Precision Meets Speed: An Attention Encoder-Decoder Network for Deforestation Segmentation

Deforestation remains a critical global environmental concern, requiring effective monitoring approaches. This letter presents a novel attention-powered encoder-decoder neural network designed to address the key challenges in deforestation mapping, including scale heterogeneity, temporal dynamics, a...

Full description

Saved in:
Bibliographic Details
Published in:IEEE geoscience and remote sensing letters Vol. 22; pp. 1 - 5
Main Authors: Benvenuto, Giovana A., Negri, Rogerio G., Colnago, Marilaine, Frery, Alejandro C., Casaca, Wallace
Format: Journal Article
Language:English
Published: Piscataway IEEE 2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Accuracy
Attention mechanisms
Coders
Computational efficiency
Computer applications
Computer architecture
Computing costs
Deep learning
Deforestation
Environmental perception
Feature extraction
Heterogeneity
Monitoring
Neural networks
Remote sensing
remote sensing (RS)
Training
ISSN:1545-598X, 1558-0571
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Deforestation remains a critical global environmental concern, requiring effective monitoring approaches. This letter presents a novel attention-powered encoder-decoder neural network designed to address the key challenges in deforestation mapping, including scale heterogeneity, temporal dynamics, and computational efficiency. The proposed framework integrates a modified YOLOv8 backbone, spatial attention (SA) mechanisms, and a conjugated Dice-Focal loss function to enhance sensitivity to small- and large-scale deforestation patterns in temporal remote sensing (RS) data. An extensive battery of tests was conducted using two datasets from the Amazon region, exploring both single-image and image-pair inputs under varying contextual and class balance conditions. The results attest to substantial improvements in accuracy and computational efficiency compared to 13 deep learning (DL) methods, establishing the proposed model as effective in deforestation monitoring scenarios, where accuracy, scalability, and computational cost are simultaneously critical.
AbstractList Deforestation remains a critical global environmental concern, requiring effective monitoring approaches. This letter presents a novel attention-powered encoder-decoder neural network designed to address the key challenges in deforestation mapping, including scale heterogeneity, temporal dynamics, and computational efficiency. The proposed framework integrates a modified YOLOv8 backbone, spatial attention (SA) mechanisms, and a conjugated Dice-Focal loss function to enhance sensitivity to small- and large-scale deforestation patterns in temporal remote sensing (RS) data. An extensive battery of tests was conducted using two datasets from the Amazon region, exploring both single-image and image-pair inputs under varying contextual and class balance conditions. The results attest to substantial improvements in accuracy and computational efficiency compared to 13 deep learning (DL) methods, establishing the proposed model as effective in deforestation monitoring scenarios, where accuracy, scalability, and computational cost are simultaneously critical.
Author Casaca, Wallace
Benvenuto, Giovana A.
Colnago, Marilaine
Frery, Alejandro C.
Negri, Rogerio G.
Author_xml – sequence: 1
  givenname: Giovana A.
  orcidid: 0000-0002-0531-1284
  surname: Benvenuto
  fullname: Benvenuto, Giovana A.
  organization: São Paulo State University (UNESP), São José do Rio Preto, Brazil
– sequence: 2
  givenname: Rogerio G.
  orcidid: 0000-0002-4808-2362
  surname: Negri
  fullname: Negri, Rogerio G.
  organization: ICT, UNESP, São José dos Campos, Brazil
– sequence: 3
  givenname: Marilaine
  orcidid: 0000-0003-1599-491X
  surname: Colnago
  fullname: Colnago, Marilaine
  organization: São Paulo State University (UNESP), São José do Rio Preto, Brazil
– sequence: 4
  givenname: Alejandro C.
  orcidid: 0000-0002-8002-5341
  surname: Frery
  fullname: Frery, Alejandro C.
  email: alejandro.frery@vuw.ac.nz
  organization: School of Mathematics and Statistics, Victoria University of Wellington, Wellington, New Zealand
– sequence: 5
  givenname: Wallace
  orcidid: 0000-0002-1073-9939
  surname: Casaca
  fullname: Casaca, Wallace
  organization: São Paulo State University (UNESP), São José do Rio Preto, Brazil
BookMark eNpFkF1LwzAYhYNMcJv-AMGLgtet-WxT78Y2pzA_cAriTciaN9Lpmpl0iP_edBt4k5OQ57zv4QxQr3ENIHROcEYILq_ms-dFRjEVGRMlFlIcoT4RQqZYFKTX3blIRSnfTtAghBXGlEtZ9NH7k4eqDrVrknuANiSLDYC5TkZNMmpbaNruZ9pUzoBPJ7DT5AHaH-c_E-t8MoF4Qmj1jlzAxzqado9TdGz1V4Czgw7R6830ZXybzh9nd-PRPK1ihjbljC05XZaYy6XWQloicxZDW0s11Vxjiq0pLcHGCKmNqApTFREklhcGi4oN0eV-7sa7722MolZu65u4UjHK84LlMpeRInuq8i4ED1ZtfL3W_lcRrLoKVVeh6ipUhwqj52LvqQHgnydY8hIX7A9t_m-g
CODEN IGRSBY
Cites_doi 10.1016/j.ecoinf.2021.101279
10.3390/rs12203372
10.1109/3DV.2016.79
10.1007/978-3-031-72751-1_1
10.1016/j.jag.2022.102685
10.3390/rs13245084
10.3390/ai6020032
10.1109/IGARSS.2018.8518015
10.3390/rs12060901
10.1109/ICIP.2018.8451652
10.1073/pnas.1605516113
10.1016/j.jag.2023.103332
10.3390/rs12060910
10.3390/rs14194694
10.1109/LSENS.2023.3340562
10.1109/TPAMI.2018.2858826
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
DBID 97E
RIA
RIE
AAYXX
CITATION
7SC
7SP
7TG
7UA
8FD
C1K
F1W
FR3
H8D
H96
JQ2
KL.
KR7
L.G
L7M
L~C
L~D
DOI 10.1109/LGRS.2025.3590585
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Meteorological & Geoastrophysical Abstracts
Water Resources Abstracts
Technology Research Database
Environmental Sciences and Pollution Management
ASFA: Aquatic Sciences and Fisheries Abstracts
Engineering Research Database
Aerospace Database
Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources
ProQuest Computer Science Collection
Meteorological & Geoastrophysical Abstracts - Academic
Civil Engineering Abstracts
Aquatic Science & Fisheries Abstracts (ASFA) Professional
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Civil Engineering Abstracts
Aquatic Science & Fisheries Abstracts (ASFA) Professional
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Water Resources Abstracts
Environmental Sciences and Pollution Management
Computer and Information Systems Abstracts Professional
Aerospace Database
Meteorological & Geoastrophysical Abstracts
Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources
ASFA: Aquatic Sciences and Fisheries Abstracts
Engineering Research Database
Advanced Technologies Database with Aerospace
Meteorological & Geoastrophysical Abstracts - Academic
DatabaseTitleList
Civil Engineering Abstracts
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Geography
Geology
EISSN 1558-0571
EndPage 5
ExternalDocumentID 10_1109_LGRS_2025_3590585
11084907
Genre orig-research
GrantInformation_xml – fundername: IBILCE, São Paulo Research Foundation (FAPESP)
  grantid: 2023/14427-8; 2024/04718-8; 2024/01610-1
  funderid: 10.13039/501100001321
– fundername: National Council for Scientific and Technological Development (CNPq)
  grantid: 316228/2021-4; 305220/2022-5
– fundername: Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
  grantid: 001
  funderid: 10.13039/501100002322
– fundername: Research Trust VUW
  grantid: 410695
GroupedDBID 0R~
29I
4.4
5GY
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACIWK
AENEX
AETIX
AFRAH
AGQYO
AGSQL
AHBIQ
AIBXA
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
EBS
EJD
HZ~
H~9
IFIPE
IPLJI
JAVBF
LAI
M43
O9-
OCL
P2P
RIA
RIE
RNS
~02
AAYXX
CITATION
7SC
7SP
7TG
7UA
8FD
C1K
F1W
FR3
H8D
H96
JQ2
KL.
KR7
L.G
L7M
L~C
L~D
ID FETCH-LOGICAL-c248t-433b42b9048baa58f1863571ff2a2a4a020fd9f10dd58ad5c7dc7aa51f47d05c3
IEDL.DBID RIE
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001544230300005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1545-598X
IngestDate Sat Nov 01 15:02:45 EDT 2025
Sat Nov 29 07:44:51 EST 2025
Wed Aug 27 01:44:42 EDT 2025
IsPeerReviewed true
IsScholarly true
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c248t-433b42b9048baa58f1863571ff2a2a4a020fd9f10dd58ad5c7dc7aa51f47d05c3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-0531-1284
0000-0002-4808-2362
0000-0002-8002-5341
0000-0002-1073-9939
0000-0003-1599-491X
PQID 3246736868
PQPubID 75725
PageCount 5
ParticipantIDs crossref_primary_10_1109_LGRS_2025_3590585
proquest_journals_3246736868
ieee_primary_11084907
PublicationCentury 2000
PublicationDate 20250000
2025-00-00
20250101
PublicationDateYYYYMMDD 2025-01-01
PublicationDate_xml – year: 2025
  text: 20250000
PublicationDecade 2020
PublicationPlace Piscataway
PublicationPlace_xml – name: Piscataway
PublicationTitle IEEE geoscience and remote sensing letters
PublicationTitleAbbrev LGRS
PublicationYear 2025
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref13
ref12
ref14
ref20
Khanam (ref19) 2024
ref11
ref10
ref2
ref1
ref17
ref16
ref18
ref8
ref7
ref9
ref4
ref3
ref6
ref5
Jocher (ref15) 2023
References_xml – ident: ref4
  doi: 10.1016/j.ecoinf.2021.101279
– ident: ref5
  doi: 10.3390/rs12203372
– ident: ref16
  doi: 10.1109/3DV.2016.79
– ident: ref18
  doi: 10.1007/978-3-031-72751-1_1
– year: 2024
  ident: ref19
  article-title: YOLOv11: An overview of the key architectural enhancements
  publication-title: arXiv:2410.17725
– ident: ref11
  doi: 10.1016/j.jag.2022.102685
– volume-title: Prodes and Deter: Get to Know These Strategic Systems in the Fight Against Deforestation in the Amazon
  ident: ref13
– ident: ref3
  doi: 10.3390/rs13245084
– volume-title: Ultralytics YOLOv8
  year: 2023
  ident: ref15
– ident: ref20
  doi: 10.3390/ai6020032
– ident: ref14
  doi: 10.1109/IGARSS.2018.8518015
– ident: ref2
  doi: 10.3390/rs12060901
– ident: ref6
  doi: 10.1109/ICIP.2018.8451652
– volume-title: Land Cover and Land Use Monitoring
  ident: ref12
– ident: ref1
  doi: 10.1073/pnas.1605516113
– ident: ref10
  doi: 10.1016/j.jag.2023.103332
– ident: ref7
  doi: 10.3390/rs12060910
– ident: ref8
  doi: 10.3390/rs14194694
– ident: ref9
  doi: 10.1109/LSENS.2023.3340562
– ident: ref17
  doi: 10.1109/TPAMI.2018.2858826
SSID ssj0024887
Score 2.409607
Snippet Deforestation remains a critical global environmental concern, requiring effective monitoring approaches. This letter presents a novel attention-powered...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Index Database
Publisher
StartPage 1
SubjectTerms Accuracy
Attention mechanisms
Coders
Computational efficiency
Computer applications
Computer architecture
Computing costs
Deep learning
Deforestation
Environmental perception
Feature extraction
Heterogeneity
Monitoring
Neural networks
Remote sensing
remote sensing (RS)
Training
Title Precision Meets Speed: An Attention Encoder-Decoder Network for Deforestation Segmentation
URI https://ieeexplore.ieee.org/document/11084907
https://www.proquest.com/docview/3246736868
Volume 22
WOSCitedRecordID wos001544230300005&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: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1558-0571
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0024887
  issn: 1545-598X
  databaseCode: RIE
  dateStart: 20040101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT4MwFG500ejFH3PG6TQ9eDJhg0Jp621xPzzMZXFqFi-E0qIeZAswk_33tqXLTIwHL8ChEPIe5X3te9_7ALjmItRt1D1HBr7vBBz5DqdEOoRKFS5jQogpHn8ZkfGYzmZsYsnqhgsjpTTFZ7KtL00uX8yTpd4q6-iS9YBp7vg2IWFF1to01qNGDU9DAgczOrMpTM9lndHwcaqWggi3fcxcrHWTfwQho6ry61ds4svg8J9vdgQOLJCE3crzx2BLZnWwZzXN31d1sDs0or2rE_A6ya2SDnyQsizgdKFi1i3sZrBbllW9I-xnmt2eOz1pznBc1YdDBWphT6qjLKqsPZzKt0_LWMoa4HnQf7q7d6ymgpMoC5WaIMUDxJmauDyOMU09qjvSeWmKYhQHsUKPqWCp5wqBaSxwQkRC1EAvDYhwceKfglo2z-QZgF6IERGcIBzTIFWwyBeM8NAXuosYQbQJbtZGjhZV64zILDlcFmmPRNojkfVIEzS0VTcDrUGboLX2S2RnVxEpEKjL0WhIz_-47QLs66dXeyUtUCvzpbwEO8lX-VHkV-bD-QaPqr9T
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3JTsMwEB0hFsGFpRRRVh84IaXN5trmVkEXRFtVFFDFJUpiBzgQUBuQ-Hs8jqsiIQ5ckhwcJZqJM8-eefMAzhLZxDbqnqPCIHDCxA-chDPlMK50uIwZY6Z4_KHPhkM-mYiRJasbLoxSyhSfqTpemly-fEs_cKusgSXroUDu-ApKZ1m61qK1Hjd6eAgKHCr4xCYxPVc0-t3bsV4M-rQeUOFSVE7-EYaMrsqvn7GJMJ2tf77bNmxaKElape93YEnlFVi3qubPXxVY6xrZ3q9deBxNrZYOGShVzMj4XUetC9LKSasoyopH0s6R3z51rpQ5k2FZIU40rCVXSh_VrMzbk7F6erWcpbwK95323WXPsaoKTqotVCBFKgn9ROipm8Qx5ZnHsSedl2V-7MdhrPFjJkXmuVJSHkuaMpkyPdDLQiZdmgZ7sJy_5WofiNekPpMJ82nMw0wDo0AKljQDiX3EmM9rcD43cvReNs-IzKLDFRF6JEKPRNYjNaiiVRcDrUFrcDT3S2Tn1yzSMBAL0niTH_xx2yms9-4G_ah_Pbw5hA18UrlzcgTLxfRDHcNq-lm8zKYn5iP6BrTCwpw
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=Precision+Meets+Speed%3A+An+Attention+Encoder%E2%80%93Decoder+Network+for+Deforestation+Segmentation&rft.jtitle=IEEE+geoscience+and+remote+sensing+letters&rft.au=Benvenuto%2C+Giovana+A.&rft.au=Negri%2C+Rog%C3%A9rio+G.&rft.au=Colnago%2C+Marilaine&rft.au=Frery%2C+Alejandro+C.&rft.date=2025&rft.issn=1545-598X&rft.eissn=1558-0571&rft.volume=22&rft.spage=1&rft.epage=5&rft_id=info:doi/10.1109%2FLGRS.2025.3590585&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_LGRS_2025_3590585
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1545-598X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1545-598X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1545-598X&client=summon