Журнал

About Editorial Board Information for authors and reviewers Publication ethics Contacts User Account: send / review a manuscript
Archive
Volume 21, 2024
Number 1
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, 2022, Vol. 19, No. 2, pp. 32-42

Sea ice cover detection in the Russian Far Eastern seas using NOAA 20 VIIRS measurements and a neural network

M.O. Kuchma 1 , Z.N. Lotareva 1 , L.A. Korneva 1 , Yu.A. Shamilova 1 
1 Far Eastern Center of SRC Planeta, Khabarovsk, Russia
Accepted: 25.03.2022
DOI: 10.21046/2070-7401-2022-19-2-32-42
In this paper, we consider the technology for calculating the ice cover mask using a convolutional neural network on the data of VIIRS measurements from the NOAA-20 satellite. Specialists of the Far-Eastern Center of State Research Center for Space Hydrometeorology “Planeta” (FEC SRC Planeta) collected a training dataset using data from October 2020 to June 2021 that amounted to about 22 thousand textures. The optimal neural network architecture for solving the problem was obtained by the empirical method. During the experiments, the optimal size of input textures was obtained, which was 21×21 pixels. In the same way, the input parameters were obtained, which were the solar zenith angle and infrared channels with central wavelengths of 0.6, 1.6, 10.7, and 12.0 µm. As reference data, ice cover masks were used, manually created by experienced decoders of FEC SRC Planeta. When compared with the data of the Community Satellite Processing Package VIIRS Aerosols, Cryosphere, Clouds and Volcanic Ash Environmental Data Record Products, the validation results of the developed algorithm showed high accuracy and probability of correct event identification — 94 and 98 %, respectively.
Keywords: remote sensing, VIIRS, NOAA-20, convolutional neural network, texture, ice, ice cover mask
Full text

References:

  1. Kramareva L. S., Andreev A. I., Bloshchinskiy V. D., Kuchma M. O., Davidenko A. N., Pustatintsev I. N., Shamilova Yu. A., Kholodov E. I., Korolev S. P., The use of neural networks in hydrometeorological problems, Vychislitel’nye tekhnologii, 2019, Vol. 24, No. 6, pp. 50–59 (in Russian), DOI: 10.25743/ICT.2019.24.6.007.
  2. Kuchma M. O., Lotareva Z. N., Slesarenko L. A., Determination of the ice edge of the Far Eastern seas using convolutional neural networks according to the MSU-MR device of the Meteor-M satellite No. 2, Materialy 18-i Vserossiiskoi otkrytoi konferentsii “Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa” (Proc. 18th All-Russia Open Conf. “Current Problems in Remote Sensing of the Earth from Space”), 16–20 Nov. 2020, Moscow: IKI RAN, 2020, p. 217 (in Russian), DOI: 10.21046/18DZZconf-2020a.
  3. Kuchma M. O., Lotareva Z. N., Slesarenko L. A., Ice cover detection of the Far Eastern Seas using the MSU-MR instrument of the Meteor-M No. 2 satellite, Issledovanie Zemli iz Kosmosa, 2021, No. 2, pp. 31–41 (in Russian), DOI: 10.31857/S0205961421020032.
  4. Paunder E., Physics of Ice, Oxford: Pergamon Press, 1967, 160 p.
  5. Smirnov V. G., Sputnikovye metody opredeleniya kharakteristik ledyanogo pokrova morei (Satellite methods for determining the characteristics of the sea ice cover), Saint Petersburg: AANII, 2011, 240 p. (in Russian).
  6. Toporov A. I., Myasoedov A. G., Gusev V. V., The use of neural network approaches for multispectral analysis of satellite data in the design of capital construction facilities, Materialy 17-i Vserossiiskoi otkrytoi konferentsii “Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa” (Proc. 17th All-Russia Open Conf. “Current Problems in Remote Sensing of the Earth from Space”), 11–15 Nov. 2019, Moscow: IKI RAN, 2019, p. 67 (in Russian).
  7. Bloshchinskiy V. D., Kuchma M. O., Andreev A. I., Sorokin A. A., Snow and cloud detection using a convolutional neural network and low-resolution data from the Electro-L No. 2 Satellite, J. Applied Remote Sensing, 2020, Vol. 14, No. 3, p. 034506, DOI: 10.1117/1.JRS.14.034506.
  8. Crane R. G., Anderson M. R., Satellite discrimination of snow/cloud surfaces, Intern. J. Remote Sensing, 1984, No. 5, pp. 213–223, DOI: 10.1080/01431168408948799.
  9. Dorsey N. E., Properties of Ordinary Water-Substance in All Its Phases, Reinhold Publishing Corporation, 1940, 673 p., DOI: 10.1038/146145a0.
  10. Godin R., Vicente G., Joint Polar Satellite System (JPSS) Operational Algorithm Description (OAD) Document for VIIRS Sea Surface Temperature (SST) Environmental Data Record (EDR) Software, USA: NASA Goddard Space Flight Center, 2017, 17 p.
  11. Ioffe S., Szegedy C., Batch normalization: accelerating deep network training by reducing internal covariate shift, Proc. 32nd Intern. Conf. Machine Learning (ICML 15), 2015, Vol. 37, pp. 448–456, DOI: 10.48550/arXiv.1502.03167.
  12. Jezek K., Perovich D., Golden K., Luther C., Barber D., Gogineni P., Grenfell T., Jordan A., Mobley C., Nghiem S., Onstott R., Broad spectral, interdisciplinary investigation of the electromagnetic properties of sea ice, IEEE Trans. Geoscience and Remote Sensing, 1998, Vol. 36, pp. 1633–1641, DOI: 10.1109/36.718635.
  13. Key J. R., Mahoney R., Liu Y., Romanov P., Tschudi M., Appel I., Maslanik J., Baldwin D., Wang X., Meade P., Snow and ice products from Suomi NPP VIIRS, J. Geophysical Research: Atmospheres, 2013, Vol. 118, pp. 12816–12830, DOI: 10.1002/2013JD020459.
  14. Kingma D. P., Ba J. L., Adam: a method for stochastic optimization, Intern. Conf. Learning Representations, 2015, 13 p., DOI: 10.48550/arXiv.1412.6980.
  15. Kuo J. C., Understanding convolutional neural networks with a mathematical model, J. Visual Communication and Image Representation, 2016, Vol. 41, pp. 406–413, DOI: 10.48550/arXiv.1609.04112.
  16. Minnett P. J., GHRSST-PP Sea Ice Working Group (SI-WG) report, Report 8th GHRSST-PP Science Team Meeting, 2007, Vol. 1, pp. 57–60.
  17. Mueller A., Guido S., An Introduction to Machine Learning with Python, O’Reilly Media, 2017, 188 p.
  18. Riggs G., Hall D., Roman M. O., VIIRS Snow Cover Algorithm Theoretical Basis Document (ATBD), USA: NASA Goddard Space Flight Center, 2015, 38 p.
  19. Salomonson V. V., Appel I., Estimating fractional snow cover from MODIS using the normalized difference snow index, Remote Sensing of Environment, 2004, Vol. 89, No. 3, pp. 351–360, DOI: 10.1016/j.rse.2003.10.016.
  20. Seaman C., Hillger D., Kopp T., Williams R., Miller S., Lindsey D., Visible Infrared Imaging Radiometer Suite (VIIRS) Imagery Environmental Data Record (EDR) User’s Guide: NOAA Technical Report NESDIS 150, 2015, 35 p.
  21. Srivastava N., Hinton G., Krizhevsky A., Sutskever I., Salakhutdinov R., Dropout: A Simple Way to Prevent Neural Networks from Overfitting, J. Machine Learning Research, 2014, Vol. 15, pp. 1929–1958.
  22. Zang L., Zang L., Du B., Deep learning for remote sensing data: a technical tutorial on the state of the art, IEEE Geoscience and Remote Sensing Magazine, 2016, Vol. 4, No. 2, pp. 22–40, DOI: 10.1109/MGRS.2016.2540798.