EGU2020-8103
https://doi.org/10.5194/egusphere-egu2020-8103
EGU General Assembly 2020
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

Using machine learning method to classify polar stratospheric cloud types from Envisat MIPAS observations

Rocco Sedona1,4, Lars Hoffmann1, Reinhold Spang2, Gabriele Cavallaro1, Sabine Griessbach1, Michael Höpfner3, Matthias Book4, and Morris Riedel4
Rocco Sedona et al.
  • 1Jülich Supercomputing Centre, Forschungszentrum Jülich, Jülich, Germany (r.sedona@fz-juelich.de)
  • 2Institut für Energie- und Klimaforschung (IEK-7), Forschungszentrum Jülich, Jülich, Germany
  • 3Institut für Meteorlogie und Klimaforschung, Karlsruher Institut für Technologie, Karlsruhe, Germany
  • 4University of Iceland, Reykjavik, Iceland

Polar stratospheric clouds (PSC) play a key role in polar ozone depletion in the stratosphere. Improved observations and continuous monitoring of PSCs can help to validate and enhance chemistry-climate models that are used to predict the evolution of the polar ozone hole. Here we present the results of our study in which we explored the potential of applying machine learning (ML) methods to classify PSC observations of infrared limb sounders. Two datasets have been considered. 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 onboard ESA's 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 these datasets and to decide which features to extract from them. More than 10,000 Brightness temperature differences (BTDs) features have been generated and fed as input to the ML methods instead of directly using the infrared spectra. 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) as well as the classification with the random forest (RF) and support vector machine (SVM) techniques. 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.

How to cite: Sedona, R., Hoffmann, L., Spang, R., Cavallaro, G., Griessbach, S., Höpfner, M., Book, M., and Riedel, M.: Using machine learning method to classify polar stratospheric cloud types from Envisat MIPAS observations, EGU General Assembly 2020, Online, 4–8 May 2020, EGU2020-8103, https://doi.org/10.5194/egusphere-egu2020-8103, 2020

Displays

Display file