References

AMT

Atmospheric Measurement Techniques

AMT

Atmos. Meas. Tech.

1867-8548

Copernicus Publications

Göttingen, Germany

10.5194/amt-7-3151-2014

Satellite retrieval of aerosol microphysical and optical parameters using neural networks: a new methodology applied to the Sahara desert dust peak

Taylor

https://orcid.org/0000-0002-3473-3478

¹ Kazadzis

¹ Tsekeri

² Gkikas

https://orcid.org/0000-0002-4137-0724

³ Amiridis

Institute for Environmental Research and Sustainable Development (IERSD), National Observatory of Athens (NOA), Metaxa & Vas. Pavlou, Penteli, 15236, Athens, Greece

Institute for Astronomy, Astrophysics, Space Applications and Remote Sensing (IAASARS), National Observatory of Athens (NOA), Metaxa & Vas. Pavlou, Penteli, 15236, Athens, Greece

Laboratory of Meteorology, Physics Department, University of Ioannina, Greece

26 09 2014

7 9 3151 3175

2014

This work is licensed under the Creative Commons Attribution 3.0 Unported License. To view a copy of this licence, visit https://creativecommons.org/licenses/by/3.0/

This article is available from https://amt.copernicus.org/articles/7/3151/2014/amt-7-3151-2014.html

The full text article is available as a PDF file from https://amt.copernicus.org/articles/7/3151/2014/amt-7-3151-2014.pdf

In order to exploit the full-earth viewing potential of satellite instruments to globally characterise aerosols, new algorithms are required to deduce key microphysical parameters like the particle size distribution and optical parameters associated with scattering and absorption from space remote sensing data. Here, a methodology based on neural networks is developed to retrieve such parameters from satellite inputs and to validate them with ground-based remote sensing data. For key combinations of input variables available from the MODerate resolution Imaging Spectro-radiometer (MODIS) and the Ozone Measuring Instrument (OMI) Level 3 data sets, a grid of 100 feed-forward neural network architectures is produced, each having a different number of neurons and training proportion. The networks are trained with principal components accounting for 98% of the variance of the inputs together with principal components formed from 38 AErosol RObotic NETwork (AERONET) Level 2.0 (Version 2) retrieved parameters as outputs. Daily averaged, co-located and synchronous data drawn from a cluster of AERONET sites centred on the peak of dust extinction in Northern Africa is used for network training and validation, and the optimal network architecture for each input parameter combination is identified with reference to the lowest mean squared error. The trained networks are then fed with unseen data at the coastal dust site Dakar to test their simulation performance. A neural network (NN), trained with co-located and synchronous satellite inputs comprising three aerosol optical depth measurements at 470, 550 and 660 nm, plus the columnar water vapour (from MODIS) and the modelled absorption aerosol optical depth at 500 nm (from OMI), was able to simultaneously retrieve the daily averaged size distribution, the coarse mode volume, the imaginary part of the complex refractive index, and the spectral single scattering albedo – with moderate precision: correlation coefficients in the range 0.368 ≤ <i>R</i> ≤ 0.514. The network failed to recover the spectral behaviour of the real part of the complex refractive index. This new methodological approach appears to offer some potential for moderately accurate daily retrieval of the total volume concentration of the coarse mode of aerosol at the Saharan dust peak in the area of Northern Africa.

References 1

Abdi, H. and Williams, L. J.: Principal component analysis, Wiley Interdisciplinary Reviews, Comput. Stat., 2, 433–459, <a href="http://dx.doi.org/10.1002/wics.101">https://doi.org/10.1002/wics.101</a>, 2010.

AERONET: Level 2.0 Version 2 daily averaged almucantar inversion products, available at:f <a href="http://aeronet.gsfc.nasa.gov/cgi-bin/combined_data_access_inv">http://aeronet.gsfc.nasa.gov/cgi-bin/combined_data_access_inv</a>, last access: 7 April 2012.

Albayrak, A., Wei, J., Petrenko, M., Lynnes, C., and Levy, R. C.: Global bias adjustment for MODIS aerosol optical thickness using neural network, J. Appl. Remote Sens., 7, 073514, 1–16, 2013.

Bishop, C. M.: Neural Networks for Pattern Recognition, Oxford University Press, New York, NY, USA, 1995.

Chin, M., Rood, R. B., Lin, S. J., Müller, J. F., and Thompson, A. M.: Atmospheric sulfur cycle simulated in the global model GOCART: model description and global properties, J. Geophys. Res., 105, 24671–24687, 2000.

Chin, M., Ginoux, P., Kinne, S., Torres, O., Holben, B. N., Duncan, B. N., and Nakajima, T.: Tropospheric aerosol optical thickness from the GOCART model and comparisons with satellite and Sun photometer measurements, J. Atmos. Sci., 59, 461–483, 2002.

Curry, B. and Morgan, P. H.: Model selection in neural networks: some difficulties, Euro. J. Operat. Res., 170, 567–577, 2006.

Cybenko, G.: Approximation by super-positions of a sigmoidal function, Math. Control Signals, 2, 303–314, 1989.

Demuth, H. and Beale, M.: Neural Network Toolbox For Use with MATLAB, Mathworks, 2004.

Deuzé, J. L., Goloub, P., Herman, M., Marchand, A., Perry, G., Susana, S., and Tanré, D.: Estimate of the aerosol properties over the ocean with POLDER, J. Geophys. Res.-Atmos., 105, 15329–15346, <a href="http://dx.doi.org/10.1029/2000JD900148">https://doi.org/10.1029/2000JD900148</a>, 2000.

Deuzé, J. L., Bréon, F. M., Devaux, C., Goloub, P., Herman, M., Lafrance, B., and Tanré, D.: Remote sensing of aerosols over land surfaces from POLDER-ADEOS-1 polarized measurements, J. Geophys. Res.-Atmos., 106, 4913–4926, <a href="http://dx.doi.org/10.1029/2000JD900364">https://doi.org/10.1029/2000JD900364</a>, 2001.

Dubovik, O. and King, M. D.: A flexible inversion algorithm for retrieval of aerosol optical properties from Sun and sky radiance measurements, J. Geophys. Res., 105, 20673–20696, 2000.

Dubovik, O., Smirnov, A., Holben, B. N., King, M. D., Kaufman, Y. J., Eck, T. F., and Slutsker, I.: Accuracy assessments of aerosol optical properties retrieved from Aerosol Robotic Network (AERONET) sun and sky radiance measurements, J. Geophys. Res.-Atmos., 105, 9791–9806, 2000.

Dubovik, O., Holben, B., Eck, T. F., Smirnov, A., Kaufman, Y. J., King, M. D., Tanré, D., and Slutsker, I.: Variability of absorption and optical properties of key aerosol types observed in worldwide locations, J. Atmos. Sci. 59, 590–608, 2002.

Dubovik, O., Herman, M., Holdak, A., Lapyonok, T., Tanré, D., Deuzé, J. L., Ducos, F., Sinyuk, A., and Lopatin, A.: Statistically optimized inversion algorithm for enhanced retrieval of aerosol properties from spectral multi-angle polarimetric satellite observations, Atmos. Meas. Tech., 4, 975–1018, <a href="http://dx.doi.org/10.5194/amt-4-975-2011">https://doi.org/10.5194/amt-4-975-2011</a>, 2011.

Gobbi, G. P., Kaufman, Y. J., Koren, I., and Eck, T. F.: Classification of aerosol properties derived from AERONET direct sun data, Atmos. Chem. Phys., 7, 453–458, <a href="http://dx.doi.org/10.5194/acp-7-453-2007">https://doi.org/10.5194/acp-7-453-2007</a>, 2007.

GOCART: Version 4 model 3 hourly yearly model output, available at: <a href="http://aeronet.gsfc.nasa.gov/cgi-bin/bamgomas_interactive">http://aeronet.gsfc.nasa.gov/cgi-bin/bamgomas_interactive</a>, last access: 7 April 2012.

Gorr, W. L., Nagin, D., and Szczypula, J.: Comparative study of artificial neural network and statistical models for predicting student grade point averages, Int. J. Forecast., 10, 17–34, 1994.

Grubbs, F. E.: Procedures for detecting outlying observations in samples, Technometrics, 11, 1–21, 1969.

Hansen, J., Nazarenko, L., Ruedy, R., Sato, M., Willis, J., Del Genio, A., and Tausnev, N.: Earth's energy imbalance: confirmation and implications, Science, 308, 1431–1435, 2005.

Hasekamp, O. P., Litvinov, P., andButz, A.: Aerosol properties over the ocean from PARASOL multiangle photopolarimetric measurements. J. Geophys. Res., 116, D14204, <a href="http://dx.doi.org/10.1029/2010JD015469">https://doi.org/10.1029/2010JD015469</a>, 2011.

Holben, B. N., Eck, T. F., Slutsker, I., Tanre, D., Buis, J. P., Setzer, A., and Smirnov, A.: Aeronet – a federated instrument network and data archive for aerosol characterization, Remote Sens. Environ., 66, 1–16, 1998.

Hornik, J., Stinchombe, M., and White, H.: Mutlilayer feedforward networks are universal approximators, Neural Networks, 2, 359–366, 1989.

Intergovernmental Panel on Climate Change (IPCC): Climate change 2007, the Physical Science Basis: Contribution of the Working Group I to the Fourth Assessment Report of the IPCC, Cambridge University Press, New York, 2007.

Intergovernmental Panel on Climate Change (IPCC): Climate change 2013 The Physical Science Basis: Contribution of the Working Group I to the Fifth Assessment Report of the IPCC, Cambridge University Press, New York, 2013.

Jolliffe, I. T.: Principal Component Analysis, 2nd Edn., Springer, New York, 2002.

King, M. D., Byrne, D. M., Herman, B. M., and Reagan, J. A.: Aerosol size distributions obtained by inversion of spectral optical depth measurements, J. Atmos. Sci., 21, 2153–2167, 1978.

Lawrence, S., Giles, C. L., and Tsoi, A. C.: What size neural network gives optimal generalization? Convergence properties of backpropagation, Technical Report UMIACS- TR-96-22 and CS-TR-3617, Institute for Advanced Computer Studies, University of Maryland, College Park, MD, United States, 1996.

Levenberg, K.: A method for the solution of certain non-linear problems in least squares, Q. Appl. Math., 2, 164–168, 1944.

Marquardt, D.: An algorithm for least-squares estimation of nonlinear parameters, Siam J. Appl. Math., 11, 431–441, 1963.

Mishchenko, M. I., Cairns, B., Kopp, G., Schueler, C. F., Fafaul, B. A., Hansen, J. E., Hooker, R. J., Itchkawich, T., Maring, H. B., and Travis, L. D.: Accurate monitoring of terrestrial aerosols and total solar irradiance: introducing the Glory mission, B. Am. Meteorol. Soc., 88, 677–691, 2007.

MODIS: Terra & Aqua Level 3 Collection 5.1 daily global 1_×1_products, available at: <a href="http://gdata1.sci.gsfc.nasa.gov/daac-bin/G3/gui.cgi?instance_id=MODIS_DAILY_L3">http://gdata1.sci.gsfc.nasa.gov/daac-bin/G3/gui.cgi?instance_id=MODIS_DAILY_L3</a>, last access: 7 April 2012.

OMI: Aura Level 3 Version 3 daily global 1_×1_gridded aerosol products, available at: <a href="http://gdata1.sci.gsfc.nasa.gov/daac-bin/G3/gui.cgi?instance_id=omi">http://gdata1.sci.gsfc.nasa.gov/daac-bin/G3/gui.cgi?instance_id=omi</a>, last access: 7 April 2012.

Picchiani, M., Chini, M., Corradini, S., Merucci, L., Sellitto, P., Del Frate, F., and Stramondo, S.: Volcanic ash detection and retrievals using MODIS data by means of neural networks, Atmos. Meas. Tech., 4, 2619–2631, <a href="http://dx.doi.org/10.5194/amt-4-2619-2011">https://doi.org/10.5194/amt-4-2619-2011</a>, 2011.

Prospero, J. M., Ginoux, P., Torres, O., Nicholson, S. E., and Gill, T. E.: Environmental characterization of global sources of atmospheric soil dust identified with the Nimbus 7 Total Ozone Mapping Spectrometer (TOMS) absorbing aerosol product, Rev. Geophys., 40, 1–31, 2002.

Radosavljevic, V., Vucetic, S., and Obradovic, Z.: A data-mining technique for aerosol retrieval across multiple accuracy measures, IEEE Geosci. Remote S., 7, 411–415, 2010.

Remer, L. A., Kaufman, Y. J., Tanre, D., Mattoo, S., Chu, D. A., Martins, J. V., Li, R. R., Ichoku, C., Levy, R. C., Kleidman, R. G., Eck, T. F., Vermote, E., and Holben, B. N.: The MODIS aerosol algorithm, products, and validation, J. Atmos. Sci., 62, 947–973, 2005.

Ristovski, K., Vucetic, S., and Obradovic, Z.: Uncertainty analysis of neural-network-based aerosol retrieval, Geosci. Remote Sens., 50, 409–414, 2012.

Samet, J. M., Dominici, M. D. F., Curriero, F. C., Coursac, I., and Zeger, S. L.: Fine particulate air pollution and mortality in 20 U.S. Cities, 1987–1994, New. Engl. J. Medicine, 343, 1742–1749, <a href="http://dx.doi.org/10.1056/NEJM200012143432401">https://doi.org/10.1056/NEJM200012143432401</a>, 2000.

Sayer, A. M., Smirnov, A., Hsu, N. C., and Holben, B. N.: A pure marine aerosol model, for use in remote sensing applications, J. Geophys. Res., 117, 1–25, 2012.

Schwartz, S. E.: Uncertainty requirements in radiative forcing of climate change, J. Air Waste Manage., 54, 1351–9, 2004.

Sellitto, P., Di Noia, A., Del Frate, F., Burini, A., Casadio, S., and Solimini, D.: On the role of visible radiation in ozone profile retrieval from nadir UV/VIS satellite measurements: An experiment with neural network algorithms inverting SCIAMACHY data, J. Quant. Spectr. Radiat. Trans., 113, 1429–1436, 2012.

Stathakis, D.: How many hidden layers and nodes?, Int. J. Remote Sens., 30, 2133–2147, 2009.

Tanré, D., Herman, M., and Kaufman, Y. J.: Information on aerosol size distribution contained in solar reflected spectral radiances, J. Geophys. Res., 101, 19043–19060, 1996.

% Taylor, M., Kazadzis, S., and Gerasopoulos, E.: Multi-modal analysis of % aerosol robotic network size distributions for remote sensing applications: % dominant aerosol type cases, Atmos. Meas. Tech., 7, 839–858, % \doi10.5194/amt-7-839-2014, 2014.

Torres, O., Bhartia, P. K., Herman, J. R., Syniuk, A., Ginoux, P., and Holben, B.: A long term record of aerosol optical depth from TOMS observations and comparison to AERONET measurements, J. Atmos. Sci., 59, 398–413, 2002.

Torres, O., Tanskanen, A., Veihelmann, B., Ahn, C., Braak, Rz., Bhartia, P. K., and Levelt, P.: Aerosols and surface UV products from Ozone Monitoring Instrument observations: an overview, J. Geophys. Res.-Atmos., 112, D24S47, <a href="http://dx.doi.org/https://doi.org/ 10.1029/2007JD008809">https://doi.org/https://doi.org/ 10.1029/2007JD008809</a>, 2007.

Waquet, F., Peers, F., Goloub, P., Ducos, F., Thieuleux, F., Derimian, Y., Riedi, J., Chami, M., and Tanré, D.: Retrieval of the Eyjafjallajökull volcanic aerosol optical and microphysical properties from POLDER/PARASOL measurements, Atmos. Chem. Phys., 14, 1755–1768, <a href="http://dx.doi.org/10.5194/acp-14-1755-2014">https://doi.org/10.5194/acp-14-1755-2014</a>, 2014.