004, 428 p. (in Russian).
  4. Chervan A. N., Tsybulko N. N., Yatsukhno V. M., Methodological approaches and practical application of the results of land/soil degradation assessment in Belarus, Izvestiya Rossiiskoi akademii nauk. Ser. geographicheskaya, V. 86, No. 1, pp. 55–68 (in Russian), DOI: 10.31857/S2587556622010058.
  5. Ahmed Z., Iqbal J., Evaluation of Landsat TM5 multispectral data for automated mapping of surface soil texture and organic matter in GIS, European J. Remote Sensing, 2014, V. 47, No. 1, pp. 557–573, DOI: 10.5721/EuJRS20144731.
  6. Anantha Natarajan V., Sunil Kumar M., Tamizhazhagan V., Chevdumoi R. M., Prediction of soil pH from remote sensing data using gradient boosted regression analysis, J. Pharmaceutical Negative Results, 2022, V. 13, Spec. Iss. 6, pp. 29–36, DOI: 10.47750/pnr.2022.13.S06.005.
  7. Castaldi F., Chabrillat S., Don A., van Wesemael B., Soil organic carbon mapping using LUCAS topsoil database and Sentinel-2 data: An approach to reduce soil moisture and crop residue effects, Remote Sensing, 2019, V. 11, No. 18, Article 2121, DOI: 10.3390/rs11182121.
  8. Chen D., Chang N., Xiao J. et al., Mapping dynamics of soil organic matter in croplands with MODIS data and machine learning algorithms, Science of the Total Environment, 2019, V. 669, P. 844–855, DOI: 10.1016/j.scitotenv.2019.03.151.
  9. Demir S., Sahin E. K., An investigation of feature selection methods for soil liquefaction prediction based on tree-based ensemble algorithms using AdaBoost, gradient boosting, and XGBoost, Neural Computing and Applications, 2023, V. 35, No. 4, pp. 3173–3190, DOI: 10.1007/s00521-022-07856-4.
  10. Diek S., Fornallaz F., Schaepman M. E., De Jong R., Barest Pixel Composite for agricultural areas using Landsat time series, Remote Sensing, 2017, V. 9, No. 12, Article 1245, DOI: 10.3390/rs9121245.
  11. Guo Y. K., Zeng F., Ding M. Q. et al., Research on SPOT-5 image-based soil organic matter content estimation, Applied Mechanics and Materials, 2013, V. 409–410, pp. 246–251, DOI: 10.4028/www.scientific.net/AMM.409-410.246.
  12. Habibi L. N., Komariah K., Ariyanto D. P. et al., Estimation of soil organic matter on paddy field using remote sensing method, SAINS TANAH — J. Soil Science and Agroclimatology, 2019, V. 16, No. 2, pp. 159–168, DOI: 10.20961/stjssa.v16i2.35395.
  13. Kang T.-H., Choi S.-W., Lee C., Chang S.-H., Soil classification by machine learning using a tunnel boring machine’s operating parameters, Applied Sciences, 2022, V. 12, No. 22, Article 11480, DOI: 10.3390/app122211480.
  14. Li X., Ding J., Liu J. et al., Digital mapping of soil organic carbon using Sentinel series data: A case study of the Ebinur Lake watershed in Xinjiang, Remote Sensing, 2021, V. 13, No. 4, Article 769, DOI: 10.3390/rs13040769.
  15. Liu H. J., Zhang M. W., Yang H. X. et al., Invertion of cultivated soil organic matter content combining multi-spectral remote sensing and random forest algorithm, Trans. Chinese Society of Agricultural Engineering, 2020, V. 36, No. 10, pp. 134–140, DOI: 10.11975/j.issn.1002-6819.2020.10.016.
  16. Pan H., Chen Z., de Wit A., Ren J., Joint assimilation of leaf area index and soil moisture from Sentinel-1 and Sentinel-2 data into the WOFOST model for winter wheat yield estimation, Sensors, 2019, V. 19, No. 14, Article 3161, DOI: 10.3390/s19143161.
  17. Sahin E. K., Comparative analysis of gradient boosting algorithms for landslide susceptibility mapping, Geocarto Intern., 2022, V. 37, No. 9, pp. 2441–2465, DOI: 10.1080/10106049.2020.1831623.
  18. Tang S., Du C., Nie T., Inversion estimation of soil organic matter in Songnen Plain based on multispectral analysis, Land, 2022, V. 11, No. 5, Article 608, DOI: 10.3390/land11050608.
  19. Tziachris P., Aschonitis V., Chatzistathis T., Papadopoulou M., Assessment of spatial hybrid methods for predicting soil organic matter using DEM derivatives and soil parameters, CATENA, 2019, V. 174, pp. 206–216, DOI: 10.1016/j.catena.2018.11.010.
  20. Vaudour E., Gomez C., Loiseau T. et al., The impact of acquisition date on the prediction performance of topsoil organic carbon from Sentinel-2 for croplands, Remote Sensing, 2019, V. 11, No. 18, Article 2143, DOI: 10.3390/rs11182143.
  21. Wang X., Han J., Wang X. et al., Estimating soil organic matter content using Sentinel-2 imagery by machine learning in Shanghai, IEEE Access, 2021, V. 9, pp. 78215–78225, DOI: 10.1109/ACCESS.2021.3080689.
  22. Yang R., Rossiter D. G., Liu F. et al., Predictive mapping of topsoil organic carbon in an Alpine environment aided by Landsat TM, PLOS One, 2015, V. 10, No. 10, Article e0139042, DOI: 10.1371/journal.pone.0139042.
  23. Ye Z., Sheng Z., Liu X. et al., Using machine learning algorithms based on GF-6 and Google Earth Engine to predict and map the spatial distribution of soil organic matter content, Sustainability, 2021, V. 13, No. 24, Article 14055, DOI: 10.3390/su132414055.
  24. Yin H., Chen C., He Y. et al., Synergistic estimation of soil salinity based on Sentinel-1 image texture and Sentinel-2 salinity spectral indices, J. Applied Remote Sensing, 2023, V. 17, No. 1, Article 018502, DOI: 10.1117/1.JRS.17.018502.
  25. Zhang L., Wang L., Optimization of site investigation program for reliability assessment of undrained slope using Spearman rank correlation coefficient, Computers and Geotechnics, 2023, V. 155, Article 105208, DOI: 10.1016/j.compgeo.2022.105208.
  26. Zhang M., Zhang M., Yang H. et al., Mapping regional soil organic matter based on Sentinel-2A and MODIS imagery using machine learning algorithms and Google Earth Engine, Remote Sensing, 2021, V. 13, No. 15, Article 2934, DOI: 10.3390/rs13152934.
  27. Zhou T., Geng Y., Chen J. et al., High-resolution digital mapping of soil organic carbon and soil total nitrogen using DEM derivatives, Sentinel-1 and Sentinel-2 data based on machine learning algorithms, Science of the Total Environment, 2020, V. 729, Article 138244, DOI: 10.1016/j.scitotenv.2020.138244.
  28. Zhou T., Geng Y., Ji C. et al., Prediction of soil organic carbon and the C:N ratio on a national scale using machine learning and satellite data: A comparison between Sentinel-2, Sentinel-3 and Landsat-8 images, Science of the Total Environment, 2021, V. 755, Article 142661, DOI: 10.1016/j.scitotenv.2020.142661.