English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

. Polar stratospheric clouds (PSCs) play a key role in polar ozone depletion in thestratosphere. Improved observations and continuous monitoring of PSCs can help to validate andimprove chemistry–climate models that are used to predict the evolution of the polar ozonehole. In this paper, we explore the potential of applying machine learning (ML) methods toclassify PSC observations of infrared limb sounders. Two datasets were considered in thisstudy. The first dataset is a collection of infrared spectra captured in Northern Hemispherewinter 2006/2007 and Southern Hemisphere winter 2009 by the Michelson Interferometer for PassiveAtmospheric Sounding (MIPAS) instrument on board the European Space Agency's (ESA) Envisat satellite. The second dataset is thecloud scenario database (CSDB) of simulated MIPAS spectra. We first performed an initial analysisto assess the basic characteristics of the CSDB and to decide which features to extract fromit. Here, we focused on an approach using brightness temperature differences (BTDs). From boththe measured and the simulated infrared spectra, more than 10 000 BTD features weregenerated. Next, we assessed the use of ML methods for the reduction of the dimensionality of thislarge feature space using principal component analysis (PCA) and kernel principal componentanalysis (KPCA) followed by a classification with the support vector machine (SVM). The randomforest (RF) technique, which embeds the feature selection step, has also been used asa classifier. All methods were found to be suitable to retrieve information on the composition ofPSCs. Of these, RF seems to be the most promising method, being less prone to overfitting andproducing results that agree well with established results based on conventional classificationmethods.

Exploration of machine learning methods for the classification of infrared limb spectra of polar stratospheric clouds