Modified method of structural analysis of remote sensing data

The problem of automating the interpretation of remote sensing data from natural objects is considered. It is shown that existing methods for structural analysis of spectral data are based on expert evaluation of the algorithms used. To automate the decoding of remote sensing information, a modifi ed method of structural data analysis has been developed, based on the use of the components of the correlation coeffi cient of a pair of spectral features. Each component is determined by the product of its components in the form of normalized values of spectral features. Based on the signs of the components of the correlation coeffi cient (positive, negative and alternating), four classes are formed. Based on the information obtained, a decision rule is determined for assessing the belonging of a control situation in the space of a pair of spectral features to one of the detected classes. Using the example of detecting forest areas damaged by the Siberian silkmoth, a comparison was made between the results of applying the proposed method and traditional methods of decomposing remote sensing data using normalized vegetation indices NDVI and GNDVI. To characterize the detected classes using the proposed method and to determine the threshold values of NDVI and GNDVI, kernel probability density estimates are used. The procedure for optimizing the kernel probability density estimate is considered, based on the choice of the fuzziness coeffi cients of the kernel functions from the condition of the maximum likelihood function. The use of a modifi ed method of structural analysis of remote sensing data allows us to circumvent the problem of determining threshold values of vegetation indices.

1. Borzov S. M., Potaturkin O. I. Increasing the classifi cation effi ciency of hyperspectral images due to multi-scale spatial processing. Computer Optics, 44(6), 937–943 (2020). https://doi.org/10.18287/2412-6179-CO-779 ; https://elibrary.ru/xrxptw

2. Shipko V. V., Borzov S. M. Analysis of the effi ciency of hyperspectral data classifi cation under constraints on the quantization bit depth, the number of spectral channels, and spatial resolution. Optoelectronics, Instrumentation and Data Processing, 58(3), 273–280 (2022). https://doi.org/10.3103/S8756699022030062 ; https://elibrary.ru/amztfv

3. Zhurbin I. V., Shaura A. S., Zlobina A. G., Bazhenova A. I. Detection of areas of the anthropogenically transformed natural environment based on a comprehensive analysis of multiseasonal multispectral survey. Optoelectronics, Instrumentation and Data Processing, 60(1), 106–115 (2024). https://doi.org/10.3103/s8756699024700080 ; https://elibrary.ru/beyneq

4. Lapko A. V., Lapko V. A., Im S. T., Tuboltsev V. P., Avdeenok V. A. Nonparametric algorithm of identifi cation of classes corresponding to single-mode fragments of the probability density of multidimensional random variables. Optoelectronics, Instrumentation and Data Processing, 55(3), 230–236 (2019). https://doi.org/10.3103/S8756699019030038 ; https://elibrary.ru/rvipgk

5. Tuboltsev V. P., Lapko A. V., Lapko V. A. Modifi ed nonparametric algorithm for automatic classifi cation of large-volume statistical data and its application. Scientifi c and Technical Information Processing, 51(6), 592–597 (2024). https://doi.org/10.3103/S0147688224700552 ; https://elibrary.ru/qhnfru

6. Shevyrnogov A. P., Botvich I. Yu., Pisman T. I., Volkova A. I., Kononova N. A., Ivanov S. A. Informative value of spectral vegetation indices for the meadow and steppe vegetation monitoring of Khakassia by ground and satellite data. Izvestiya, Atmospheric and Oceanic Physics, 60(9), 992–1002 (2024). https://doi.org/10.31857/S0205961424010028 ; https://elibrary.ru/gncmtk

7. Sahu G., Garanayak M., Paikaray B. Green vegetation detection in satellite imagery using the normalised difference vegetation index method. International Journal of Bioinformatics Research and Applications, 19(4), 327–342 (2023). https://doi.org/10.1504/ijbra.2023.135367 ; https://elibrary.ru/ayuqdk

8. Basit I., Faizi F., Mahmood Kh., Faizi R., Ramzan S., Parvez Sh., Mushtaq F. Assessment of vegetation dynamics under changed climate situation using geostatistical modeling. Theoretical and Applied Climatology, 155(4), 3371–3386 (2024). https://doi.org/10.1007/s00704-024-04840-x ; https://elibrary.ru/plvaiv

9. Segura Martinez W. D. Comparison of vegetation indices NDVI, GNDVI, NDMI and NDWI on the example of an african palm in Puerto Vilches (Santander, Colombia). Agrophysica, (4), 25–31 (2023). https://doi.org/10.25695/AGRPH.2023.04.04 ; https://elibrary.ru/morywp

10. Piedad Rubio A. M., Hernández López D. R., Lárraga Altamirano H. R., Zacarías González E. Teledetección en la agricultura de precisión: estado del arte de los índices de vegetación. Tectzapic, (6), 47–59 (2020). (In Esp.)

11. Lapko A. V., Lapko V. A. Procedure for decomposing the values of two-dimensional spectral features of remote sensing based on the analysis of correlation coeffi cient components. Measurement Techniques, 67(6), 427–432 (2024). https://doi.org/10.1007/s11018-024-02362-6 ; https://elibrary.ru/pphujk

12. Lapko A. V., Lapko V. A., Im S. T. Decomposition of Spectral Features of Remote Sensing Based on the Correlation Coeffi cient Components. Optoelectronics, Instrumentation and Data Processing, 61(3), 310–317 (2025). https://doi.org/10.3103/S8756699025700360 ; https://elibrary.ru/fzvcxo

13. Parzen E. On estimation of a probability density function and mode. Annals of Mathematical Statistics, 33(3), 1065–1076 (1962). https://doi.org/10.1214/aoms/1177704472

14. Epanechnikov V. A. Non-parametric estimation of a multivariate probability density. Theory of Probability & Its Applications, 14(1), 156–161 (1969). https://doi.org/10.1137/1114019

15. Duin R. P. W. On the choice of smoothing parameters for Parzen estimators of probability density functions. IEEE Transactions on Computers, C-25(11), 1175–1179 (1976). https://doi.org/10.1109/TC.1976.1674577

16. Botev Z. I., Kroese D. P. Non-asymptotic Bandwidth Selection for Density Estimation of Discrete Data. Methodology and Computing in Applied Probability, 10(3), 435–451 (2008). https://elibrary.ru/pljmag

17. Kharuk V. I., Im S. T., Soldatov V. V. Siberian silkmoth outbreaks surpassed geoclimatic barrier in Siberian Mountains. Journal of Mountain Science, 17, 1891–1900 (2020). https://doi.org/10.1007/s11629-020-5989-3 ; https://elibrary.ru/xetekq

18. Kharuk V. I., Im S. T., Ranson K. J., Yagunov M. N. Climate-induced northerly expansion of Siberian silkmoth range. Forests, 8(8), 301 (2017). https://doi.org/10.3390/f8080301

19. Riano D., Chuvieco E., Salas J., Aguado I. Assessment of different topographic corrections in Landsat-TM data for mapping vegetation types. IEEE Transactions on Geoscience and Remote Sensing, 41, 1056–1061 (2003). https://doi.org/10.1109/TGRS.2003.811693

20. Huang S., Tang L., Hupy J. P. et al. A commentary review on the use of normalized difference vegetation index (NDVI) in the era of popular remote sensing. Journal of Forest Research, 32, 1–6 (2021). https://doi.org/10.1007/s11676-020-01155-1 ; https://elibrary.ru/lmntkd

21. Chávez R. O., Clevers J. G. P. W., Decuyper M., de Bruin S., Herold M. 50 years of water extraction in the Pampa del Tamarugal basin: Can Prosopis tamarugo trees survive in the hyper-arid Atacama Desert (Northern Chile). Journal of Arid Environments, 124, 292–303 (2016). https://doi.org/10.1016/j.jaridenv.2015.09.007 ; https://elibrary.ru/veltzt

22. Gitelson A., Kaufman Y., Merzlyak M. Use of a green channel in remote sensing of global vegetation from EOS-MODIS. Remote Sensing of Environment, 58, 289–298 (1996). https://doi.org/10.1016/S0034-4094257(96)00072-7 ; https://elibrary.ru/ldkhlh

23. Hunt E. R. Jr., Hively W. D., Fujikawa S. J., Linden D. S., Daughtry C. S. T., McCarty G. W. Acquisition of NIR-GreenBlue Digital Photographs from Unmanned Aircraft for Crop Monitoring. Remote Sensing, 2(1), 290–305 (2010). https://doi.org/10.3390/rs2010290 ; https://elibrary.ru/pnqned.