Automated detection and classification of synoptic-scale fronts from atmospheric data grids

Automatic determination of fronts from atmospheric data is an important task for weather prediction as well as for research of synoptic-scale phenomena. In this paper we introduce a deep neural network to detect and classify fronts from multi-level ERA5 reanalysis data. Model training and prediction...

Full description

Saved in:
Bibliographic Details
Published inWeather and climate dynamics Vol. 3; no. 1; pp. 113 - 137
Main Authors Niebler, Stefan, Miltenberger, Annette, Schmidt, Bertil, Spichtinger, Peter
Format Journal Article
LanguageEnglish
Published Copernicus Publications 01.02.2022
Online AccessGet full text

Cover

Loading…
Abstract Automatic determination of fronts from atmospheric data is an important task for weather prediction as well as for research of synoptic-scale phenomena. In this paper we introduce a deep neural network to detect and classify fronts from multi-level ERA5 reanalysis data. Model training and prediction is evaluated using two different regions covering Europe and North America with data from two weather services. We apply label deformation within our loss function, which removes the need for skeleton operations or other complicated post-processing steps as used in other work, to create the final output. We obtain good prediction scores with a critical success index higher than 66.9 % and an object detection rate of more than 77.3 %. Frontal climatologies of our network are highly correlated (greater than 77.2 %) to climatologies created from weather service data. Comparison with a well-established baseline method based on thermodynamic criteria shows a better performance of our network classification. Evaluated cross sections further show that the surface front data of the weather services as well as our network classification are physically plausible. Finally, we investigate the link between fronts and extreme precipitation events to showcase possible applications of the proposed method. This demonstrates the usefulness of our new method for scientific investigations.
AbstractList Automatic determination of fronts from atmospheric data is an important task for weather prediction as well as for research of synoptic-scale phenomena. In this paper we introduce a deep neural network to detect and classify fronts from multi-level ERA5 reanalysis data. Model training and prediction is evaluated using two different regions covering Europe and North America with data from two weather services. We apply label deformation within our loss function, which removes the need for skeleton operations or other complicated post-processing steps as used in other work, to create the final output. We obtain good prediction scores with a critical success index higher than 66.9 % and an object detection rate of more than 77.3 %. Frontal climatologies of our network are highly correlated (greater than 77.2 %) to climatologies created from weather service data. Comparison with a well-established baseline method based on thermodynamic criteria shows a better performance of our network classification. Evaluated cross sections further show that the surface front data of the weather services as well as our network classification are physically plausible. Finally, we investigate the link between fronts and extreme precipitation events to showcase possible applications of the proposed method. This demonstrates the usefulness of our new method for scientific investigations.
Author Spichtinger, Peter
Miltenberger, Annette
Niebler, Stefan
Schmidt, Bertil
Author_xml – sequence: 1
  givenname: Stefan
  surname: Niebler
  fullname: Niebler, Stefan
– sequence: 2
  givenname: Annette
  orcidid: 0000-0003-3320-4272
  surname: Miltenberger
  fullname: Miltenberger, Annette
– sequence: 3
  givenname: Bertil
  surname: Schmidt
  fullname: Schmidt, Bertil
– sequence: 4
  givenname: Peter
  orcidid: 0000-0003-4008-4977
  surname: Spichtinger
  fullname: Spichtinger, Peter
BookMark eNpNkEtLAzEYRYNUsNZuXecPTM1rZpJlKT4KBTe6chG-yaOmTCcliUj_vdNWxNW93MXhcm7RZIiDQ-iekkVNlXj4NrbiFaW8YoSxKzRljZKVILSZ_Os3aJ7zjhDCZMtFI6foY_lV4h6Ks9i64kwJccAwWGx6yDn4YOA8RY_zcYiHEkyVDfQO-xSHkk-xx1D2MR8-XQoGWyiAtynYfIeuPfTZzX9zht6fHt9WL9Xm9Xm9Wm4qw0VdKtko7q3oSMu8smNRvjaMthwYaa2y0tWdp1zWrRI1BQrOSyaJh453HTjCZ2h94doIO31IYQ_pqCMEfR5i2mpI4_HeadMw7qlQrOmc4KJVQDoPUAtmqFFUjqzFhWVSzDk5_8ejRJ9M69G05no0rU-m-Q-xEnSt
CitedBy_id crossref_primary_10_5194_gmd_16_4427_2023
crossref_primary_10_1126_sciadv_adh4195
Cites_doi 10.3390/cli7110130
10.1175/JCLI-D-15-0171.1
10.1002/qj.3803
10.1175/BAMS-87-3-343
10.1175/BAMS-D-16-0261.1
10.2151/sola.2019-028
10.1109/TPAMI.2016.2572683
10.1175/MWR-D-18-0289.1
10.1002/joc.4373
10.1002/2017GL073662
10.1016/j.wace.2021.100313
10.1002/met.204
10.1007/s00382-020-05619-2
10.1029/2010GL046451
10.1002/jgrd.50852
10.1175/BAMS-D-18-0137.1
10.1175/MWR-D-12-00252.1
10.1175/1520-0493(1965)093<0547:EINOFA>2.3.CO;2
10.1175/JCLI-D-11-00100.1
10.1017/S1350482798000553
10.1175/WAF-D-18-0183.1
10.5194/ascmo-5-147-2019
10.3390/atmos12101312
10.1002/qj.2471
10.1007/978-3-319-24574-4_28
10.1002/2016GL070017
10.1175/1520-0493(1999)127<0945:APMOSM>2.0.CO;2
10.1109/CVPR.2019.01133
10.1175/JCLI-D-11-00705.1
10.3103/S1068373914010014
10.25080/Majora-92bf1922-011
10.1002/met.142
10.1175/BAMS-85-6-837
10.1002/joc.4945
ContentType Journal Article
DBID AAYXX
CITATION
DOA
DOI 10.5194/wcd-3-113-2022
DatabaseName CrossRef
Open Access: DOAJ - Directory of Open Access Journals
DatabaseTitle CrossRef
DatabaseTitleList CrossRef

Database_xml – sequence: 1
  dbid: DOA
  name: Open Access: DOAJ - Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
Discipline Meteorology & Climatology
EISSN 2698-4016
EndPage 137
ExternalDocumentID oai_doaj_org_article_c623f14926be43479a0bfaa542c1c918
10_5194_wcd_3_113_2022
GroupedDBID AAFWJ
AAYXX
AFPKN
AHGZY
ALMA_UNASSIGNED_HOLDINGS
CITATION
GROUPED_DOAJ
H13
M~E
OK1
ID FETCH-LOGICAL-c345t-8693fd4b072f9dd4b9f5c2173a207d9d8e5bf138579451a1aef8280fab3bbae03
IEDL.DBID DOA
ISSN 2698-4016
IngestDate Tue Oct 22 15:08:18 EDT 2024
Fri Aug 23 01:15:42 EDT 2024
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 1
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c345t-8693fd4b072f9dd4b9f5c2173a207d9d8e5bf138579451a1aef8280fab3bbae03
ORCID 0000-0003-4008-4977
0000-0003-3320-4272
OpenAccessLink https://doaj.org/article/c623f14926be43479a0bfaa542c1c918
PageCount 25
ParticipantIDs doaj_primary_oai_doaj_org_article_c623f14926be43479a0bfaa542c1c918
crossref_primary_10_5194_wcd_3_113_2022
PublicationCentury 2000
PublicationDate 2022-02-01
PublicationDateYYYYMMDD 2022-02-01
PublicationDate_xml – month: 02
  year: 2022
  text: 2022-02-01
  day: 01
PublicationDecade 2020
PublicationTitle Weather and climate dynamics
PublicationYear 2022
Publisher Copernicus Publications
Publisher_xml – name: Copernicus Publications
References ref13
ref35
ref12
ref34
ref15
ref37
ref14
ref36
ref31
ref30
ref11
ref33
ref10
ref32
ref2
ref1
ref17
ref39
ref16
ref38
ref19
ref18
ref24
ref23
ref45
ref26
ref25
ref20
ref42
ref41
ref22
ref44
ref21
ref43
ref28
ref27
ref29
ref8
ref7
ref9
ref4
ref3
ref6
ref5
ref40
References_xml – ident: ref4
  doi: 10.3390/cli7110130
– ident: ref8
  doi: 10.1175/JCLI-D-15-0171.1
– ident: ref13
  doi: 10.1002/qj.3803
– ident: ref24
  doi: 10.1175/BAMS-87-3-343
– ident: ref37
  doi: 10.1175/BAMS-D-16-0261.1
– ident: ref22
  doi: 10.2151/sola.2019-028
– ident: ref41
  doi: 10.1109/TPAMI.2016.2572683
– ident: ref43
  doi: 10.1175/MWR-D-18-0289.1
– ident: ref33
  doi: 10.1002/joc.4373
– ident: ref45
– ident: ref29
  doi: 10.1002/2017GL073662
– ident: ref7
  doi: 10.1016/j.wace.2021.100313
– ident: ref15
  doi: 10.1002/met.204
– ident: ref17
  doi: 10.1007/s00382-020-05619-2
– ident: ref25
– ident: ref2
  doi: 10.1029/2010GL046451
– ident: ref9
  doi: 10.1002/jgrd.50852
– ident: ref44
  doi: 10.1175/BAMS-D-18-0137.1
– ident: ref27
– ident: ref16
  doi: 10.1175/MWR-D-12-00252.1
– ident: ref32
  doi: 10.1175/1520-0493(1965)093<0547:EINOFA>2.3.CO;2
– ident: ref42
  doi: 10.1175/JCLI-D-11-00100.1
– ident: ref11
– ident: ref14
  doi: 10.1017/S1350482798000553
– ident: ref30
– ident: ref20
  doi: 10.1175/WAF-D-18-0183.1
– ident: ref38
– ident: ref3
  doi: 10.5194/ascmo-5-147-2019
– ident: ref5
  doi: 10.3390/atmos12101312
– ident: ref36
  doi: 10.1002/qj.2471
– ident: ref34
  doi: 10.1007/978-3-319-24574-4_28
– ident: ref21
  doi: 10.1002/2016GL070017
– ident: ref28
– ident: ref35
  doi: 10.1175/1520-0493(1999)127<0945:APMOSM>2.0.CO;2
– ident: ref23
– ident: ref1
  doi: 10.1109/CVPR.2019.01133
– ident: ref26
– ident: ref31
  doi: 10.1175/JCLI-D-11-00705.1
– ident: ref40
  doi: 10.3103/S1068373914010014
– ident: ref39
  doi: 10.25080/Majora-92bf1922-011
– ident: ref19
  doi: 10.1002/met.142
– ident: ref18
– ident: ref6
  doi: 10.1175/BAMS-85-6-837
– ident: ref10
– ident: ref12
  doi: 10.1002/joc.4945
SSID ssj0002873468
Score 2.26176
Snippet Automatic determination of fronts from atmospheric data is an important task for weather prediction as well as for research of synoptic-scale phenomena. In...
SourceID doaj
crossref
SourceType Open Website
Aggregation Database
StartPage 113
Title Automated detection and classification of synoptic-scale fronts from atmospheric data grids
URI https://doaj.org/article/c623f14926be43479a0bfaa542c1c918
Volume 3
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8QwEA7iyYv4xPVFDqKnYPPatsdVXERYTy4IHsrkJSvayrYiXvztTtJV1pMXL21TQgnfZJpvkskXQk68Lo0CpdDFnWIKArBShMC8D14o7YS0Kcv3dng9VTf3-n7pqK-YE9bLA_fAnVscnwOPsnbGq7jtETITALQSltuS99t8uV4Kpp7SlFEu1bDoVRqRpKjzd-uYZJxL7BdC_BqFlsT606gy3iDrCzpIR30zNsmKr7fIYIJMtpmnCW96Si-fZ0grU2mbPIzeugaL3lHnu5RHVVOoHbWRBse8nwQ1bQJtP-oGfwiWtWgHT0OUKmjj7YVC99K0UVBgZmnMEaWP85lrd8h0fHV3ec0WByQwK5XuWDEsZXDKZLkIpcOHMmiLMYYEkeWudIXXJnBZaHQ6zYGDDxhgZQGMNAZ8JnfJat3Ufo9QBSaHPB-CS0unptAWvTV3DitC4HpAzr4Bq157HYwK44cIbYXQVhJDCVlFaAfkIuL5UyvqV6cXaNVqYdXqL6vu_8dHDshabFCfY31IVrv5mz9CCtGZ49Rb8Dr5vPoCBNPH5w
link.rule.ids 315,786,790,870,2115,27955,27956
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Automated+detection+and+classification+of+synoptic-scale+fronts+from+atmospheric+data+grids&rft.jtitle=Weather+and+climate+dynamics&rft.au=Niebler%2C+Stefan&rft.au=Miltenberger%2C+Annette&rft.au=Schmidt%2C+Bertil&rft.au=Spichtinger%2C+Peter&rft.date=2022-02-01&rft.issn=2698-4016&rft.eissn=2698-4016&rft.volume=3&rft.issue=1&rft.spage=113&rft.epage=137&rft_id=info:doi/10.5194%2Fwcd-3-113-2022&rft.externalDBID=n%2Fa&rft.externalDocID=10_5194_wcd_3_113_2022
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2698-4016&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2698-4016&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2698-4016&client=summon