1. Proceedings
  2. I3M
  3. 2018
  4. SESDE
  5. 10.46354/i3m.2018.sesde.002

Hyperspectral data processing and adaptive modelling for the Natural Objects properties detection

  • a Olga V. Grigoreva, 
  • b Viktor F. Mochalov, 
  • cVjasheslav A. Zelentsov
  • abMilitary Space Academy named after A.F. Mozhaisky, Zhdanovskaya embankment, 41, 197198 St.Petersburg, Russia
  • cSt.Petersburg Institute for Informatics and Automation of RAS, 14 line 39, 199178 St.Petersburg, Russia
Cite as
Grigoreva O.V., Mochalov V.F., Zelentsov V.A. (2018). Hyperspectral data processing and adaptive modelling for the Natural Objects properties detection. Proceedings of the 6th International Workshop on Simulation for Energy, Sustainable Development & Environment (SESDE 2018), pp. 7-14. DOI: https://doi.org/10.46354/i3m.2018.sesde.002

Abstract

The article proposes a method for assessing the state of natural objects that is based on the complex use of heterogeneous models and hyperspectral Earth remote sensing data used to estimate the parameters of these models. The base model is an artificial neural network,
for the training of which multiparametric models of radiation transfer, gradient search algorithms, as well as regression empirical models supplementing them, can be used and adaptively adjusted. The advantage of the method is the ability to determine the state of water bodies and vegetation under conditions of uncertainty with the possibility of making more precise estimates for the limited volume of ground measurements at reference points. Examples of approbation of the method in determining the state of coastal waters of the Black Sea with the use of hyperspectral imaging materials from “Resurs-P” satellite, as well as in assessing the state of vineyards, are shown.

References

  1. Brovkina O., Novotnya J., Cienciala E., Zemeka F., Russ R., 2017. Mapping forest aboveground biomass using airborne hyperspectral and LiDAR data in the mountainous conditions of Central Europe. Ecological Engineering, 100, 219–230. Available from: www.elsevier.com/locate/ecoleng.
  2. Hagan M.T., Demuth H.B., Beale M.H., Jesus O., 1996. Neural Network Design. 2nd ed. Boston, MA: PWS Publishing.
  3. Kay S., Hedley J., and Lavender S., 2009.Sun glint correction of high and low spatial resolution images of aquatic scenes: A review of methods for visible and near-infrared wavelengths. Remote Sens., 1(4), 697–730.
  4. Grigorieva O.V., Markov A. V., Zhukov D.V., Mochalov V.F., Nikolenko A.A., 2016. Possibility of the use of visible and near infrared multispectral and hyperspectral sensors for the bottom classification of shallow seas. Problems of military-applied geophysics and control of the state of the natural environment, 111-116. Petersburg: A.F. Mozhaysky's Military-Space Academy.
  5. Hagan M.T., Menhaj M.B., 1994. Training feedforward network with the marquardt algorithm. IEEE Transactions on neural networks, 5(6), 989-993.
  6. Lee Z., Carder K. L., Hawes S. K., Steward R.G., Peacock T.G., Davis C.O., 1994. A model for
    interpretation of hyperspectral remote-sensing reflectance. Appl. Opt., 33, 5721– 5732.
  7. Grigoryeva O.V., Zhukov D.V., Markov A.V., Mochalov V.F., 2016. Reconstruction of the depths of coastal waters from data of multi- and hyperspectral imaging. Optics of the Atmosphere and the Ocean, 29(7), 553-559.
  8. Jacquemoud S., Zarco-Tejada P.J., Verhoef W., Asner G.P., Ustin S.L., Baret F., François C., 2006. PROSPECT+SAIL: 15 Years of Use for and Surface Characterization. Proceedings IEEE International geoscience and remote sensing symposium, 31 July – 4 August, Denver, Colorado.
  9. Gastellu-Etchegorry J.P., Demarez, V.Pinel V., Zagolki F., 1996. Modeling radiative transfer in
    heterogeneous 3-D vegetation canopies. Remote Sensing of Environment, 58, 131-156.
  10. Rosema A.W., Verhoef W., Noobergen H., Borgesius J.J., 1992. A new forest light interaction model in support of forest monitoring. Remote Sensing of Environment, 42, 23-41.
  11. Borel C.C., Gerstl S.A.W., 1994. Nonlinear spectral mixing models for vegetative and soil surfaces. Remote Sensing of Environment, 47, 403-416.
  12. Khaikin S., 2008. Neural Networks: Full Course. Williams Publishing House.
  13. R. Kalan, 2001. Basic Concepts of Neural Networks. Williams Publishing House.
  14. Schowengerdt R.A., 2007. Remote Sensing, Third Edition: Models and Methods for Image Processing. Burlington, MA, Academic Press. 
  15. Egorov V.V., Ilyin A.A., Kalinin A.P., Rodionov A.I., Rodionov I.D., 2011. Biometrical features
    estimation of narcotic vegetation on the data of aircraft hyperspectral survey. Current problems in remote sensing of the Earth from space, 8(2), 195-200.
  16. Zhukov D.V., 2016. Spectral features for identification of typical examples of pollution of seas according to aerial and space survey data. Optics of the Atmosphere and the Ocean, 29(7), 560-565.
  17. Grigoryeva O.V., Zhukov D.V., Markov A.V., Mochalov V.F., 2016. Reconstruction of the depths of coastal waters from data of multi- and hyperspectral surveys. Optics of the Atmosphere and the Ocean, 29(7), 553-559.
  18. Grigoryeva O.V., Shilin B.V., 2012. Experience in assessing the ecological characteristics of marine areas of seaports according to video spectral survey data. Modern problems of Earth remote sensing from space, 9(1), 156-166.
  19. Biospheric Aspects of the Hydrological Cycle (BAHS), 1993. Report №27. Ed. By BAHC Core Project Office. Institut fur Meteorologie, Freie Universitat Berlin, Germany.
  20. Biftu G.F., Gan T.Y., 2001. Semi-distributed, physically based, hydrologic modeling of the Paddle River basin, Alberta, using remotely sensed data. Journal of Hydrology, 244, 137-156.
  21. Fefilov Yu.V., 2003. Development and creation of information technology for remote determination of parameters of primary productivity in ocean monitoring systems: Abstract from. disseration of Cand. tech. sciences. Moscow: Moscow Institute of Electronics and Mathematics.
  22. Zelentsov V. et al., 2017. River Flood Forecasting System: An Interdisciplinary Approach. In: Refice A., D'Addabbo A., Capolongo D. (eds) Flood Monitoring through Remote Sensing. Springer Remote Sensing: Photogrammetry. Springer, Cham.
  23. Zelentsov V., Sokolov B., Grigorieva O., Mochalov V., Potryasaev S., Shumeiko V., 2016. “Resurs-P” satellite hyperspectral data: preliminary evaluation of information capacities. Proc. ‘Living Planet Symposium 2016’, 1789. May 9-13 (ESA SP-740, August 2016), Prague, Czech Republic.
  24. Sokolov B., Zelentsov V., Yusupov R., Merkuryev Yu., 2014. Multiple models of information fusion processes: Quality definition and estimation. Journal of Computational Science, 5(3), 380-386.
  25. Zelentsov V.A., Potriasaev S.A., 2017. Architecture and Examples of Implementing the Informational Platform for Creation and Provision of Thematic Services Using Earth Remote Sensing Data. SPIIRAS Proceedings, 55, 86-113.