Preprint Article Version 2 This version is not peer-reviewed

Deep Convolutional Neural Networks Capabilities for Binary Classification of Polar Mesocyclones in Satellite Mosaics

Version 1 : Received: 18 September 2018 / Approved: 19 September 2018 / Online: 19 September 2018 (03:36:51 CEST)
Version 2 : Received: 6 October 2018 / Approved: 8 October 2018 / Online: 8 October 2018 (09:51:13 CEST)
Version 3 : Received: 26 October 2018 / Approved: 29 October 2018 / Online: 29 October 2018 (10:16:49 CET)

A peer-reviewed article of this Preprint also exists.

Krinitskiy, M.; Verezemskaya, P.; Grashchenkov, K.; Tilinina, N.; Gulev, S.; Lazzara, M. Deep Convolutional Neural Networks Capabilities for Binary Classification of Polar Mesocyclones in Satellite Mosaics. Atmosphere 2018, 9, 426. Krinitskiy, M.; Verezemskaya, P.; Grashchenkov, K.; Tilinina, N.; Gulev, S.; Lazzara, M. Deep Convolutional Neural Networks Capabilities for Binary Classification of Polar Mesocyclones in Satellite Mosaics. Atmosphere 2018, 9, 426.

Journal reference: Atmosphere 2018, 9, 426
DOI: 10.3390/atmos9110426

Abstract

Polar mesocyclones (MCs) are small marine atmospheric vortices. The class of intense MCs, called polar lows, are accompanied by extremely strong surface winds and heat fluxes and thus largely influencing deep ocean water formation in the polar regions. Accurate detection of polar mesocyclones in high-resolution satellite data, while challenging, is a time-consuming task, when performed manually. Existing algorithms for the automatic detection of polar mesocyclones are based on the conventional analysis of patterns of cloudiness and involve different empirically defined thresholds of geophysical variables. As a result, various detection methods typically reveal very different results when applied to a single dataset. We present a conceptually novel approach for the detection of MCs based on the use of deep convolutional neural networks (DCNNs). We demonstrate that DCNN model is capable of performing binary classification of 500x500km patches of satellite images regarding MC patterns presence in it. The training dataset is based on the reference database of MCs manually tracked in the Southern Hemisphere from satellite mosaics. This dataset is further used for testing several different DCNN setups, specifically, DCNN built “from scratch”, DCNN based on VGG16 pre-trained weights also engaging the Transfer Learning technique, and DCNN based on VGG16 with Fine Tuning technique. Each of these networks is further applied to both infrared (IR) and a combination of infrared and water vapor (IR+WV) satellite imagery. The best skills (97% in terms of the binary classification accuracy score) is achieved with the model that averages the estimates of the ensemble of different DCNNs. The algorithm can be further extended to the automatic identification and tracking numerical scheme and applied to other atmospheric phenomena characterized by a distinct signature in satellite imagery.

Subject Areas

deep learning; convolutional neural networks; polar mesocyclones; satellite data processing; pattern recognition

Comments (0)

We encourage comments and feedback from a broad range of readers. See criteria for comments and our diversity statement.

Leave a public comment
Send a private comment to the author(s)
Views 0
Downloads 0
Comments 0
Metrics 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.