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
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. 39-50

Design of satellite sensing data classification algorithm based on machine learning using the example of granulometric composition of soils in agricultural landscapes of Western Siberia

V.V. Chursin 1, 2 , I.V. Kuzhevskaia 1 , O.E. Merzliakov 1 , T.V. Valevich 1 , K.V. Ruchkina 1 
1 National Research Tomsk State University, Tomsk, Russia
2 Siberian Center of SRC Planeta, Novosibirsk, Russia
Accepted: 25.02.2021
DOI: 10.21046/2070-7401-2021-18-2-39-50
The possibility of using Sentinel-2 images and machine learning algorithms to identify and map the spatial heterogeneity of ground cover from the PSD (particle size distribution) of agricultural land, along with the use of precise farming data is discussed. An array was obtained on the basis of field data comprising satellite images with NDVI values <0.3 and additionally computed indices, including those related to spectral brightness (sensitive to PSD), for training and evaluating binary classification models based on solution trees. The XGBoost algorithm was used to train four binary classification models. For these models, the optimum hyperparameter values were chosen and the most important variables for the classification of each type of soil were determined. The architecture of the neural network, including spectral reflectivity values, calculated indices and effects of binary classification, was suggested as input data. The precision of the designed procedure on the validation set reached 76 %.
Keywords: soil texture, clay content, Copernicus mission, Sentinel, multispectral imagery, gradient boosting, mapping of soils
Full text

References:

  1. Drobysh S. V., Bubnova T. V., Matychenkova O. V., Impact granulometric composition on the spectral reflectivity of the agro-sod-podzolic soils, Pochvovedenie i agrokhimiya, 2013, Vol. 50, No. 1, pp. 126–132 (in Russian).
  2. Shevyrnogov A. P., Botvich I. Yu., Emelyanov D. V., Larko A. A., Vysotskaya G. S., Ivchenko V. K., Demyanenko T. N., Possibilities of experimental field soil cover recognition using ground and satellite data, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2019, Vol. 16, No. 4, pp. 150–160 (in Russian).
  3. Ballabio C., Panagos P., Monatanarella L., Mapping topsoil physical properties at European scale using the LUCAS database, Geoderma, 2016, Vol. 261, pp. 110–123.
  4. Ballabio C., Lugato E., Fernández-Ugalde O., Orgiazzi A., Jones A., Borrelli P., Montanarella L., Panagos P., Mapping LUCAS topsoil chemical properties at European scale using Gaussian process regression, Geoderma, 2019, Vol. 355, Art. No. 113912.
  5. Ben-Dor E., Quantitative remote sensing of soil properties, Advances in Agronomy, 2002, Vol. 75, pp. 173–243.
  6. Brown D. J., Shepherd K. D., Walsh M. G., Mays M. D., Reinsch T. G., Global soil characterization with VNIR diffuse reflectance spectroscopy, Geoderma, 2006, Vol. 132, No. 3–4, pp. 273–290.
  7. Caruana R., Niculescu-Mizil A., An empirical comparison of supervised learning algorithms, Proc. 23rd Intern. Conf. Machine Learning, 2006, pp. 161–168, DOI: 10.1145/1143844.1143865.
  8. El-Gammal M. I., Ali R. R., Samra R. A., NDVI threshold classification for detecting vegetation cover in Damietta governorate, Egypt, J. American Science, 2014, Vol. 10, No. 8, pp. 108–113.
  9. Gatti A., Bertolini A., Sentinel-2 Products Specification Document, ESA, 2015, Issue 13.1, 496 p.
  10. Ge Y., Thomasson J. A., Wavelet incorporated spectral analysis for soil property determination, Trans. ASABE, 2006, Vol. 49, No. 4, pp. 1193–1201, DOI: 10.13031/2013.21719.
  11. Ge Y., Thomasson J. A., Sui R., Remote sensing of soil properties in precision agriculture: A review, Frontiers of Earth Science, 2011, Vol. 5, pp. 229–238.
  12. Gholizadeha A., Žižalaa D., Saberioonc M., Borůvka L., Soil organic carbon and texture retrieving and mapping using proximal, airborne and Sentinel-2 spectral imaging, Remote Sensing of Environment, 2018, Vol. 218, pp. 89–103.
  13. He X., Pan J., Jin O., Xu T., Liu B., Xu T., Shi Y., Atallah A., Herbrich R., Bowers S., Candela J. Q., Practical lessons from predicting clicks on ads at Facebook, Proc. 8th Intern. Workshop on Data Mining for Online Advertising, ACM, 2014, 9 p., available at: https://doi.org/10.1145/2648584.2648589.
  14. Jahn R., Blume H. P., Asio V. B., Spaargaren O., Schad P., Guidelines for Soil Description, FAO, 2006, 109 p.
  15. Li Z., Taylor J., Frewer L., Zhao C., Yang G., Cheng X. A., A Comparative Review of the State and Advancement of Site-Specific Crop Management in the UK and China, Frontiers of Agricultural Science and Engineering, 2019, Vol. 6, No. 2, pp. 116–136.
  16. Mulla D. J., Twenty five years of remote sensing in precision agriculture: Key advances and remaining knowledge gaps, Biosystems Engineering, 2013, Vol. 114, No. 4, pp. 358–371.
  17. Natekin A., Knoll A., Gradient boosting machines, a tutorial, Front neurorobotics, 2013, Vol. 7, No. 21, pp. 1–21.
  18. Ogen Y., Goldshleger N., Ben-Dor E., 3D spectral analysis in the VNIR–SWIR spectral region as a tool for soil classification, Geoderma, 2017, Vol. 302, pp. 100–110.
  19. Shi W., Liu J., Du Z., Yue T., Development of a surface modeling method for mapping soil properties, J. Geographical Sciences, 2012, Vol. 22, pp. 752–760.
  20. Yigini Y., Panagos P., Assessment of soil organic carbon stocks under future climate and land cover changes in Europe, Science of the Total Environment, 2016, Vol. 557, pp. 838–850.
  21. Yuzugullu O., Lorenz F., Fröhlich P., Liebisch F., Understanding Fields by Remote Sensing: Soil Zoning and Property Mapping, Remote Sensing, 2020, Vol. 12, pp. 11–16.