% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Sedona:878382,
author = {Sedona, Rocco and Hoffmann, Lars and Spang, Reinhold and
Cavallaro, Gabriele and Griessbach, Sabine and Höpfner,
Michael and Book, Matthias and Riedel, Morris},
title = {{E}xploration of machine learning methods for the
classification of infrared limb spectra of polar
stratospheric clouds},
journal = {Atmospheric measurement techniques},
volume = {13},
number = {7},
issn = {1867-8548},
address = {Katlenburg-Lindau},
publisher = {Copernicus},
reportid = {FZJ-2020-02819},
pages = {3661 - 3682},
year = {2020},
abstract = {Polar stratospheric clouds (PSCs) play a key role in polar
ozone depletion in the stratosphere. Improved observations
and continuous monitoring of PSCs can help to validate and
improve chemistry–climate models that are used to predict
the evolution of the polar ozone hole. In this paper, we
explore the potential of applying machine learning (ML)
methods to classify PSC observations of infrared limb
sounders. Two datasets were considered in this study. The
first dataset is a collection of infrared spectra captured
in Northern Hemisphere winter 2006/2007 and Southern
Hemisphere winter 2009 by the Michelson Interferometer for
Passive Atmospheric Sounding (MIPAS) instrument on board the
European Space Agency's (ESA) Envisat satellite. The second
dataset is the cloud scenario database (CSDB) of simulated
MIPAS spectra. We first performed an initial analysis to
assess the basic characteristics of the CSDB and to decide
which features to extract from it. Here, we focused on an
approach using brightness temperature differences (BTDs).
From both the measured and the simulated infrared spectra,
more than 10 000 BTD features were generated. Next, we
assessed the use of ML methods for the reduction of the
dimensionality of this large feature space using principal
component analysis (PCA) and kernel principal component
analysis (KPCA) followed by a classification with the
support vector machine (SVM). The random forest (RF)
technique, which embeds the feature selection step, has also
been used as a classifier. All methods were found to be
suitable to retrieve information on the composition of PSCs.
Of these, RF seems to be the most promising method, being
less prone to overfitting and producing results that agree
well with established results based on conventional
classification methods.},
cin = {JSC / IEK-7},
ddc = {550},
cid = {I:(DE-Juel1)JSC-20090406 / I:(DE-Juel1)IEK-7-20101013},
pnm = {244 - Composition and dynamics of the upper troposphere and
middle atmosphere (POF3-244) / 511 - Computational Science
and Mathematical Methods (POF3-511) / 512 - Data-Intensive
Science and Federated Computing (POF3-512)},
pid = {G:(DE-HGF)POF3-244 / G:(DE-HGF)POF3-511 /
G:(DE-HGF)POF3-512},
typ = {PUB:(DE-HGF)16},
UT = {WOS:000548519300003},
doi = {10.5194/amt-13-3661-2020},
url = {https://juser.fz-juelich.de/record/878382},
}