Transferability of the Deep Learning Mask R-CNN Model for Automated Mapping of Ice-Wedge Polygons in High-Resolution Satellite and UAV Images

State-of-the-art deep learning technology has been successfully applied to relatively small selected areas of very high spatial resolution (0.15 and 0.25 m) optical aerial imagery acquired by a fixed-wing aircraft to automatically characterize ice-wedge polygons (IWPs) in the Arctic tundra. However,...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Remote sensing (Basel, Switzerland) Ročník 12; číslo 7; s. 1085
Hlavní autori: Zhang, Weixing, Liljedahl, Anna K., Kanevskiy, Mikhail, Epstein, Howard E., Jones, Benjamin M., Jorgenson, M. Torre, Kent, Kelcy
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Basel MDPI AG 28.03.2020
Predmet:
ISSN:2072-4292, 2072-4292
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract State-of-the-art deep learning technology has been successfully applied to relatively small selected areas of very high spatial resolution (0.15 and 0.25 m) optical aerial imagery acquired by a fixed-wing aircraft to automatically characterize ice-wedge polygons (IWPs) in the Arctic tundra. However, any mapping of IWPs at regional to continental scales requires images acquired on different sensor platforms (particularly satellite) and a refined understanding of the performance stability of the method across sensor platforms through reliable evaluation assessments. In this study, we examined the transferability of a deep learning Mask Region-Based Convolutional Neural Network (R-CNN) model for mapping IWPs in satellite remote sensing imagery (~0.5 m) covering 272 km2 and unmanned aerial vehicle (UAV) (0.02 m) imagery covering 0.32 km2. Multi-spectral images were obtained from the WorldView-2 satellite sensor and pan-sharpened to ~0.5 m, and a 20 mp CMOS sensor camera onboard a UAV, respectively. The training dataset included 25,489 and 6022 manually delineated IWPs from satellite and fixed-wing aircraft aerial imagery near the Arctic Coastal Plain, northern Alaska. Quantitative assessments showed that individual IWPs were correctly detected at up to 72% and 70%, and delineated at up to 73% and 68% F1 score accuracy levels for satellite and UAV images, respectively. Expert-based qualitative assessments showed that IWPs were correctly detected at good (40–60%) and excellent (80–100%) accuracy levels for satellite and UAV images, respectively, and delineated at excellent (80–100%) level for both images. We found that (1) regardless of spatial resolution and spectral bands, the deep learning Mask R-CNN model effectively mapped IWPs in both remote sensing satellite and UAV images; (2) the model achieved a better accuracy in detection with finer image resolution, such as UAV imagery, yet a better accuracy in delineation with coarser image resolution, such as satellite imagery; (3) increasing the number of training data with different resolutions between the training and actual application imagery does not necessarily result in better performance of the Mask R-CNN in IWPs mapping; (4) and overall, the model underestimates the total number of IWPs particularly in terms of disjoint/incomplete IWPs.
AbstractList State-of-the-art deep learning technology has been successfully applied to relatively small selected areas of very high spatial resolution (0.15 and 0.25 m) optical aerial imagery acquired by a fixed-wing aircraft to automatically characterize ice-wedge polygons (IWPs) in the Arctic tundra. However, any mapping of IWPs at regional to continental scales requires images acquired on different sensor platforms (particularly satellite) and a refined understanding of the performance stability of the method across sensor platforms through reliable evaluation assessments. In this study, we examined the transferability of a deep learning Mask Region-Based Convolutional Neural Network (R-CNN) model for mapping IWPs in satellite remote sensing imagery (~0.5 m) covering 272 km² and unmanned aerial vehicle (UAV) (0.02 m) imagery covering 0.32 km². Multi-spectral images were obtained from the WorldView-2 satellite sensor and pan-sharpened to ~0.5 m, and a 20 mp CMOS sensor camera onboard a UAV, respectively. The training dataset included 25,489 and 6022 manually delineated IWPs from satellite and fixed-wing aircraft aerial imagery near the Arctic Coastal Plain, northern Alaska. Quantitative assessments showed that individual IWPs were correctly detected at up to 72% and 70%, and delineated at up to 73% and 68% F1 score accuracy levels for satellite and UAV images, respectively. Expert-based qualitative assessments showed that IWPs were correctly detected at good (40–60%) and excellent (80–100%) accuracy levels for satellite and UAV images, respectively, and delineated at excellent (80–100%) level for both images. We found that (1) regardless of spatial resolution and spectral bands, the deep learning Mask R-CNN model effectively mapped IWPs in both remote sensing satellite and UAV images; (2) the model achieved a better accuracy in detection with finer image resolution, such as UAV imagery, yet a better accuracy in delineation with coarser image resolution, such as satellite imagery; (3) increasing the number of training data with different resolutions between the training and actual application imagery does not necessarily result in better performance of the Mask R-CNN in IWPs mapping; (4) and overall, the model underestimates the total number of IWPs particularly in terms of disjoint/incomplete IWPs.
State-of-the-art deep learning technology has been successfully applied to relatively small selected areas of very high spatial resolution (0.15 and 0.25 m) optical aerial imagery acquired by a fixed-wing aircraft to automatically characterize ice-wedge polygons (IWPs) in the Arctic tundra. However, any mapping of IWPs at regional to continental scales requires images acquired on different sensor platforms (particularly satellite) and a refined understanding of the performance stability of the method across sensor platforms through reliable evaluation assessments. In this study, we examined the transferability of a deep learning Mask Region-Based Convolutional Neural Network (R-CNN) model for mapping IWPs in satellite remote sensing imagery (~0.5 m) covering 272 km2 and unmanned aerial vehicle (UAV) (0.02 m) imagery covering 0.32 km2. Multi-spectral images were obtained from the WorldView-2 satellite sensor and pan-sharpened to ~0.5 m, and a 20 mp CMOS sensor camera onboard a UAV, respectively. The training dataset included 25,489 and 6022 manually delineated IWPs from satellite and fixed-wing aircraft aerial imagery near the Arctic Coastal Plain, northern Alaska. Quantitative assessments showed that individual IWPs were correctly detected at up to 72% and 70%, and delineated at up to 73% and 68% F1 score accuracy levels for satellite and UAV images, respectively. Expert-based qualitative assessments showed that IWPs were correctly detected at good (40–60%) and excellent (80–100%) accuracy levels for satellite and UAV images, respectively, and delineated at excellent (80–100%) level for both images. We found that (1) regardless of spatial resolution and spectral bands, the deep learning Mask R-CNN model effectively mapped IWPs in both remote sensing satellite and UAV images; (2) the model achieved a better accuracy in detection with finer image resolution, such as UAV imagery, yet a better accuracy in delineation with coarser image resolution, such as satellite imagery; (3) increasing the number of training data with different resolutions between the training and actual application imagery does not necessarily result in better performance of the Mask R-CNN in IWPs mapping; (4) and overall, the model underestimates the total number of IWPs particularly in terms of disjoint/incomplete IWPs.
Author Zhang, Weixing
Jones, Benjamin M.
Epstein, Howard E.
Kent, Kelcy
Liljedahl, Anna K.
Kanevskiy, Mikhail
Jorgenson, M. Torre
Author_xml – sequence: 1
  givenname: Weixing
  orcidid: 0000-0001-8253-3932
  surname: Zhang
  fullname: Zhang, Weixing
– sequence: 2
  givenname: Anna K.
  surname: Liljedahl
  fullname: Liljedahl, Anna K.
– sequence: 3
  givenname: Mikhail
  surname: Kanevskiy
  fullname: Kanevskiy, Mikhail
– sequence: 4
  givenname: Howard E.
  surname: Epstein
  fullname: Epstein, Howard E.
– sequence: 5
  givenname: Benjamin M.
  orcidid: 0000-0002-1517-4711
  surname: Jones
  fullname: Jones, Benjamin M.
– sequence: 6
  givenname: M. Torre
  surname: Jorgenson
  fullname: Jorgenson, M. Torre
– sequence: 7
  givenname: Kelcy
  surname: Kent
  fullname: Kent, Kelcy
BookMark eNptkU1vEzEQhleoSJTSC7_AEheEtODPrPcYhY9GSgsqLRytye5467Cxg-095Efwn-s0CFCFLzPyPO87Hs_z6sQHj1X1ktG3QrT0XUyM04ZRrZ5UpyXjteQtP_knf1adp7Sh5QjBWipPq183EXyyGGHtRpf3JFiS75C8R9yRFUL0zg_kEtIPcl0vrq7IZehxJDZEMp9y2ELGvpR3uwNWtMsO6-_YD0i-hHE_BJ-I8-TCDXf1NaYwTtkFT74W2VjaIQHfk9v5N7LcwoDpRfXUwpjw_Hc8q24_frhZXNSrz5-Wi_mqBqlFrgUw2fOG2hap7cFqa7sZqLaxnFPRINdrCzNq1VowKWQjWtVJLa2WGqlslDirlkffPsDG7KLbQtybAM48XIQ4GIjZdSMa4IqyvrSl2kraztai50ojMM1E18iD1-uj1y6GnxOmbLYudWU88BimZHirlWqZ0Lygrx6hmzBFXyY1XGjFGJeiKdSbI9XFkFJE--eBjJrDos3fRReYPoI7l-HwyTmCG_8nuQdF1Kn1
CitedBy_id crossref_primary_10_1029_2023EA002845
crossref_primary_10_3390_jimaging6120137
crossref_primary_10_1016_j_jag_2023_103569
crossref_primary_10_1109_COMST_2023_3312221
crossref_primary_10_3390_rs14153656
crossref_primary_10_1186_s40645_024_00610_5
crossref_primary_10_3390_rs14030624
crossref_primary_10_3390_rs13020197
crossref_primary_10_3390_rs13061217
crossref_primary_10_3390_rs14133046
crossref_primary_10_3390_rs13010071
crossref_primary_10_3390_rs13081509
crossref_primary_10_1016_j_icarus_2023_115722
crossref_primary_10_1080_01431161_2023_2275320
crossref_primary_10_1016_j_rse_2024_114052
crossref_primary_10_3390_rs16244670
crossref_primary_10_1088_2752_664X_ad9f6c
crossref_primary_10_1139_dsa_2021_0045
crossref_primary_10_1016_j_ophoto_2022_100024
crossref_primary_10_1016_j_compgeo_2024_106549
crossref_primary_10_1016_j_rse_2024_114299
crossref_primary_10_3390_rs13061184
crossref_primary_10_1109_ACCESS_2021_3111706
crossref_primary_10_1109_TGRS_2022_3222223
crossref_primary_10_3390_rs13224618
crossref_primary_10_3390_rs13214294
crossref_primary_10_1016_j_scitotenv_2022_155886
crossref_primary_10_3390_rs13132450
crossref_primary_10_1016_j_geomorph_2023_108615
crossref_primary_10_3390_rs13132591
crossref_primary_10_1002_ppp_2123
crossref_primary_10_3390_jimaging6090097
crossref_primary_10_3390_rs13245052
crossref_primary_10_3390_rs14122761
crossref_primary_10_1029_2024JH000550
crossref_primary_10_3390_rs13061070
crossref_primary_10_3390_rs17061040
crossref_primary_10_1109_MGRS_2023_3312347
Cites_doi 10.1029/2018GL081584
10.1109/CVPR.2019.00657
10.1038/srep15865
10.1109/ICCV.2019.00925
10.1109/TKDE.2009.191
10.1029/2005GL024960
10.3390/rs10091487
10.1007/s10021-017-0165-5
10.1109/ICCV.2017.322
10.1038/s41467-018-07663-3
10.1080/2150704X.2015.1072288
10.1109/CVPR.2019.00511
10.3390/rs9070640
10.1038/nature14539
10.1016/j.rse.2019.111534
10.5194/tc-13-237-2019
10.1080/07038992.2017.1370367
10.3390/rs10060954
10.1109/CVPR.2018.00913
10.1016/j.rse.2018.11.034
10.1111/j.1467-8306.1972.tb00839.x
10.1111/gcb.12500
10.1109/CVPR.2018.00644
10.1109/CVPR.2017.472
10.1002/2015JF003602
10.1007/978-3-319-10602-1_48
10.1016/j.rse.2017.06.031
10.1145/3343031.3350535
10.1038/ngeo2674
10.1109/CVPR.2016.343
10.1130/SPE70-p1
10.1016/j.coldregions.2012.08.002
10.1086/622281
10.1080/2150704X.2015.1088668
ContentType Journal Article
Copyright 2020. This work is licensed under http://creativecommons.org/licenses/by/3.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: 2020. This work is licensed under http://creativecommons.org/licenses/by/3.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID AAYXX
CITATION
7QF
7QO
7QQ
7QR
7SC
7SE
7SN
7SP
7SR
7TA
7TB
7U5
8BQ
8FD
8FE
8FG
ABJCF
ABUWG
AFKRA
ARAPS
AZQEC
BENPR
BGLVJ
BHPHI
BKSAR
C1K
CCPQU
DWQXO
F28
FR3
H8D
H8G
HCIFZ
JG9
JQ2
KR7
L6V
L7M
L~C
L~D
M7S
P5Z
P62
P64
PCBAR
PHGZM
PHGZT
PIMPY
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
PTHSS
7S9
L.6
DOA
DOI 10.3390/rs12071085
DatabaseName CrossRef
Aluminium Industry Abstracts
Biotechnology Research Abstracts
Ceramic Abstracts
Chemoreception Abstracts
Computer and Information Systems Abstracts
Corrosion Abstracts
Ecology Abstracts
Electronics & Communications Abstracts
Engineered Materials Abstracts
Materials Business File
Mechanical & Transportation Engineering Abstracts
Solid State and Superconductivity Abstracts
METADEX
Technology Research Database
ProQuest SciTech Collection
ProQuest Technology Collection
Materials Science & Engineering Collection
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
Advanced Technologies & Computer Science Collection
ProQuest Central Essentials
ProQuest Central
Technology collection
ProQuest Natural Science Collection
Earth, Atmospheric & Aquatic Science Collection
Environmental Sciences and Pollution Management
ProQuest One Community College
ProQuest Central
ANTE: Abstracts in New Technology & Engineering
Engineering Research Database
Aerospace Database
Copper Technical Reference Library
SciTech Premium Collection
Materials Research Database
ProQuest Computer Science Collection
Civil Engineering Abstracts
ProQuest Engineering Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
Engineering Database
Advanced Technologies & Aerospace Database
ProQuest Advanced Technologies & Aerospace Collection
Biotechnology and BioEngineering Abstracts
Earth, Atmospheric & Aquatic Science Database
ProQuest Central Premium
ProQuest One Academic
Publicly Available Content Database
ProQuest One Academic Middle East (New)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
Engineering Collection
AGRICOLA
AGRICOLA - Academic
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
Publicly Available Content Database
Materials Research Database
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
SciTech Premium Collection
ProQuest Central China
Materials Business File
Environmental Sciences and Pollution Management
ProQuest One Applied & Life Sciences
Engineered Materials Abstracts
Natural Science Collection
Chemoreception Abstracts
ProQuest Central (New)
Engineering Collection
ANTE: Abstracts in New Technology & Engineering
Advanced Technologies & Aerospace Collection
Engineering Database
Aluminium Industry Abstracts
ProQuest One Academic Eastern Edition
Electronics & Communications Abstracts
Earth, Atmospheric & Aquatic Science Database
ProQuest Technology Collection
Ceramic Abstracts
Ecology Abstracts
Biotechnology and BioEngineering Abstracts
ProQuest One Academic UKI Edition
Solid State and Superconductivity Abstracts
Engineering Research Database
ProQuest One Academic
ProQuest One Academic (New)
Technology Collection
Technology Research Database
Computer and Information Systems Abstracts – Academic
ProQuest One Academic Middle East (New)
Mechanical & Transportation Engineering Abstracts
ProQuest Central (Alumni Edition)
ProQuest One Community College
Earth, Atmospheric & Aquatic Science Collection
ProQuest Central
Aerospace Database
Copper Technical Reference Library
ProQuest Engineering Collection
Biotechnology Research Abstracts
ProQuest Central Korea
Advanced Technologies Database with Aerospace
Civil Engineering Abstracts
ProQuest SciTech Collection
METADEX
Computer and Information Systems Abstracts Professional
Advanced Technologies & Aerospace Database
Materials Science & Engineering Collection
Corrosion Abstracts
AGRICOLA
AGRICOLA - Academic
DatabaseTitleList AGRICOLA
Publicly Available Content Database
CrossRef

Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: PIMPY
  name: Publicly Available Content Database
  url: http://search.proquest.com/publiccontent
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Geography
EISSN 2072-4292
ExternalDocumentID oai_doaj_org_article_a2501d48308f4096b3d258ea1813c745
10_3390_rs12071085
GeographicLocations United States--US
Alaska
Arctic region
GeographicLocations_xml – name: Alaska
– name: Arctic region
– name: United States--US
GroupedDBID 29P
2WC
2XV
5VS
8FE
8FG
8FH
AADQD
AAHBH
AAYXX
ABDBF
ABJCF
ACUHS
ADBBV
ADMLS
AENEX
AFFHD
AFKRA
AFZYC
ALMA_UNASSIGNED_HOLDINGS
ARAPS
BCNDV
BENPR
BGLVJ
BHPHI
BKSAR
CCPQU
CITATION
E3Z
ESX
FRP
GROUPED_DOAJ
HCIFZ
I-F
IAO
ITC
KQ8
L6V
LK5
M7R
M7S
MODMG
M~E
OK1
P62
PCBAR
PHGZM
PHGZT
PIMPY
PQGLB
PROAC
PTHSS
TR2
TUS
7QF
7QO
7QQ
7QR
7SC
7SE
7SN
7SP
7SR
7TA
7TB
7U5
8BQ
8FD
ABUWG
AZQEC
C1K
DWQXO
F28
FR3
H8D
H8G
JG9
JQ2
KR7
L7M
L~C
L~D
P64
PKEHL
PQEST
PQQKQ
PQUKI
PRINS
7S9
L.6
PUEGO
ID FETCH-LOGICAL-a483t-3a14d270f9e0fdaf8ffc6a597f22037e28bfa60f5b314347395c484f848e04753
IEDL.DBID BENPR
ISICitedReferencesCount 42
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000537709600035&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2072-4292
IngestDate Fri Oct 03 12:42:23 EDT 2025
Thu Oct 02 10:55:57 EDT 2025
Mon Oct 20 02:52:51 EDT 2025
Tue Nov 18 21:36:24 EST 2025
Sat Nov 29 07:18:41 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 7
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a483t-3a14d270f9e0fdaf8ffc6a597f22037e28bfa60f5b314347395c484f848e04753
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0001-8253-3932
0000-0002-1517-4711
OpenAccessLink https://www.proquest.com/docview/2385112437?pq-origsite=%requestingapplication%
PQID 2385112437
PQPubID 2032338
ParticipantIDs doaj_primary_oai_doaj_org_article_a2501d48308f4096b3d258ea1813c745
proquest_miscellaneous_2985591382
proquest_journals_2385112437
crossref_primary_10_3390_rs12071085
crossref_citationtrail_10_3390_rs12071085
PublicationCentury 2000
PublicationDate 20200328
PublicationDateYYYYMMDD 2020-03-28
PublicationDate_xml – month: 03
  year: 2020
  text: 20200328
  day: 28
PublicationDecade 2020
PublicationPlace Basel
PublicationPlace_xml – name: Basel
PublicationTitle Remote sensing (Basel, Switzerland)
PublicationYear 2020
Publisher MDPI AG
Publisher_xml – name: MDPI AG
References Kanevskiy (ref_8) 2013; 85
Mackay (ref_7) 1972; 62
Diao (ref_24) 2015; 6
ref_36
ref_34
ref_11
Gorelick (ref_16) 2017; 202
Lara (ref_19) 2019; 221
ref_31
ref_30
Jorgenson (ref_3) 2015; 120
Liljedahl (ref_10) 2016; 9
Cooley (ref_20) 2019; 46
ref_17
ref_39
ref_38
ref_15
ref_37
Huang (ref_32) 2020; 237
Guan (ref_25) 2015; 6
Raynolds (ref_14) 2014; 20
Chen (ref_33) 2017; 43
Frost (ref_12) 2018; 21
ref_21
Fleet (ref_28) 2014; Volume 8693
Abolt (ref_18) 2019; 13
ref_1
LeCun (ref_23) 2015; 521
ref_2
ref_29
Leffingwell (ref_4) 1915; 23
ref_27
ref_26
ref_9
Nitze (ref_22) 2018; 9
Jones (ref_13) 2015; 5
ref_5
Pan (ref_35) 2010; 22
ref_6
References_xml – volume: 46
  start-page: 2111
  year: 2019
  ident: ref_20
  article-title: Arctic-Boreal Lake Dynamics Revealed Using CubeSat Imagery
  publication-title: Geophys. Res. Lett.
  doi: 10.1029/2018GL081584
– ident: ref_37
  doi: 10.1109/CVPR.2019.00657
– volume: 5
  start-page: 15865
  year: 2015
  ident: ref_13
  article-title: Recent Arctic tundra fire initiates widespread thermokarst development
  publication-title: Sci. Rep.
  doi: 10.1038/srep15865
– ident: ref_27
  doi: 10.1109/ICCV.2019.00925
– volume: 22
  start-page: 1345
  year: 2010
  ident: ref_35
  article-title: A Survey on Transfer Learning
  publication-title: IEEE Trans. Knowl. Data Eng.
  doi: 10.1109/TKDE.2009.191
– ident: ref_9
  doi: 10.1029/2005GL024960
– ident: ref_34
– ident: ref_17
  doi: 10.3390/rs10091487
– volume: 21
  start-page: 507
  year: 2018
  ident: ref_12
  article-title: Seasonal and Long-Term Changes to Active-Layer Temperatures after Tall Shrubland Expansion and Succession in Arctic Tundra
  publication-title: Ecosystems
  doi: 10.1007/s10021-017-0165-5
– ident: ref_26
  doi: 10.1109/ICCV.2017.322
– volume: 9
  start-page: 5423
  year: 2018
  ident: ref_22
  article-title: Remote sensing quantifies widespread abundance of permafrost region disturbances across the Arctic and Subarctic
  publication-title: Nat. Commun.
  doi: 10.1038/s41467-018-07663-3
– volume: 6
  start-page: 745
  year: 2015
  ident: ref_24
  article-title: Object recognition in remote sensing images using sparse deep belief networks
  publication-title: Remote Sens. Lett.
  doi: 10.1080/2150704X.2015.1072288
– ident: ref_39
  doi: 10.1109/CVPR.2019.00511
– ident: ref_21
  doi: 10.3390/rs9070640
– volume: 521
  start-page: 436
  year: 2015
  ident: ref_23
  article-title: Deep learning
  publication-title: Nature
  doi: 10.1038/nature14539
– volume: 237
  start-page: 111534
  year: 2020
  ident: ref_32
  article-title: Using deep learning to map retrogressive thaw slumps in the Beiluhe region (Tibetan Plateau) from CubeSat images
  publication-title: Remote Sens. Environ.
  doi: 10.1016/j.rse.2019.111534
– ident: ref_1
– volume: 13
  start-page: 237
  year: 2019
  ident: ref_18
  article-title: Brief communication: Rapid machine-learning-based extraction and measurement of ice wedge polygons in high-resolution digital elevation models
  publication-title: Cryosphere
  doi: 10.5194/tc-13-237-2019
– volume: 43
  start-page: 513
  year: 2017
  ident: ref_33
  article-title: Mapping Arctic Coastal Ecosystems with High Resolution Optical Satellite Imagery Using a Hybrid Classification Approach
  publication-title: Can. J. Remote Sens.
  doi: 10.1080/07038992.2017.1370367
– ident: ref_11
  doi: 10.3390/rs10060954
– ident: ref_6
– ident: ref_36
  doi: 10.1109/CVPR.2018.00913
– volume: 221
  start-page: 462
  year: 2019
  ident: ref_19
  article-title: Automated detection of thermoerosion in permafrost ecosystems using temporally dense Landsat image stacks
  publication-title: Remote Sens. Environ.
  doi: 10.1016/j.rse.2018.11.034
– ident: ref_2
– volume: 62
  start-page: 1
  year: 1972
  ident: ref_7
  article-title: The World of Underground Ice
  publication-title: Ann. Assoc. Am. Geogr.
  doi: 10.1111/j.1467-8306.1972.tb00839.x
– volume: 20
  start-page: 1211
  year: 2014
  ident: ref_14
  article-title: Cumulative geoecological effects of 62 years of infrastructure and climate change in ice-rich permafrost landscapes, Prudhoe Bay Oilfield, Alaska
  publication-title: Glob. Chang. Biol.
  doi: 10.1111/gcb.12500
– ident: ref_38
  doi: 10.1109/CVPR.2018.00644
– ident: ref_30
  doi: 10.1109/CVPR.2017.472
– volume: 120
  start-page: 2280
  year: 2015
  ident: ref_3
  article-title: Role of ground ice dynamics and ecological feedbacks in recent ice wedge degradation and stabilization
  publication-title: J. Geophys. Res. Earth Surf.
  doi: 10.1002/2015JF003602
– volume: Volume 8693
  start-page: 740
  year: 2014
  ident: ref_28
  article-title: Microsoft COCO: Common Objects in Context
  publication-title: Computer Vision—ECCV 2014
  doi: 10.1007/978-3-319-10602-1_48
– volume: 202
  start-page: 18
  year: 2017
  ident: ref_16
  article-title: Google Earth Engine: Planetary-scale geospatial analysis for everyone
  publication-title: Remote Sens. Environ.
  doi: 10.1016/j.rse.2017.06.031
– ident: ref_31
  doi: 10.1145/3343031.3350535
– volume: 9
  start-page: 312
  year: 2016
  ident: ref_10
  article-title: Pan-Arctic ice-wedge degradation in warming permafrost and its influence on tundra hydrology
  publication-title: Nat. Geosci.
  doi: 10.1038/ngeo2674
– ident: ref_15
– ident: ref_29
  doi: 10.1109/CVPR.2016.343
– ident: ref_5
  doi: 10.1130/SPE70-p1
– volume: 85
  start-page: 56
  year: 2013
  ident: ref_8
  article-title: Ground ice in the upper permafrost of the Beaufort Sea coast of Alaska
  publication-title: Cold Reg. Sci. Technol.
  doi: 10.1016/j.coldregions.2012.08.002
– volume: 23
  start-page: 635
  year: 1915
  ident: ref_4
  article-title: Ground-Ice Wedges: The Dominant Form of Ground-Ice on the North Coast of Alaska
  publication-title: J. Geol.
  doi: 10.1086/622281
– volume: 6
  start-page: 864
  year: 2015
  ident: ref_25
  article-title: Deep learning-based tree classification using mobile LiDAR data
  publication-title: Remote Sens. Lett.
  doi: 10.1080/2150704X.2015.1088668
SSID ssj0000331904
Score 2.4369185
Snippet State-of-the-art deep learning technology has been successfully applied to relatively small selected areas of very high spatial resolution (0.15 and 0.25 m)...
SourceID doaj
proquest
crossref
SourceType Open Website
Aggregation Database
Enrichment Source
Index Database
StartPage 1085
SubjectTerms Accuracy
Aircraft
Aircraft configurations
Aircraft icing
Alaska
Annotations
Arctic
Arctic region
Artificial neural networks
Assessments
Automation
cameras
CMOS
Coastal plains
data collection
Datasets
Deep learning
Fixed wings
High resolution
ice-wedge polygons
Image acquisition
Image detection
Image processing
Image resolution
Machine learning
Mapping
Mask R-CNN
Model accuracy
Neural networks
Permafrost
Polygons
Remote sensing
Satellite imagery
Satellites
Sensors
Spatial discrimination
Spatial resolution
Spectral bands
Stability analysis
Studies
Training
Tundra
UAV
Unmanned aerial vehicles
Wedges
WorldView-2
SummonAdditionalLinks – databaseName: DOAJ Directory of Open Access Journals
  dbid: DOA
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Nb9QwELVQhQQXVL7EQkFGcOFgNWs7sXNcChU9sKqAQm-RY4-3FUtSbbKV9kfwn5lx0mUlkLhwjSeS5ZnxvGdbbxh7bV2IHnLMNETfQhvvMKVcEFhJnC19KL2JqdmEmc_t-Xl5utPqi96EDfLAw8IdOqzR06CtymxELlLUKsjcgsPKpLzRSb0UUc8OmUp7sMLQyvSgR6qQ1x-uuqmkckpNk3cqUBLq_2MfTsXleJ_dG1Ehnw2zuc9uQfOA3RkblF9sHrKfqaZEWA2y2hveRo7Qjb8DuOKjRuqCf3Tdd_5JHM3nnHqcLTkiUj5b9y3CUgg4TGIMC_r3xIP4Rkdp_LRdbhYYevyy4fToQ9CB_hCO_LNLep09cNcEfjb7yk9-4P7TPWJnx--_HH0QYycF4XDleqHcVAdpslhCFoOLNkZfOOQSUcpMGZC2jq7IYl4rxE-aLu-8tjpabSHTyGges72mbeAJ49qrvIS6ts4qXShf5mDyHIrMOiO9ggl7c7O6lR9lxqnbxbJCukGeqH57YsJebW2vBnGNv1q9JSdtLUgQO33AMKnGMKn-FSYTdnDj4mrM0q5CuEJ4UyszYS-3w5hfdGniGmjXaFNaJF2k1Pj0f8zjGbsribFnSkh7wPb61Rqes9v-ur_sVi9SEP8CfHT0NQ
  priority: 102
  providerName: Directory of Open Access Journals
Title Transferability of the Deep Learning Mask R-CNN Model for Automated Mapping of Ice-Wedge Polygons in High-Resolution Satellite and UAV Images
URI https://www.proquest.com/docview/2385112437
https://www.proquest.com/docview/2985591382
https://doaj.org/article/a2501d48308f4096b3d258ea1813c745
Volume 12
WOSCitedRecordID wos000537709600035&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2072-4292
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000331904
  issn: 2072-4292
  databaseCode: DOA
  dateStart: 20090101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2072-4292
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000331904
  issn: 2072-4292
  databaseCode: M~E
  dateStart: 20090101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: Advanced Technologies & Aerospace Database
  customDbUrl:
  eissn: 2072-4292
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000331904
  issn: 2072-4292
  databaseCode: P5Z
  dateStart: 20090301
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/hightechjournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Earth, Atmospheric & Aquatic Science Database
  customDbUrl:
  eissn: 2072-4292
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000331904
  issn: 2072-4292
  databaseCode: PCBAR
  dateStart: 20090301
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/eaasdb
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Engineering Database
  customDbUrl:
  eissn: 2072-4292
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000331904
  issn: 2072-4292
  databaseCode: M7S
  dateStart: 20090301
  isFulltext: true
  titleUrlDefault: http://search.proquest.com
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 2072-4292
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000331904
  issn: 2072-4292
  databaseCode: BENPR
  dateStart: 20090301
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Publicly Available Content Database
  customDbUrl:
  eissn: 2072-4292
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000331904
  issn: 2072-4292
  databaseCode: PIMPY
  dateStart: 20090301
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/publiccontent
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lj9MwELagiwQX3ojCUhnBhYO1aewkzgl1l67oYaNol4WFS-T4UVaUpDQpUi_8A_4zM4nbRQJx4eJDPLESzYznm7H1DSEvpTJO2wg8DdA3E4lW4FLKMIgkSqbapDpxXbOJJMvkxUWa-4Jb469VbvfEbqM2tcYa-QGEFsQGgievl98Ydo3C01XfQuM62UOmMjEge4fTLD_dVVkCDiYWiJ6XlEN-f7BqxiGGVWye_Fsk6gj7_9iPuyBzfOd_P-8uue3hJZ309nCPXLPVfXLTdzr_vHlAfnbBydlVz8-9obWjgAHpG2uX1JOtzumJar7QU3aUZRSbpS0oQFs6Wbc14FtrYBpZHeb47kxb9gFrcjSvF5s52DC9rCjeHmF4MtDbNT1THfFna6mqDD2fvKezr7CRNQ_J-fH03dFb5lsyMCUkbxlXY2HCJHCpDZxRTjqnYwVJiQvDgCc2lKVTceCikgMQE3gKqIUUTgppAwGp0SMyqOrKPiZUaB6ltiylklzEXKeRTaLIxoFUSai5HZJXW_UU2vOVY9uMRQF5C6qyuFLlkLzYyS57lo6_Sh2ilncSyKzdPahX88I7aqEAE44N_GwgHeS-cclNGEmrAAlxnQhYZH9rAIV396a40v6QPN9Ng6Pi6YuqbL0GmVRC9oaUj0_-vcRTcivEpD7gLJT7ZNCu1vYZuaG_t5fNauQtfNQVD0Z4VfUMxx9TGPPoE8zns5P84y94dgrg
linkProvider ProQuest
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3LbtQwFLWqKVLZ8EYMFDACFiyiemIncRYIDS1Vo3aiEbTQroLj2EPFkAxJBjQfwa_wjdybxxQJxK4LtrFjKcm59x4_cg4hz6TKrDYeRBqwb0cEWkFIqcyBSqJkqLNQB7YxmwjiWJ6ehtMN8rP_FwaPVfY5sUnUWaFxjXwHSgtyA8GDV4uvDrpG4e5qb6HRwuLQrL7DlK16Ge3B933uuvtvjncPnM5VwFFC8trhaiQyN2A2NMxmykprta-AV1vXZTwwrkyt8pn1Ug5cQuBGlhZSWCmkYSJAlwhI-ZsCwC4HZHMaTaZn61UdxgHSTLQ6qJyHbKesRi6WcTRr_q3yNQYBf-T_pqjtX__fXscNcq2jz3Tc4v0m2TD5LbLVObl_Wt0mP5ria03Z6o-vaGEpcFy6Z8yCdmKyMzpR1Wf61tmNY4pmcHMK1J2Ol3UB_N1k0IyqFTO8N9LG-YBrjnRazFcziFF6nlM8HePgzkcbt_SdaoRNa0NVntGT8XsafYFEXd0hJ5fyNu6SQV7k5h6hQnMvNGkqleTC5zr0TOB5xmdSBa7mZkhe9HBIdKfHjrYg8wTmZQid5AI6Q_J03XfRqpD8tddrRNW6ByqHNxeKcpZ0iShRwHlHGTwskxbm9n7KMwCyUcD0uA4EDLLdAy7p0lmVXKBtSJ6smyER4e6Syk2xhD6hhNkpSlre__cQj8nWwfHkKDmK4sMH5KqLCxiMO67cJoO6XJqH5Ir-Vp9X5aMuuij5eNkI_gUdo2D1
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3LjtMwFLVGHQRseCMKAxgBCxZRXduJnQVCnZaKaqCqBgZmFxzH7oymJKVpQf0Ifoiv494k7SCB2M2CbexYSnLuvcePnEPIM20yb10IkQbsO5DKGggpkwVQSYyObRZb5SuzCTUe6-PjeLJDfm7-hcFjlZucWCXqrLC4Rt6B0oLcQArV8c2xiMlg-Gr-NUAHKdxp3dhp1BA5cOvvMH0rX44G8K2fcz58_aH_JmgcBgIjtVgGwnRlxhXzsWM-M157byMDHNtzzoRyXKfeRMyHqQBeIXFTy0otvZbaManQMQLS_66OFOMtsjvp7_cOtys8TAC8maw1UYWIWWdRdjmWdDRu_q0KVmYBf9SCqsANr__Pr-YGudbQatqr4-Am2XH5LXKlcXg_Wd8mP6qi7N2i1iVf08JT4L504NycNiKzU_rOlGf0MOiPxxRN4mYUKD3trZYF8HqXQTOqWUzx3pF1wSdci6STYraeQuzS05ziqZkAd0TqeKbvTSV4unTU5Bk96n2koy-QwMs75OhC3sZd0sqL3N0jVFoRxi5NtdFCRsLGoVNh6CKmjeJWuDZ5sYFGYhuddrQLmSUwX0MYJecwapOn277zWp3kr732EWHbHqgoXl0oFtOkSVCJAS7czeBhmfYw549SkfFQOwMMUFglYZC9DfiSJs2VyTny2uTJthkSFO46mdwVK-gTa5i1otTl_X8P8ZhcBtgmb0fjgwfkKsd1DSYCrvdIa7lYuYfkkv22PC0Xj5pAo-TzRQP4FyreaWU
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=Transferability+of+the+Deep+Learning+Mask+R-CNN+Model+for+Automated+Mapping+of+Ice-Wedge+Polygons+in+High-Resolution+Satellite+and+UAV+Images&rft.jtitle=Remote+sensing+%28Basel%2C+Switzerland%29&rft.au=Zhang%2C+Weixing&rft.au=Liljedahl%2C+Anna+K&rft.au=Kanevskiy%2C+Mikhail&rft.au=Epstein%2C+Howard+E&rft.date=2020-03-28&rft.pub=MDPI+AG&rft.eissn=2072-4292&rft.volume=12&rft.issue=7&rft.spage=1085&rft_id=info:doi/10.3390%2Frs12071085&rft.externalDBID=HAS_PDF_LINK
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2072-4292&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2072-4292&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2072-4292&client=summon