Vol. 37, issue 11, article # 5

Abstract:

Liquid-drop clouds play a significant role in the evolution of cloud systems and the formation of the Earth’s radiation balance. Determination of their optical and microphysical characteristics is one of the most important problems of optics and atmospheric physics. The paper is devoted to assessing the applicability of an artificial neural network to processing synthetic data of passive satellite measurements of reflected solar radiation of low and medium spatial resolution in the visible and short-wave infrared spectral regions in order to simultaneously retrieve the optical thickness and effective radius of droplets of horizontally inhomogeneous cloudiness. The network is trained using the Monte Carlo calculated values of radiance in marine stratocumulus clouds generated by a fractal model. Through a nonlinear approximation of the dependence of optical and microphysical parameters of clouds on radiation characteristics, the tested algorithm allows taking into account the effects of horizontal radiative transfer, unlike classical IPA/NIPA (Independent Pixel Approximation/Nonlocal Independent Pixel Approximation) schemes. It is shown that the errors in solving the inverse problem can be reduced by assimilating data in adjacent pixels, reducing spatial resolution, and using radiance data received at small solar zenith angles. The high correlation between the test and retrieved optical thickness and effective radius indicate the possibility of using a neural network approach to interpreting satellite measurement data.

Keywords:

neural network, remote sensing, clouds, optical thickness, effective radius, inverse problem, numerical simulation

Figures:

References:

1. King M.D. Determination of the scaled optical thickness of clouds from reflected solar radiation measurements // Atmos. Sci. 1987. V. 44, N 13. P. 1734–1751. DOI: 10.1175/1520-0469(1987)044<1734:DOTSOT>2.0.CO;2.
2. Platnick S., King M.D., Ackerman S.A., Menzel W.P., Baum B.A., Riédi J.C., Frey R.A. The MODIS cloud products: Algorithms and examples from Terra // IEEE Trans. Geosci. Remote. Sens. 2003. V. 41, N 2. P. 459–473. DOI: 10.1109/TGRS.2002.808301.
3. Cahalan R.F., Ridgway W., Wiscombe W.J., Gollmer S., Harshvardhan S., Gollmer S. Independent pixel and Monte Carlo estimates of stratocumulus albedo // Atmos. Sci. 1994. V. 51, N 51. P. 3776–3790. DOI: 10.1175/1520-0469(1994)051<3776:IPAMCE>2.0.CO;2.
4. Titov G.A. Radiative horizontal transport and absorption in stratocumulus clouds // J. Atmos. Sci. 1998. V. 55, N 15. P. 2549–2560. DOI: 10.1029/2002JD002103.
5. Cahalan R.F., Ridgway W., Wiscombe W.J., Bell T.L. The albedo of fractal stratocumulus clouds // J. Atmos. Sci. 1994. V. 51, N 16. P. 2434–2455. DOI: 10.1175/1520-0469(1994)051<2434:TAOFSC>2.0.CO;2.
6. Marshak A., Davis A., Cahalan R., Wiscombe W.J. Nonlocal independent pixel approximation: Direct and inverse problems // IEEE Trans. Geos. Remote Sens. 1998. V. 36, N 1. P. 192–205. DOI: 10.1109/TGRS.1998.662753.
7. 3D Radiative Transfer in Cloudy Atmospheres // A. Marshak, A. Davis (eds.). Berlin, Heidelberg, New York: Springer Science @ Business Media, 2005. 686 p.
8. Benner T.C., Evans K.F. Three dimensional solar radiative transfer in small tropical cumulus fields derived from high-resolution imagery // J. Geophys. Res. 2001. V. 106, N D14. P. 14975–14984. DOI: 10.1029/2001JD900158.
9. Zhang Z., Platnick S. An assessment of differences between cloud effective particle radius retrievals for marine water clouds from three MODIS spectral bands // J. Geophys. Res. 2011. V. 116, N D20215. DOI: 10.1029/2011JD016216.
10. Loeb N.G., Davies R. Observational evidence of plane parallel model biases: Apparent dependence of cloud optical depth on solar zenith angle // J. Geophys. Res. 1996. V. 101, N D1. P. 1621–1634. DOI: 10.1029/95JD03298.
11. Deminov O.V., Matyushchenko Yu.Ya., Kalachev A.V., Pashnev V.V. Ispol'zovanie neirosetevykh tekhnologii dlya opredeleniya opticheskikh parametrov atmosfery // Yuzhno-Sibirskii nauchnyi vestnik. 2024. V. 54, N 2. P. 53–59. DOI: 10.25699/SSSB.2024.54.2.005.
12. Rozanov A.P., Gribanov K.G. Neirosetevaya model' dlya otsenki potokov ugleroda v lesnykh ekosistemakh po dannym distantsionnogo zondirovaniya Zemli // Optika atmosf. i okeana. 2023. V. 36, N 2. P. 122–128. DOI: 10.15372/AOO20230207; Rozanov A.P., Gribanov K.G. A neural network model for estimating carbon fluxes in forest ecosystems from remote sensing data // Atmos. Ocean. Opt. 2023. V. 36, N 4. P. 323–328.
13. Faure T., Isaka H., Guillemet B. Neural network retrieval of cloud parameters of inhomogeneous and fractional clouds: Feasibility study // Remote Sens. Environ. 2001. V. 77, N 2. P. 123–138. DOI: 10.1016/S0034-4257(01)00199-7.
14. 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. Geophys. Res.: Atmos. 2004. V. 109, N D12203. DOI: 10.1029/2003JD004186.
15. 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 // Atmos. Meas. Tech. 2017. V. 10. P. 4747–4759. DOI: 10.5194/amt-10-4747-2017.
16. Cornet C., Buriez J.-C., Riédi J., Isaka H., Guillemet B. Case study of inhomogeneous cloud parameter retrieval from MODIS data // Geophys. Res. Lett. 2005. V. 32, N L13807. DOI: 10.1029/2005GL022791.
17. Nakajima T.Y., Nakajima T. Wide-area determination of cloud microphysical properties from NOAA AVHRR measurements for FIRE and ASTEX regions // J. Atmos. Sci. 1995. V. 52. P. 4043–4059. DOI: 10.1175/1520-0469(1995)052<4043:WADOCM>2.0.CO;2.
18. Han Q., Rossow W.B., Chou J., Welch R.M. Global variations of column droplet concentration in low-level clouds // Geophys. Res. Lett. 1998. V. 25. P. 1419–1422. DOI: 10.1029/98GL01095.
19. Russkova T.V., Skorokhodov A.V. Algoritm vosstanovleniya opticheskoi tolshchiny odnosloinoi gorizontal'no neodnorodnoi oblachnosti s ispol'zovaniem neironnoi seti // Sovrem. problemy distants. zondirovaniya Zemli iz kosmosa. 2024. V. 21, N 1. P. 88–105. DOI: 10.21046/2070-7401-2024-21-1-88-105.
20. Funahashi K. On the approximate realization of continuous mappings by neural networks // Neural Networks. 1989. V. 2, N 3. P. 183–192. DOI: 10.1016/0893-6080(89)90003-8.
21. Faure T., Isaka H., Guillement B. Neural network retrieval of cloud parameters from high-resolution multispectral radiometric data. A feasibility study // Remote Sens. Environ. 2002. V. 80. P. 285–296. DOI: 10.1016/S0034-4257(01)00310-8.
22. Magaritz-Rohen L., Khain A., Pinsky M. About the horizontal variability of effective radius in stratocumulus clouds // J. Geophys. Res.: Atmos. 2016. V. 121. P. 9640–9660. DOI: 10.1002/2016JD024977.
23. Panteleev A.V., Lobanov A.V. Gradientnye metody optimizatsii v mashinnom obuchenii identifikatsii parametrov dinamicheskikh sistem // Modelirovanie i analiz dannykh. 2019. V. 9, N 4. P. 88–99. DOI: 10.17759/mda.2019090407.
24. Nikolenko S., Kadurin A., Arkhangel'skaya E. Glubokoe obuchenie. Pogruzhenie v mir neironnykh setei. SPb.: Piter, 2022. 440 p.