A Neural Network Correction to the Scalar Approximation in Radiative Transfer

Patricia Castellanos Global Modeling and Assimilation Office, NASA Goddard Space Flight Center, Greenbelt, Maryland

Search for other papers by Patricia Castellanos in
Current site
Google Scholar
PubMed
Close
and
Arlindo da Silva Global Modeling and Assimilation Office, NASA Goddard Space Flight Center, Greenbelt, Maryland

Search for other papers by Arlindo da Silva in
Current site
Google Scholar
PubMed
Close
Restricted access

Abstract

The next generation of advanced high-resolution sensors in geostationary orbit will gather detailed information for studying the Earth system. There is an increasing desire to perform observing system simulation experiments (OSSEs) for new sensors during the development phase of the mission in order to better leverage information content from the new and existing sensors. Forward radiative transfer calculations that simulate the observing characteristics of a new instrument are the first step to an OSSE, and they are computationally intensive. The scalar approximation to the radiative transfer equation, a simplification of the vector representation, can save considerable computational cost, but produces errors in top of the atmosphere (TOA) radiance as large as 10% due to neglecting polarization effects. This article presents an artificial neural network technique to correct scalar TOA radiance over both land and ocean surfaces to within 1% of vector-calculated radiance. A neural network was trained on a database of scalar–vector TOA radiance differences at a large range of solar and viewing angles for several thousand realistic atmospheric vertical profiles that were sampled from a high-resolution (7 km) global atmospheric transport model. The profiles include Rayleigh scattering and aerosol scattering and absorption. Training and validation of the neural network was demonstrated for two wavelengths in the ultraviolet–visible (UV-Vis) spectral range (354 and 670 nm). The significant computational savings accrued from using a scalar approximation plus neural network correction approach to simulating TOA radiance will make feasible hyperspectral forward simulations of high-resolution sensors on geostationary satellites, such as Tropospheric Emissions: Monitoring of Pollution (TEMPO), GOES-R, Geostationary Environmental Monitoring Spectrometer (GEMS), and Sentinel-4.

Supplemental information related to this paper is available at the Journals Online website: https://doi.org/10.1175/JTECH-D-18-0003.s1.

For information regarding reuse of this content and general copyright information, consult the AMS Copyright Policy (www.ametsoc.org/PUBSReuseLicenses).

Corresponding author: Patricia Castellanos, patricia.castellanos@nasa.gov

Abstract

The next generation of advanced high-resolution sensors in geostationary orbit will gather detailed information for studying the Earth system. There is an increasing desire to perform observing system simulation experiments (OSSEs) for new sensors during the development phase of the mission in order to better leverage information content from the new and existing sensors. Forward radiative transfer calculations that simulate the observing characteristics of a new instrument are the first step to an OSSE, and they are computationally intensive. The scalar approximation to the radiative transfer equation, a simplification of the vector representation, can save considerable computational cost, but produces errors in top of the atmosphere (TOA) radiance as large as 10% due to neglecting polarization effects. This article presents an artificial neural network technique to correct scalar TOA radiance over both land and ocean surfaces to within 1% of vector-calculated radiance. A neural network was trained on a database of scalar–vector TOA radiance differences at a large range of solar and viewing angles for several thousand realistic atmospheric vertical profiles that were sampled from a high-resolution (7 km) global atmospheric transport model. The profiles include Rayleigh scattering and aerosol scattering and absorption. Training and validation of the neural network was demonstrated for two wavelengths in the ultraviolet–visible (UV-Vis) spectral range (354 and 670 nm). The significant computational savings accrued from using a scalar approximation plus neural network correction approach to simulating TOA radiance will make feasible hyperspectral forward simulations of high-resolution sensors on geostationary satellites, such as Tropospheric Emissions: Monitoring of Pollution (TEMPO), GOES-R, Geostationary Environmental Monitoring Spectrometer (GEMS), and Sentinel-4.

Supplemental information related to this paper is available at the Journals Online website: https://doi.org/10.1175/JTECH-D-18-0003.s1.

For information regarding reuse of this content and general copyright information, consult the AMS Copyright Policy (www.ametsoc.org/PUBSReuseLicenses).

Corresponding author: Patricia Castellanos, patricia.castellanos@nasa.gov

Supplementary Materials

    • Supplemental Materials (PDF 214.43 KB)
Save
  • Chin, M., and Coauthors, 2002: Tropospheric aerosol optical thickness from the GOCART model and comparisons with satellite and sun photometer measurements. J. Atmos. Sci., 59, 461483, https://doi.org/10.1175/1520-0469(2002)059<0461:TAOTFT>2.0.CO;2.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Choi, W. J., and Coauthors, 2018: Introducing the Geostationary Environment Monitoring Spectrometer. J. Appl. Remote Sens., 12, 044005, https://doi.org/10.1117/1.JRS.12.044005.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Esposito, J. A., X. Xiong, A. Wu, J. Sun, and W. L. Barnes, 2004: MODIS reflective solar bands uncertainty analysis. Proc. SPIE, 5542, 448458, https://doi.org/10.1117/12.558106.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Gulde, S. T., M. G. Kolm, D. J. Smith, R. Maurer, G. B. Courrèges-Lacoste, M. Sallusti, and G. Bagnasco, 2017: Sentinel 4: A geostationary imaging UVN spectrometer for air quality monitoring: Status of design, performance and development. Proc. SPIE, 10563, 1056341, https://doi.org/10.1117/12.2304099.

    • Search Google Scholar
    • Export Citation
  • Hansen, J. E., 1971: Multiple scattering of polarized light in planetary atmospheres. Part II. Sunlight reflected by terrestrial water clouds. J. Atmos. Sci., 28, 14001426, https://doi.org/10.1175/1520-0469(1971)028<1400:MSOPLI>2.0.CO;2.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Herman, M., J. L. Deuzé, C. Devaux, P. Goloub, F. M. Bréon, and D. Tanré, 1997: Remote sensing of aerosols over land surfaces including polarization measurements and application to POLDER measurements. J. Geophys. Res., 102, 17 03917 049, https://doi.org/10.1029/96JD02109.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Hornik, K., M. Stinchcombe, and H. White, 1989: Multilayer feedforward networks are universal approximators. Neural Networks, 2, 359366, https://doi.org/10.1016/0893-6080(89)90020-8.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Huttunen, J., and Coauthors, 2016: Retrieval of aerosol optical depth from surface solar radiation measurements using machine learning algorithms, non-linear regression and a radiative transfer-based look-up table. Atmos. Chem. Phys., 16, 81818191, https://doi.org/10.5194/acp-16-8181-2016.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Lacis, A. A., J. Chowdhary, M. I. Mishchenko, and B. Cairns, 1998: Modeling errors in diffuse-sky radiation: Vector vs scalar treatment. Geophys. Res. Lett., 25, 135138, https://doi.org/10.1029/97GL03613.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Lary, D. J., L. A. Remer, D. MacNeill, B. Roscoe, and S. Paradise, 2009: Machine learning and bias correction of MODIS aerosol optical depth. IEEE Geosci. Remote Sens. Lett., 6, 694698, https://doi.org/10.1109/LGRS.2009.2023605.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Levy, R. C., L. A. Remer, and Y. J. Kaufman, 2004: Effects of neglecting polarization on the MODIS aerosol retrieval over land. IEEE Trans. Geosci. Remote Sens., 42, 25762583, https://doi.org/10.1109/TGRS.2004.837336.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Liu, X., P. K. Bhartia, K. Chance, R. J. D. Spurr, and T. P. Kurosu, 2010: Ozone profile retrievals from the Ozone Monitoring Instrument. Atmos. Chem. Phys., 10, 25212537, https://doi.org/10.5194/acp-10-2521-2010.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Loyola, D. G., 2006: Applications of neural network methods to the processing of Earth observation satellite data. Neural Networks, 19, 168177, https://doi.org/10.1016/j.neunet.2006.01.010.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Lyapustin, A., J. Martonchik, Y. Wang, I. Laszlo, and S. Korkin, 2011a: Multiangle Implementation of Atmospheric Correction (MAIAC): 1. Radiative transfer basis and look-up tables. J. Geophys. Res., 116, D03210, https://doi.org/10.1029/2010JD014985.

    • Search Google Scholar
    • Export Citation
  • Lyapustin, A., Y. Wang, I. Laszlo, R. Kahn, S. Korkin, L. Remer, R. Levy, and J. S. Reid, 2011b: Multiangle Implementation of Atmospheric Correction (MAIAC): 2. Aerosol algorithm. J. Geophys. Res., 116, D03211, https://doi.org/10.1029/2010JD014986.

    • Search Google Scholar
    • Export Citation
  • Mishchenko, M. I., and L. D. Travis, 1997: Satellite retrieval of aerosol properties over the ocean using polarization as well as intensity of reflected sunlight. J. Geophys. Res., 102, 16 98917 013, https://doi.org/10.1029/96JD02425.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Mishchenko, M. I., A. A. Lacis, and L. D. Travis, 1994: Errors induced by the neglect of polarization in radiance calculations for Rayleigh-scattering atmospheres. J. Quant. Spectrosc. Radiat. Transfer, 51, 491510, https://doi.org/10.1016/0022-4073(94)90149-X.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Natraj, V., X. Jiang, R.-L. Shia, X. Huang, J. S. Margolis, and Y. L. Yung, 2005: Application of principal component analysis to high spectral resolution radiative transfer: A case study of the band. J. Quant. Spectrosc. Radiat. Transfer, 95, 539556, https://doi.org/10.1016/j.jqsrt.2004.12.024.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Putman, W., A. da Silva, L. E. Ott, and A. Darmenov, 2014: Model configuration for the 7-km GEOS-5 Nature Run, Ganymed release. NASA Global Modeling and Assimilation Office Note 5, version 1.0, 24 pp.

  • Rivera, J., J. Verrelst, J. Gómez-Dans, J. Muñoz-Marí, J. Moreno, and G. Camps-Valls, 2015: An emulator toolbox to approximate radiative transfer models with statistical learning. Remote Sens., 7, 93479370, https://doi.org/10.3390/rs70709347.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Schmit, T. J., P. Griffith, M. M. Gunshor, J. M. Daniels, S. J. Goodman, and W. J. Lebair, 2017: A closer look at the ABI on the GOES-R series. Bull. Amer. Meteor. Soc., 98, 681698, https://doi.org/10.1175/BAMS-D-15-00230.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Spurr, R., 2006: VLIDORT: A linearized pseudo-spherical vector discrete ordinate radiative transfer code for forward model and retrieval studies in multilayer multiple scattering media. J. Quant. Spectrosc. Radiat. Transfer, 102, 316342, https://doi.org/10.1016/j.jqsrt.2006.05.005.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Spurr, R., 2008: LIDORT and VLIDORT: Linearized pseudo-spherical scalar and vector discrete ordinate radiative transfer models for use in remote sensing retrieval problems. Light Scattering Reviews, Vol. 3, Springer, 229–275.

    • Crossref
    • Export Citation
  • Wojciechowski, M., 2005: Feed-forward neural network for Python. Lodz University of Technology, http://ffnet.sourceforge.net/.

  • Wojciechowski, M., 2011: Application of artificial neural network in soil parameter identification for deep excavation numerical model. Comput. Assisted Methods Eng. Sci., 18, 303311, http://cames.ippt.gov.pl/index.php/cames/article/view/109.

    • Search Google Scholar
    • Export Citation
  • Wojciechowski, M., 2012: Solving differential equations by means of feed-forward artificial neural networks. Artificial Intelligence and Soft Computing, Springer, 187–195.

    • Crossref
    • Export Citation
  • Zoogman, P., and Coauthors, 2017: Tropospheric Emissions: Monitoring of Pollution (TEMPO). J. Quant. Spectrosc. Radiat. Transfer, 186, 1739, https://doi.org/10.1016/j.jqsrt.2016.05.008.

    • Crossref
    • Search Google Scholar
    • Export Citation
All Time Past Year Past 30 Days
Abstract Views 0 0 0
Full Text Views 502 112 7
PDF Downloads 498 84 10