Open Access
Atmosphere, volume 9, issue 11, pages 426
Deep Convolutional Neural Networks Capabilities for Binary Classification of Polar Mesocyclones in Satellite Mosaics
Verezemskaya Polina
1, 2
,
Grashchenkov Kirill
1, 3
,
Tilinina Natalia
1
,
Gulev Sergey
1
,
Lazzara Matthew
4
4
University of Wisconsin-Madison and Madison Area Technical College, Madison, WI 53704, USA
|
Publication type: Journal Article
Publication date: 2018-10-31
Atmospheric Science
Environmental Science (miscellaneous)
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 they 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 develop a conceptually novel approach for the detection of MCs based on the use of deep convolutional neural networks (DCNNs). As a first step, we demonstrate that DCNN model is capable of performing binary classification of 500 × 500 km 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. We use a subset of this database with MC diameters falling in the range of 200–400 km. 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 that are characterized by a distinct signature in satellite imagery.
Citations by journals
|
1
2
3
4
5
|
|
|
Atmosphere
|
Atmosphere
5 publications, 33.33%
|
|
International journal of computer assisted radiology and surgery
|
International journal of computer assisted radiology and surgery
1 publication, 6.67%
|
|
IOP Conference Series: Earth and Environmental Science
|
IOP Conference Series: Earth and Environmental Science
1 publication, 6.67%
|
|
IEEE Transactions on Geoscience and Remote Sensing
|
IEEE Transactions on Geoscience and Remote Sensing
1 publication, 6.67%
|
|
Strategic Management Journal
|
Strategic Management Journal
1 publication, 6.67%
|
|
Tellus A: Dynamic Meteorology and Oceanography
|
Tellus A: Dynamic Meteorology and Oceanography, 1, 6.67%
Tellus A: Dynamic Meteorology and Oceanography
1 publication, 6.67%
|
|
Springer Geology
|
Springer Geology
1 publication, 6.67%
|
|
Moscow University Physics Bulletin (English Translation of Vestnik Moskovskogo Universiteta, Fizika)
|
Moscow University Physics Bulletin (English Translation of Vestnik Moskovskogo Universiteta, Fizika)
1 publication, 6.67%
|
|
Frontiers in Earth Science
|
Frontiers in Earth Science
1 publication, 6.67%
|
|
1
2
3
4
5
|
Citations by publishers
|
1
2
3
4
5
|
|
|
Multidisciplinary Digital Publishing Institute (MDPI)
|
Multidisciplinary Digital Publishing Institute (MDPI)
5 publications, 33.33%
|
|
Springer Nature
|
Springer Nature
2 publications, 13.33%
|
|
IOP Publishing
|
IOP Publishing
1 publication, 6.67%
|
|
IEEE
|
IEEE
1 publication, 6.67%
|
|
Wiley
|
Wiley
1 publication, 6.67%
|
|
Stockholm University Press
|
Stockholm University Press, 1, 6.67%
Stockholm University Press
1 publication, 6.67%
|
|
Allerton Press
|
Allerton Press, 1, 6.67%
Allerton Press
1 publication, 6.67%
|
|
Frontiers Media S.A.
|
Frontiers Media S.A.
1 publication, 6.67%
|
|
1
2
3
4
5
|
- We do not take into account publications that without a DOI.
- Statistics recalculated only for publications connected to researchers, organizations and labs registered on the platform.
- Statistics recalculated weekly.
{"yearsCitations":{"type":"bar","data":{"show":true,"labels":[2019,2020,2021,2022,2023,2024],"ids":[0,0,0,0,0,0],"codes":[0,0,0,0,0,0],"imageUrls":["","","","","",""],"datasets":[{"label":"Citations number","data":[3,2,5,2,2,1],"backgroundColor":["#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6"],"percentage":["20","13.33","33.33","13.33","13.33","6.67"],"barThickness":null}]},"options":{"indexAxis":"x","maintainAspectRatio":true,"scales":{"y":{"ticks":{"precision":0,"autoSkip":false,"font":{"family":"Montserrat"},"color":"#000000"}},"x":{"ticks":{"stepSize":1,"precision":0,"font":{"family":"Montserrat"},"color":"#000000"}}},"plugins":{"legend":{"position":"top","labels":{"font":{"family":"Montserrat"},"color":"#000000"}},"title":{"display":true,"text":"Citations per year","font":{"size":24,"family":"Montserrat","weight":600},"color":"#000000"}}}},"journals":{"type":"bar","data":{"show":true,"labels":["Atmosphere","International journal of computer assisted radiology and surgery","IOP Conference Series: Earth and Environmental Science","IEEE Transactions on Geoscience and Remote Sensing","Strategic Management Journal","Tellus A: Dynamic Meteorology and Oceanography","Springer Geology","Moscow University Physics Bulletin (English Translation of Vestnik Moskovskogo Universiteta, Fizika)","Frontiers in Earth Science"],"ids":[9708,11348,6042,12644,18543,21665,21235,3806,19415],"codes":[0,0,0,0,0,0,0,0,0],"imageUrls":["\/storage\/images\/resized\/MjH1ITP7lMYGxeqUZfkt2BnVLgjkk413jwBV97XX_medium.webp","\/storage\/images\/resized\/voXLqlsvTwv5p3iMQ8Dhs95nqB4AXOG7Taj7G4ra_medium.webp","\/storage\/images\/resized\/LsKy6OnmmmRGcAU6CZgWQvNiP1polbaSLNrN7zqj_medium.webp","\/storage\/images\/resized\/6scCJegesojp2jubwY3uKCzTAmgsaH2GIFlg6Hfk_medium.webp","\/storage\/images\/resized\/bRyGpdm98BkAUYiK1YFNpl5Z7hPu6Gd87gbIeuG3_medium.webp","","\/storage\/images\/resized\/voXLqlsvTwv5p3iMQ8Dhs95nqB4AXOG7Taj7G4ra_medium.webp","\/storage\/images\/resized\/oZgeErrVFhuDksyqFURLvYS1wtVSBWczh001igGo_medium.webp","\/storage\/images\/resized\/4QWA67eqfcfyOiA8Wk7YnqroHFqQbTsmDJUYTCTg_medium.webp"],"datasets":[{"label":"","data":[5,1,1,1,1,1,1,1,1],"backgroundColor":["#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6"],"percentage":[33.33,6.67,6.67,6.67,6.67,6.67,6.67,6.67,6.67],"barThickness":13}]},"options":{"indexAxis":"y","maintainAspectRatio":false,"scales":{"y":{"ticks":{"precision":0,"autoSkip":false,"font":{"family":"Montserrat"},"color":"#000000"}},"x":{"ticks":{"stepSize":null,"precision":0,"font":{"family":"Montserrat"},"color":"#000000"}}},"plugins":{"legend":{"position":"top","labels":{"font":{"family":"Montserrat"},"color":"#000000"}},"title":{"display":true,"text":"Journals","font":{"size":24,"family":"Montserrat","weight":600},"color":"#000000"}}}},"publishers":{"type":"bar","data":{"show":true,"labels":["Multidisciplinary Digital Publishing Institute (MDPI)","Springer Nature","IOP Publishing","IEEE","Wiley","Stockholm University Press","Allerton Press","Frontiers Media S.A."],"ids":[202,8,2075,6953,11,3948,6983,208],"codes":[0,0,0,0,0,0,0,0],"imageUrls":["\/storage\/images\/resized\/MjH1ITP7lMYGxeqUZfkt2BnVLgjkk413jwBV97XX_medium.webp","\/storage\/images\/resized\/voXLqlsvTwv5p3iMQ8Dhs95nqB4AXOG7Taj7G4ra_medium.webp","\/storage\/images\/resized\/LsKy6OnmmmRGcAU6CZgWQvNiP1polbaSLNrN7zqj_medium.webp","\/storage\/images\/resized\/6scCJegesojp2jubwY3uKCzTAmgsaH2GIFlg6Hfk_medium.webp","\/storage\/images\/resized\/bRyGpdm98BkAUYiK1YFNpl5Z7hPu6Gd87gbIeuG3_medium.webp","","","\/storage\/images\/resized\/4QWA67eqfcfyOiA8Wk7YnqroHFqQbTsmDJUYTCTg_medium.webp"],"datasets":[{"label":"","data":[5,2,1,1,1,1,1,1],"backgroundColor":["#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6"],"percentage":[33.33,13.33,6.67,6.67,6.67,6.67,6.67,6.67],"barThickness":13}]},"options":{"indexAxis":"y","maintainAspectRatio":false,"scales":{"y":{"ticks":{"precision":0,"autoSkip":false,"font":{"family":"Montserrat"},"color":"#000000"}},"x":{"ticks":{"stepSize":null,"precision":0,"font":{"family":"Montserrat"},"color":"#000000"}}},"plugins":{"legend":{"position":"top","labels":{"font":{"family":"Montserrat"},"color":"#000000"}},"title":{"display":true,"text":"Publishers","font":{"size":24,"family":"Montserrat","weight":600},"color":"#000000"}}}}}
Metrics
Cite this
GOST |
RIS |
BibTex |
MLA
Cite this
GOST
Copy
Krinitskiy M. et al. Deep Convolutional Neural Networks Capabilities for Binary Classification of Polar Mesocyclones in Satellite Mosaics // Atmosphere. 2018. Vol. 9. No. 11. p. 426.
GOST all authors (up to 50)
Copy
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. Vol. 9. No. 11. p. 426.
Cite this
RIS
Copy
TY - JOUR
DO - 10.3390/atmos9110426
UR - https://doi.org/10.3390%2Fatmos9110426
TI - Deep Convolutional Neural Networks Capabilities for Binary Classification of Polar Mesocyclones in Satellite Mosaics
T2 - Atmosphere
AU - Krinitskiy, Mikhail
AU - Verezemskaya, Polina
AU - Grashchenkov, Kirill
AU - Gulev, Sergey
AU - Lazzara, Matthew
AU - Tilinina, Natalia
PY - 2018
DA - 2018/10/31 00:00:00
PB - Multidisciplinary Digital Publishing Institute (MDPI)
SP - 426
IS - 11
VL - 9
SN - 2073-4433
ER -
Cite this
BibTex
Copy
@article{2018_Krinitskiy,
author = {Mikhail Krinitskiy and Polina Verezemskaya and Kirill Grashchenkov and Sergey Gulev and Matthew Lazzara and Natalia Tilinina},
title = {Deep Convolutional Neural Networks Capabilities for Binary Classification of Polar Mesocyclones in Satellite Mosaics},
journal = {Atmosphere},
year = {2018},
volume = {9},
publisher = {Multidisciplinary Digital Publishing Institute (MDPI)},
month = {oct},
url = {https://doi.org/10.3390%2Fatmos9110426},
number = {11},
pages = {426},
doi = {10.3390/atmos9110426}
}
Cite this
MLA
Copy
Krinitskiy, Mikhail, et al. “Deep Convolutional Neural Networks Capabilities for Binary Classification of Polar Mesocyclones in Satellite Mosaics.” Atmosphere, vol. 9, no. 11, Oct. 2018, p. 426. https://doi.org/10.3390%2Fatmos9110426.