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 Number 4 Number 5
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, 2024, Vol. 21, No. 1, pp. 88-105

Algorithm for retrieving the optical depth of single-layer horizontally inhomogeneous clouds using a neural network

T.V. Russkova 1 , A.V. Skorokhodov 1 
1 V.E. Zuev Institute of Atmospheric Optics SB RAS, Tomsk, Russia
Accepted: 11.12.2023
DOI: 10.21046/2070-7401-2024-21-1-88-105
A neural network technique for retrieving the optical thickness of horizontally inhomogeneous clouds is presented. To train the neural network, sets of reflected solar radiation intensity values in the visible and short-wave infrared regions of the spectrum were used. Radiative transfer simulation in marine stratocumulus clouds was carried out using the Monte Carlo method, and a fractal model based on the method of limited cascades was used to generate cloud fields. The difference between the presented technique and the classical IPA/NIPA (Independent Pixel Approximation/Nonlocal Independent Pixel Approximation) schemes is that the former allows you to integrate radiometric data in the required quantity and take into account the effects of horizontal radiation transfer not only within the target pixel, but also adjacent areas. In addition, without significantly increasing the complexity of the algorithm, additional parameters can be included in the vector of retrieved characteristics, in particular, the indicator of the relative heterogeneity of the optical thickness and the cloud fraction within the observation pixel. The paper examines the dependence of the accuracy of solving the inverse problem on the architecture and values of the hyperparameters of the neural network, the volume and structure of the training sample. High values of the correlation coefficient (0.95–0.99) were achieved between the original and retrieved values of the optical thickness at a fixed value of the effective radius of cloud particles. It is shown that when additional information about the reflected radiation in adjacent pixels is used and the spatial resolution is reduced within the considered range, the standard deviation of the optical thickness decreases and the correlation coefficient increases.
Keywords: remote sensing, broken clouds, optical thickness, inverse problems, numerical simulation, solar radiative transfer, Monte Carlo method, neural networks
Full text

References:

  1. Gribanov K. G., Imasu R., Zakharov V. I., Neural Networks for CO2 Profile Retrieval from the Data of GOSAT/TANSO-FTS, Atmospheric and Oceanic Optics, 2010, Vol. 23, No. 01, pp. 42–47, DOI: 10.1134/S1024856010010094.
  2. Eltsov N. P., Ogorodnikov V. A., Prigarin S. M., A study of bounded cascade models of random fields on a plane, Numererical Analysis and Applications, 2008, Vol. 1, Issue 4, pp. 332–338, DOI: 10.1134/S1995423908040034.
  3. Marchuk G. I., Mikhailov G. A., Nazaraliev M. A. et al., The Monte Carlo Methods in Atmospheric Optics, Heidelberg: Springer-Verlag Berlin, 1980, 210 p., DOI: 10.1007/978-3-540-35237-2.
  4. Matvienko G. G., Sukhanov A. Ya., Babchenko S. V., The Analysis of Capabilities of Neural Networks in CO2 Sounding with Spaceborne IPDA-Lidar with the Use of Different a Priori Data, Atmospheric and Oceanic Optics, 2019, Vol. 32, No. 02, pp. 165–170, DOI: 10.1134/S102485601902009X.
  5. Nikolenko S., Kadurin A., Arkhangelskaya E., Glubokoe obuchenie. Pogruzhenie v mir neironnykh setei (Deep learning. Dive into the world of neural networks), Saint Petersburg: Piter, 2022, 440 p. (in Russian).
  6. Panteleev A. V., Lobanov A. V., Gradient optimization methods in machine learning for the identification of dynamic systems parameters, Modelirovanie i analiz dannykh, 2019, Vol. 09, No. 4, pp. 88–99 (in Russian), DOI: 10.17759/mda.2019090407.
  7. Feigelson E. M., Radiation in a Cloudy Atmosphere, Dordrecht: D. Reidel Publishing Company, 1984, 293 p., DOI: 10.1007/978-94-009-6443-3.
  8. Russkova T. V., Monte Carlo Simulation of the Solar Radiation Transfer in a Cloudy Atmosphere with the Use of Graphic Processor and NVIDIA CUDA Technology, Atmospheric and Oceanic Optics, 2018, Vol. 31, No. 02, pp. 119–130, DOI: 10.1134/S1024856018020100.
  9. Barker H., A parameterization for computing grid-averaged solar fluxes for inhomogeneous marine boundary layer clouds. Part I: Methodology and homogeneous biases, J. Atmospheric Sciences, 1996, Vol. 53, Issue 16, pp. 2289–2303, DOI: 10.1175/1520-0469(1996)053<2289:APFCGA>2.0.CO;2.
  10. Barker H., Davies J. A., Cumulus cloud radiative properties and the characteristics of satellite radiance wavenumber spectra, Remote Sensing of Environment, 1992, Vol. 42, Issue 1, pp. 51–64, DOI: 10.1016/0034-4257(92)90067-T.
  11. Benner T. C., Evans K. F., Three dimensional solar radiative transfer in small tropical cumulus fields derived from high-resolution imagery, J. Geophysical Research, 2001, Vol. 106, Issue D14, pp. 14975–14984, DOI: 10.1029/2001JD900158.
  12. Buriez J. C., Doutriaux-Boucher M., Parol F., Loeb N. G., Angular variability of the liquid water cloud optical thickness retrieved from ADEOS-POLDER, J. Atmospheric Sciences, 2001, Vol. 58, Issue 20, pp. 3007–3018, DOI: 10.1175/1520-0469(2001)058<3007:AVOTLW>2.0.CO;2.
  13. Cahalan R. F., Ridgway W., Wiscombe W. J., Bell T. L. (1994a), The albedo of fractal stratocumulus clouds, J. Atmospheric Sciences, 1994, Vol. 51, Issue 16, pp. 2434–2455, DOI: 10.1175/1520-0469(1994)051<2434:TAOFSC>2.0.CO;2.
  14. Cahalan R. F., Ridgway W., Wiscombe W. J. et al. (1994b), Independent pixel and Monte Carlo estimates of stratocumulus albedo, J. Atmospheric Sciences, 1994, Vol. 51, No. 51, pp. 3776–3790, DOI: 10.1175/1520-0469(1994)051<3776:IPAMCE>2.0.CO;2.
  15. Cornet C., Isaka H., Guillemet B., Szczap F., Neural network retrieval of cloud parameters of inhomogeneous clouds from multispectral and multiscale radiance data: Feasibility study, J. Geophysical Research: Atmospheres, 2004, Vol. 109, Article D12203, DOI: 10.1029/2003JD004186.
  16. Cornet C., Buriez J.-C., Riédi J. et al., Case study of inhomogeneous cloud parameter retrieval from MODIS data, Geophysical Research Letters, 2005, Vol. 32, Article L13807, DOI: 10.1029/2005GL022791.
  17. Faure T., Isaka H., Guillemet B., Neural network retrieval of cloud parameters of inhomogeneous and fractional clouds: Feasibility study, Remote Sensing of Environment, 2001, Vol. 77, Issue 2, pp. 123–138, DOI: 10.1016/S0034-4257(01)00199-7.
  18. Hess M., Koepke P., Schult I., Optical Properties of Aerosols and Clouds: The software package OPAC, Bull. American Meteorological Society, 1998, Vol. 79, Issue 5, pp. 831–844, DOI: 10.1175/1520-0477(1998)079<0831:OPOAAC>2.0.CO;2.
  19. King M. D., Determination of the Scaled Optical Thickness of Clouds from Reflected Solar Radiation Measurements, J. Atmospheric Sciences, 1987, Vol. 44, No. 13, pp. 1734–1751, DOI: 10.1175/1520-0469(1987)044<1734:DOTSOT>2.0.CO;2.
  20. Loeb N. G., Davies R., Observational evidence of plane parallel model biases: Apparent dependence of cloud optical depth on solar zenith angle, J. Geophysical Research, 1996, Vol. 101, Issue D1, pp. 1621–1634, DOI: 10.1029/95JD03298.
  21. Loeb N. G., Varnai T., Davies R., Effect of cloud inhomogeneities on the solar zenith angle dependence of nadir reflectance, J. Geophysical Research, 1997, Vol. 102, Issue D8, pp. 9387–9395, DOI: 10.1029/96Jd03719.
  22. Magaritz-Rohen L., Khain A., Pinsky M., About the horizontal variability of effective radius in stratocumulus clouds, J. Geophysical Research: Atmospheres, 2016, Vol. 121, pp. 9640–9660, DOI: 10.1002/2016JD024977.
  23. Marshak A., Davis A., Cahalan R., Wiscombe W., Bounded cascade models as nonstationary multifractals, Physical Review E, 1994, Vol. 49, Issue 1, pp. 55–69, DOI: 10.1103/PHYSREVE.49.55.
  24. Marshak A., Davis A., Cahalan R., Wiscombe W. J., Nonlocal independent pixel approximation: direct and inverse problems, IEEE Trans. Geoscience and Remote Sensing, 1998, Vol. 36, Issue 1, pp. 192–205, DOI:10.1109/36.655329.
  25. Nikitin S. V., Chulichkov A. I., Borovski A. N., Postylyakov O. V., On estimation of atmospheric scattering characteristics from spectral measurements of solar radiation using machine learning algorithms, Proc. SPIE, 2020, Vol. 11531, Article 115310V, DOI: 10.1117/12.2574237.
  26. Okamura R., Iwabuchi H., Schmidt K. S., Feasibility study of multi-pixel retrieval of optical thickness and droplet effective radius of inhomogeneous clouds using deep learning, Atmospheric Measurement Techniques, 2017, Vol. 10, pp. 4747–4759, DOI: 10.5194/amt-10-4747-2017.
  27. Platnick S., King M. D., Ackerman S. A. et al., The MODIS cloud products: Algorithms and examples from Terra, IEEE Trans. Geoscience and Remote Sensing, 2003, Vol. 41, No. 2, pp. 459–473, DOI: 10.1109/TGRS.2002.808301.
  28. Rothman L. S., Gordon I. E., Barbe A. et al., The HITRAN 2008 molecular spectroscopic database, J. Quantitative Spectroscopy and Radiative Transfer, 2009, Vol. 110, No. 9–10, pp. 533–572, DOI: 10.1016/j.jqsrt.2009.02.013.
  29. Schneider T., Kaul C. M., Pressel K. G., Possible climate transitions from breakup of stratocumulus decks under greenhouse warming, Nature Geoscience, 2019, Vol. 12, pp. 163–167, DOI: 10.1038/s41561-019-0310-1.
  30. Titov G. A., Radiative Horizontal Transport and Absorption in Stratocumulus Clouds, J. Atmospheric Sciences, 1998, Vol. 55, Issue 15, pp. 2549–2560, DOI: 10.1175/1520-0469(1998)055<2549:RHTAAI>2.0.CO;2.
  31. Zhang Z., Platnick S., An assessment of differences between cloud effective particle radius retrievals for marine water clouds from three MODIS spectral bands, J. Geophysical Research, 2011, Vol. 116, Article D20215, DOI: 10.1029/2011JD016216.