Journal cover Journal topic
Atmospheric Chemistry and Physics An interactive open-access journal of the European Geosciences Union
Journal topic

Journal metrics

Journal metrics

  • IF value: 5.668 IF 5.668
  • IF 5-year value: 6.201 IF 5-year
    6.201
  • CiteScore value: 6.13 CiteScore
    6.13
  • SNIP value: 1.633 SNIP 1.633
  • IPP value: 5.91 IPP 5.91
  • SJR value: 2.938 SJR 2.938
  • Scimago H <br class='hide-on-tablet hide-on-mobile'>index value: 174 Scimago H
    index 174
  • h5-index value: 87 h5-index 87
Volume 16, issue 13
Atmos. Chem. Phys., 16, 8181-8191, 2016
https://doi.org/10.5194/acp-16-8181-2016
© Author(s) 2016. This work is distributed under
the Creative Commons Attribution 3.0 License.
Atmos. Chem. Phys., 16, 8181-8191, 2016
https://doi.org/10.5194/acp-16-8181-2016
© Author(s) 2016. This work is distributed under
the Creative Commons Attribution 3.0 License.

Research article 07 Jul 2016

Research article | 07 Jul 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

Jani Huttunen1,2, Harri Kokkola1, Tero Mielonen1, Mika Esa Juhani Mononen3, Antti Lipponen1,2, Juha Reunanen4, Anders Vilhelm Lindfors1, Santtu Mikkonen2, Kari Erkki Juhani Lehtinen1,2, Natalia Kouremeti5,6, Alkiviadis Bais6, Harri Niska7, and Antti Arola1 Jani Huttunen et al.
  • 1Finnish Meteorological Institute (FMI), Atmospheric Research Centre of Eastern Finland, Kuopio, Finland
  • 2Department of Applied Physics, University of Eastern Finland, Kuopio, Finland
  • 3Independent researcher, Kuopio, Finland
  • 4Tomaattinen Oy, Helsinki, Finland
  • 5Physikalisch-Meteorologisches Observatorium Davos, Dorfstrasse 33, 7260 Davos Dorf, Switzerland
  • 6Aristotle University of Thessaloniki, Laboratory of Atmospheric Physics, Thessaloniki, 54124, Greece
  • 7Department of Environmental and Biological Sciences, University of Eastern Finland, Kuopio, Finland

Abstract. In order to have a good estimate of the current forcing by anthropogenic aerosols, knowledge on past aerosol levels is needed. Aerosol optical depth (AOD) is a good measure for aerosol loading. However, dedicated measurements of AOD are only available from the 1990s onward. One option to lengthen the AOD time series beyond the 1990s is to retrieve AOD from surface solar radiation (SSR) measurements taken with pyranometers. In this work, we have evaluated several inversion methods designed for this task. We compared a look-up table method based on radiative transfer modelling, a non-linear regression method and four machine learning methods (Gaussian process, neural network, random forest and support vector machine) with AOD observations carried out with a sun photometer at an Aerosol Robotic Network (AERONET) site in Thessaloniki, Greece. Our results show that most of the machine learning methods produce AOD estimates comparable to the look-up table and non-linear regression methods. All of the applied methods produced AOD values that corresponded well to the AERONET observations with the lowest correlation coefficient value being 0.87 for the random forest method. While many of the methods tended to slightly overestimate low AODs and underestimate high AODs, neural network and support vector machine showed overall better correspondence for the whole AOD range. The differences in producing both ends of the AOD range seem to be caused by differences in the aerosol composition. High AODs were in most cases those with high water vapour content which might affect the aerosol single scattering albedo (SSA) through uptake of water into aerosols. Our study indicates that machine learning methods benefit from the fact that they do not constrain the aerosol SSA in the retrieval, whereas the LUT method assumes a constant value for it. This would also mean that machine learning methods could have potential in reproducing AOD from SSR even though SSA would have changed during the observation period.

Publications Copernicus
Download
Short summary
For a good estimate of the current forcing by anthropogenic aerosols, knowledge in past is needed. One option to lengthen time series is to retrieve aerosol optical depth from solar radiation measurements. We have evaluated several methods for this task. Most of the methods produce aerosol optical depth estimates with a good accuracy. However, machine learning methods seem to be the most applicable not to produce any systematic biases, since they do not need constrain the aerosol properties.
For a good estimate of the current forcing by anthropogenic aerosols, knowledge in past is...
Citation
Share