Journal cover Journal topic
Atmospheric Chemistry and Physics An interactive open-access journal of the European Geosciences Union
https://doi.org/10.5194/acp-2018-492
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.
Research article
07 Jun 2018
Review status
This discussion paper is a preprint. It is a manuscript under review for the journal Atmospheric Chemistry and Physics (ACP).
A Neural Network Aerosol Typing Algorithm Based on Lidar Data
Doina Nicolae1, Jeni Vasilescu1, Camelia Talianu1,2, Ioannis Binietoglou1, Victor Nicolae1,3, Simona Andrei1, and Bogdan Antonescu1 1National Institute of R&D for Optoelectronics, 409 Atomiştilor Str., Mǎgurele, Ilfov, România
2Institute of Meteorology, University of Natural Resources and Life Sciences, 33 Gregor-Mendel Str., 1180, Vienna, Austria
3Faculty of Physics, University of Bucharest, 409 Atomiştilor Str., Mǎgurele, Ilfov, Romania
Abstract. Atmospheric aerosols play a crucial role in the earth system, but their role is not completely understood, partly because of the large variability in their properties resulting from a large number of possible aerosol sources. Recently developed techniques were able to retrieve the height distributions of optical and microphysical properties of fine-mode and coarse-mode particles, providing the types of the aerosols depicted. One such technique for aerosol typing is based on artificial neural networks (ANNs). In this article, a Neural Network Aerosol Typing Algorithm Based on Lidar Data (NATALI) was developed to estimate the most probable aerosol type from a set of multispectral data. The algorithm has been adjusted for running on the EARLINET 3ß + 2a (+1d) profiles. The NATALI algorithm is based on the ability of specialized ANNs to resolve the overlapping values of the intensive optical parameters calculated for each identified layer in the multiwavelength Raman lidar profiles. The ANNs were trained using synthetic data, for which a new aerosol model was developed. Two parallel typing schemes were implemented in order to accommodate datasets containing or not the measured linear particle depolarization ratios (LPDR): a) identification of mixtures from 14 aerosol mixtures (high-resolution typing) if the LPDR is available in the input data files, and b) identification of 5 predominant aerosol types (low-resolution typing) if the LPDR is not provided. For each scheme, three ANNs were run simultaneously, and a voting procedure selects the most probable answer. The whole algorithm has been integrated into a Python code. The main issue with the approached used in NATALI is that the results are strongly dependent on the input data, and thus the outputs should be understood accordingly. The algorithm has side-applications, for example, to test the quality of the optical data and identify incorrect calibration or incorrect cloud screening. Blind tests on EARLINET data samples showed the capability of this tool to retrieve the aerosol type from a large variety of data, with different quality and physical content.
Citation: Nicolae, D., Vasilescu, J., Talianu, C., Binietoglou, I., Nicolae, V., Andrei, S., and Antonescu, B.: A Neural Network Aerosol Typing Algorithm Based on Lidar Data, Atmos. Chem. Phys. Discuss., https://doi.org/10.5194/acp-2018-492, in review, 2018.
Doina Nicolae et al.
Doina Nicolae et al.
Doina Nicolae et al.

Viewed

Total article views: 240 (including HTML, PDF, and XML)

HTML PDF XML Total BibTeX EndNote
175 62 3 240 1 3

Views and downloads (calculated since 07 Jun 2018)

Cumulative views and downloads (calculated since 07 Jun 2018)

Viewed (geographical distribution)

Total article views: 240 (including HTML, PDF, and XML)

Thereof 235 with geography defined and 5 with unknown origin.

Country # Views %
  • 1

Saved

Discussed

Latest update: 18 Jun 2018
Publications Copernicus
Download
Short summary
A new aerosol typing algorithm based on artificial neural networks (ANNs) has been developed. The algorithm is providing the most probable aerosol type based on EARLINET LIDAR profiles. The ANNs used by the algorithm were trained using synthetic data, for which a new aerosol model has been developed. Blind tests on EARLINET data samples showed the capability of the algorithm to retrieve the aerosol type from a large variety of data, with different quality and physical content.
A new aerosol typing algorithm based on artificial neural networks (ANNs) has been developed. ...
Share