No Cover Image

Journal article 270 views 108 downloads

Temporal Optimisation of Satellite Image‐Based Crop Mapping: A Comparison of Deep Time Series and Semi‐Supervised Time Warping Strategies

Rosie Finnegan, Joseph Metcalfe, Sara Sharifzadeh Orcid Logo, Fabio Caraffini Orcid Logo, Xianghua Xie Orcid Logo, Alberto Hornero, Nicholas W. Synes

IET Computer Vision, Volume: 19, Issue: 1, Start page: e70014

Swansea University Authors: Rosie Finnegan, Joseph Metcalfe, Sara Sharifzadeh Orcid Logo, Fabio Caraffini Orcid Logo, Xianghua Xie Orcid Logo

  • 69047.VOR.pdf

    PDF | Version of Record

    © 2025 The Author(s). IET Computer Vision published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology. This is an open access article under the terms of the Creative Commons Attribution License (CC BY).

    Download (5.04MB)

Check full text

DOI (Published version): 10.1049/cvi2.70014

Abstract

This study presents a novel approach to crop mapping using remotely sensed satellite images. It addresses the significant classification modelling challenges, including (1) the requirements for extensive labelled data and (2) the complex optimisation problem for selection of appropriate temporal win...

Full description

Published in: IET Computer Vision
ISSN: 1751-9632 1751-9640
Published: Wiley 2025
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa69047
first_indexed 2025-03-06T16:00:31Z
last_indexed 2025-04-03T06:16:52Z
id cronfa69047
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2025-04-02T15:28:02.2836945</datestamp><bib-version>v2</bib-version><id>69047</id><entry>2025-03-06</entry><title>Temporal Optimisation of Satellite Image&#x2010;Based Crop Mapping: A Comparison of Deep Time Series and Semi&#x2010;Supervised Time Warping Strategies</title><swanseaauthors><author><sid>1f9ac10d65c83136f89fff2b95c58af2</sid><firstname>Rosie</firstname><surname>Finnegan</surname><name>Rosie Finnegan</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>eb9b5f2baa2b06d0430d94a71f772982</sid><firstname>Joseph</firstname><surname>Metcalfe</surname><name>Joseph Metcalfe</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>a4e15f304398ecee3f28c7faec69c1b0</sid><ORCID>0000-0003-4621-2917</ORCID><firstname>Sara</firstname><surname>Sharifzadeh</surname><name>Sara Sharifzadeh</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>d0b8d4e63d512d4d67a02a23dd20dfdb</sid><ORCID>0000-0001-9199-7368</ORCID><firstname>Fabio</firstname><surname>Caraffini</surname><name>Fabio Caraffini</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>b334d40963c7a2f435f06d2c26c74e11</sid><ORCID>0000-0002-2701-8660</ORCID><firstname>Xianghua</firstname><surname>Xie</surname><name>Xianghua Xie</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2025-03-06</date><deptcode>BGPS</deptcode><abstract>This study presents a novel approach to crop mapping using remotely sensed satellite images. It addresses the significant classification modelling challenges, including (1) the requirements for extensive labelled data and (2) the complex optimisation problem for selection of appropriate temporal windows in the absence of prior knowledge of cultivation calendars. We compare the lightweight Dynamic Time Warping (DTW) classification method with the heavily supervised Convolutional Neural Network - Long Short-Term Memory (CNN-LSTM) using high-resolution multispectral optical satellite imagery (3 m/pixel). Our approach integrates effective practical preprocessing steps, including data augmentation and a data-driven optimisation strategy for the temporal window, even in the presence of numerous crop classes. Our findings demonstrate that DTW, despite its lower data demands, can match the performance of CNN-LSTM through our effective preprocessing steps while significantly improving runtime. These results demonstrate that both CNN-LSTM and DTW can achieve deployment-level accuracy and underscore the potential of DTW as a viable alternative to more resource-intensive models. The results also prove the effectiveness of temporal windowing for improving runtime and accuracy of a crop classification study, even with no prior knowledge of planting timeframes.</abstract><type>Journal Article</type><journal>IET Computer Vision</journal><volume>19</volume><journalNumber>1</journalNumber><paginationStart>e70014</paginationStart><paginationEnd/><publisher>Wiley</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>1751-9632</issnPrint><issnElectronic>1751-9640</issnElectronic><keywords>computer vision, convolutional neural nets, learning (artificial intelligence), remote sensing, time series</keywords><publishedDay>31</publishedDay><publishedMonth>12</publishedMonth><publishedYear>2025</publishedYear><publishedDate>2025-12-31</publishedDate><doi>10.1049/cvi2.70014</doi><url/><notes/><college>COLLEGE NANME</college><department>Biosciences Geography and Physics School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>BGPS</DepartmentCode><institution>Swansea University</institution><apcterm>SU Library paid the OA fee (TA Institutional Deal)</apcterm><funders>Funding for this paper was kindly provided by Swansea University EPSRC DTP funding Project Reference EP/W524694/1 and Swansea University Research Excellence funding Scheme of the School of Mathematics and Computer Science.</funders><projectreference/><lastEdited>2025-04-02T15:28:02.2836945</lastEdited><Created>2025-03-06T11:53:27.2048897</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Rosie</firstname><surname>Finnegan</surname><order>1</order></author><author><firstname>Joseph</firstname><surname>Metcalfe</surname><order>2</order></author><author><firstname>Sara</firstname><surname>Sharifzadeh</surname><orcid>0000-0003-4621-2917</orcid><order>3</order></author><author><firstname>Fabio</firstname><surname>Caraffini</surname><orcid>0000-0001-9199-7368</orcid><order>4</order></author><author><firstname>Xianghua</firstname><surname>Xie</surname><orcid>0000-0002-2701-8660</orcid><order>5</order></author><author><firstname>Alberto</firstname><surname>Hornero</surname><order>6</order></author><author><firstname>Nicholas W.</firstname><surname>Synes</surname><order>7</order></author></authors><documents><document><filename>69047__33932__b13aabcb3d504e7e9e223df1e9cdd51c.pdf</filename><originalFilename>69047.VOR.pdf</originalFilename><uploaded>2025-04-02T15:25:16.9904514</uploaded><type>Output</type><contentLength>5285787</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>&#xA9; 2025 The Author(s). IET Computer Vision published by John Wiley &amp; Sons Ltd on behalf of The Institution of Engineering and Technology. This is an open access article under the terms of the Creative Commons Attribution License (CC BY).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2025-04-02T15:28:02.2836945 v2 69047 2025-03-06 Temporal Optimisation of Satellite Image‐Based Crop Mapping: A Comparison of Deep Time Series and Semi‐Supervised Time Warping Strategies 1f9ac10d65c83136f89fff2b95c58af2 Rosie Finnegan Rosie Finnegan true false eb9b5f2baa2b06d0430d94a71f772982 Joseph Metcalfe Joseph Metcalfe true false a4e15f304398ecee3f28c7faec69c1b0 0000-0003-4621-2917 Sara Sharifzadeh Sara Sharifzadeh true false d0b8d4e63d512d4d67a02a23dd20dfdb 0000-0001-9199-7368 Fabio Caraffini Fabio Caraffini true false b334d40963c7a2f435f06d2c26c74e11 0000-0002-2701-8660 Xianghua Xie Xianghua Xie true false 2025-03-06 BGPS This study presents a novel approach to crop mapping using remotely sensed satellite images. It addresses the significant classification modelling challenges, including (1) the requirements for extensive labelled data and (2) the complex optimisation problem for selection of appropriate temporal windows in the absence of prior knowledge of cultivation calendars. We compare the lightweight Dynamic Time Warping (DTW) classification method with the heavily supervised Convolutional Neural Network - Long Short-Term Memory (CNN-LSTM) using high-resolution multispectral optical satellite imagery (3 m/pixel). Our approach integrates effective practical preprocessing steps, including data augmentation and a data-driven optimisation strategy for the temporal window, even in the presence of numerous crop classes. Our findings demonstrate that DTW, despite its lower data demands, can match the performance of CNN-LSTM through our effective preprocessing steps while significantly improving runtime. These results demonstrate that both CNN-LSTM and DTW can achieve deployment-level accuracy and underscore the potential of DTW as a viable alternative to more resource-intensive models. The results also prove the effectiveness of temporal windowing for improving runtime and accuracy of a crop classification study, even with no prior knowledge of planting timeframes. Journal Article IET Computer Vision 19 1 e70014 Wiley 1751-9632 1751-9640 computer vision, convolutional neural nets, learning (artificial intelligence), remote sensing, time series 31 12 2025 2025-12-31 10.1049/cvi2.70014 COLLEGE NANME Biosciences Geography and Physics School COLLEGE CODE BGPS Swansea University SU Library paid the OA fee (TA Institutional Deal) Funding for this paper was kindly provided by Swansea University EPSRC DTP funding Project Reference EP/W524694/1 and Swansea University Research Excellence funding Scheme of the School of Mathematics and Computer Science. 2025-04-02T15:28:02.2836945 2025-03-06T11:53:27.2048897 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Rosie Finnegan 1 Joseph Metcalfe 2 Sara Sharifzadeh 0000-0003-4621-2917 3 Fabio Caraffini 0000-0001-9199-7368 4 Xianghua Xie 0000-0002-2701-8660 5 Alberto Hornero 6 Nicholas W. Synes 7 69047__33932__b13aabcb3d504e7e9e223df1e9cdd51c.pdf 69047.VOR.pdf 2025-04-02T15:25:16.9904514 Output 5285787 application/pdf Version of Record true © 2025 The Author(s). IET Computer Vision published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology. This is an open access article under the terms of the Creative Commons Attribution License (CC BY). true eng http://creativecommons.org/licenses/by/4.0/
title Temporal Optimisation of Satellite Image‐Based Crop Mapping: A Comparison of Deep Time Series and Semi‐Supervised Time Warping Strategies
spellingShingle Temporal Optimisation of Satellite Image‐Based Crop Mapping: A Comparison of Deep Time Series and Semi‐Supervised Time Warping Strategies
Rosie Finnegan
Joseph Metcalfe
Sara Sharifzadeh
Fabio Caraffini
Xianghua Xie
title_short Temporal Optimisation of Satellite Image‐Based Crop Mapping: A Comparison of Deep Time Series and Semi‐Supervised Time Warping Strategies
title_full Temporal Optimisation of Satellite Image‐Based Crop Mapping: A Comparison of Deep Time Series and Semi‐Supervised Time Warping Strategies
title_fullStr Temporal Optimisation of Satellite Image‐Based Crop Mapping: A Comparison of Deep Time Series and Semi‐Supervised Time Warping Strategies
title_full_unstemmed Temporal Optimisation of Satellite Image‐Based Crop Mapping: A Comparison of Deep Time Series and Semi‐Supervised Time Warping Strategies
title_sort Temporal Optimisation of Satellite Image‐Based Crop Mapping: A Comparison of Deep Time Series and Semi‐Supervised Time Warping Strategies
author_id_str_mv 1f9ac10d65c83136f89fff2b95c58af2
eb9b5f2baa2b06d0430d94a71f772982
a4e15f304398ecee3f28c7faec69c1b0
d0b8d4e63d512d4d67a02a23dd20dfdb
b334d40963c7a2f435f06d2c26c74e11
author_id_fullname_str_mv 1f9ac10d65c83136f89fff2b95c58af2_***_Rosie Finnegan
eb9b5f2baa2b06d0430d94a71f772982_***_Joseph Metcalfe
a4e15f304398ecee3f28c7faec69c1b0_***_Sara Sharifzadeh
d0b8d4e63d512d4d67a02a23dd20dfdb_***_Fabio Caraffini
b334d40963c7a2f435f06d2c26c74e11_***_Xianghua Xie
author Rosie Finnegan
Joseph Metcalfe
Sara Sharifzadeh
Fabio Caraffini
Xianghua Xie
author2 Rosie Finnegan
Joseph Metcalfe
Sara Sharifzadeh
Fabio Caraffini
Xianghua Xie
Alberto Hornero
Nicholas W. Synes
format Journal article
container_title IET Computer Vision
container_volume 19
container_issue 1
container_start_page e70014
publishDate 2025
institution Swansea University
issn 1751-9632
1751-9640
doi_str_mv 10.1049/cvi2.70014
publisher Wiley
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str 1
active_str 0
description This study presents a novel approach to crop mapping using remotely sensed satellite images. It addresses the significant classification modelling challenges, including (1) the requirements for extensive labelled data and (2) the complex optimisation problem for selection of appropriate temporal windows in the absence of prior knowledge of cultivation calendars. We compare the lightweight Dynamic Time Warping (DTW) classification method with the heavily supervised Convolutional Neural Network - Long Short-Term Memory (CNN-LSTM) using high-resolution multispectral optical satellite imagery (3 m/pixel). Our approach integrates effective practical preprocessing steps, including data augmentation and a data-driven optimisation strategy for the temporal window, even in the presence of numerous crop classes. Our findings demonstrate that DTW, despite its lower data demands, can match the performance of CNN-LSTM through our effective preprocessing steps while significantly improving runtime. These results demonstrate that both CNN-LSTM and DTW can achieve deployment-level accuracy and underscore the potential of DTW as a viable alternative to more resource-intensive models. The results also prove the effectiveness of temporal windowing for improving runtime and accuracy of a crop classification study, even with no prior knowledge of planting timeframes.
published_date 2025-12-31T08:00:24Z
_version_ 1831897110683844608
score 11.070674

Similar Items