View in EDS HTML Full Text PDF Full Text

Using Sentinel-2 Time Series to Monitor the Loss of Individual Large Trees in Humanized Landscapes.

Saved in:
Bibliographic Details
Title: Using Sentinel-2 Time Series to Monitor the Loss of Individual Large Trees in Humanized Landscapes.
Authors: Soutinho, João Gonçalo1,2,3,4,5,6 (AUTHOR) soutinhojg@cibio.up.pt, Vierling, Kerri T.2,5 (AUTHOR), Vierling, Lee A.3,7 (AUTHOR), Müller, Jörg4,8 (AUTHOR), Gonçalves, João F.1,3,5,9 (AUTHOR)
Source: Remote Sensing. May2026, Vol. 18 Issue 10, p1519. 38p.
Subjects: Trees, Tree mortality, Landscapes, Time series analysis, Remote sensing, Change-point problems
Geographic Terms: Portugal
Abstract: Highlights: What are the main findings? Sentinel-2 spectral indices' time series, combined with breakpoint detection algorithms, can identify the loss of previously mapped individual large trees in humanized and peri-urban landscapes, achieving balanced accuracies of 73–78% under conservative validation. Detection performance varies strongly with the choice of the spectral index, algorithm and post-breakpoint validation strategy. It is also significantly influenced by tree genus and structural traits (size and height), whereas time-series pre-processing has a comparatively smaller effect. What are the implications of the main findings? Earth observation-based breakpoint analysis provides a scalable, low-cost approach for retrospective and medium- to long-term monitoring of large trees, complementing field surveys and citizen-science inventories. The proposed framework supports wide-scale monitoring systems capable of issuing early warnings vital to support conservation planning, and policy evaluation for large-tree retention in fragmented landscapes, including urban, agricultural, and selectively managed forest environments. Large trees are keystone ecological structures that sustain biodiversity and ecosystem services, particularly in human-altered landscapes. However, their persistence is increasingly threatened by land-use change, urban expansion, and inadequate monitoring. This study develops and validates a scalable, automated framework for monitoring the loss of large individual trees using satellite image time series and breakpoint detection. We compared four spectral indices (SIs): Enhanced Vegetation Index 2–EVI2; Normalized Burn Ratio–NBR; Normalized Difference Red Edge–NDRE, and the Normalized Difference Vegetation Index–NDVI derived from Sentinel-2 imagery (2015–2025) for 691 georeferenced trees in Lousada, northern Portugal. Data were accessed and processed in Google Earth Engine and analyzed using a custom R-based workflow, including cloud masking, gap-filling, temporal interpolation, upper-envelope smoothing, deseasonalization, and break detection. Five breakpoint detection algorithms were compared: BFAST, energy-divisive, linear regression of structural changes, wild-binary segmentation, and change point models. Detected breakpoints were subsequently post-validated to determine whether they were associated with declines in SIs, using three pre-/post-breakpoint methods: comparisons of short- and long-term medians and a randomized trend analysis. As a baseline, these algorithms/post-validation logic were compared against the Continuous Change Detection and Classification (CCDC) approach. The results indicate moderate but consistent break detection performance, with a maximum balanced accuracy of 73% (for EVI2 or NDVI and using the energy-divisive algorithm coupled with the long-term median post-validator) under conservative validation criteria and high specificity for surviving trees. CCDC ranked comparatively lower at 62%. Algorithm performance varied substantially, with the energy-divisive providing the most conservative detection and the wild-binary segmentation yielding higher sensitivity. Performance was further influenced by tree structural attributes and species identity, with larger, taller and isolated trees, as well as particular genera, showing higher detection accuracy, with genus Eucalyptus, Tilia and Celtis yielding top performance results (79–65%) and Quercus, Castanea and Platanus the lowest (62–60%). By integrating satellite observations with large-tree inventory data from the Green Giants citizen science project, this study demonstrates the potential of decentralized, Earth observation-based monitoring to support tree-level loss assessments in fragmented landscapes. The proposed framework provides a transferable foundation for wide-scale monitoring of large trees in peri-urban and mixed-use environments. [ABSTRACT FROM AUTHOR]
Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 194141044
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Using Sentinel-2 Time Series to Monitor the Loss of Individual Large Trees in Humanized Landscapes.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Soutinho%2C+João+Gonçalo%22">Soutinho, João Gonçalo</searchLink><relatesTo>1,2,3,4,5,6</relatesTo> (AUTHOR)<i> soutinhojg@cibio.up.pt</i><br /><searchLink fieldCode="AR" term="%22Vierling%2C+Kerri+T%2E%22">Vierling, Kerri T.</searchLink><relatesTo>2,5</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Vierling%2C+Lee+A%2E%22">Vierling, Lee A.</searchLink><relatesTo>3,7</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Müller%2C+Jörg%22">Müller, Jörg</searchLink><relatesTo>4,8</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Gonçalves%2C+João+F%2E%22">Gonçalves, João F.</searchLink><relatesTo>1,3,5,9</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Remote+Sensing%22">Remote Sensing</searchLink>. May2026, Vol. 18 Issue 10, p1519. 38p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Trees%22">Trees</searchLink><br /><searchLink fieldCode="DE" term="%22Tree+mortality%22">Tree mortality</searchLink><br /><searchLink fieldCode="DE" term="%22Landscapes%22">Landscapes</searchLink><br /><searchLink fieldCode="DE" term="%22Time+series+analysis%22">Time series analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Remote+sensing%22">Remote sensing</searchLink><br /><searchLink fieldCode="DE" term="%22Change-point+problems%22">Change-point problems</searchLink>
– Name: SubjectGeographic
  Label: Geographic Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Portugal%22">Portugal</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Highlights: What are the main findings? Sentinel-2 spectral indices' time series, combined with breakpoint detection algorithms, can identify the loss of previously mapped individual large trees in humanized and peri-urban landscapes, achieving balanced accuracies of 73–78% under conservative validation. Detection performance varies strongly with the choice of the spectral index, algorithm and post-breakpoint validation strategy. It is also significantly influenced by tree genus and structural traits (size and height), whereas time-series pre-processing has a comparatively smaller effect. What are the implications of the main findings? Earth observation-based breakpoint analysis provides a scalable, low-cost approach for retrospective and medium- to long-term monitoring of large trees, complementing field surveys and citizen-science inventories. The proposed framework supports wide-scale monitoring systems capable of issuing early warnings vital to support conservation planning, and policy evaluation for large-tree retention in fragmented landscapes, including urban, agricultural, and selectively managed forest environments. Large trees are keystone ecological structures that sustain biodiversity and ecosystem services, particularly in human-altered landscapes. However, their persistence is increasingly threatened by land-use change, urban expansion, and inadequate monitoring. This study develops and validates a scalable, automated framework for monitoring the loss of large individual trees using satellite image time series and breakpoint detection. We compared four spectral indices (SIs): Enhanced Vegetation Index 2–EVI2; Normalized Burn Ratio–NBR; Normalized Difference Red Edge–NDRE, and the Normalized Difference Vegetation Index–NDVI derived from Sentinel-2 imagery (2015–2025) for 691 georeferenced trees in Lousada, northern Portugal. Data were accessed and processed in Google Earth Engine and analyzed using a custom R-based workflow, including cloud masking, gap-filling, temporal interpolation, upper-envelope smoothing, deseasonalization, and break detection. Five breakpoint detection algorithms were compared: BFAST, energy-divisive, linear regression of structural changes, wild-binary segmentation, and change point models. Detected breakpoints were subsequently post-validated to determine whether they were associated with declines in SIs, using three pre-/post-breakpoint methods: comparisons of short- and long-term medians and a randomized trend analysis. As a baseline, these algorithms/post-validation logic were compared against the Continuous Change Detection and Classification (CCDC) approach. The results indicate moderate but consistent break detection performance, with a maximum balanced accuracy of 73% (for EVI2 or NDVI and using the energy-divisive algorithm coupled with the long-term median post-validator) under conservative validation criteria and high specificity for surviving trees. CCDC ranked comparatively lower at 62%. Algorithm performance varied substantially, with the energy-divisive providing the most conservative detection and the wild-binary segmentation yielding higher sensitivity. Performance was further influenced by tree structural attributes and species identity, with larger, taller and isolated trees, as well as particular genera, showing higher detection accuracy, with genus Eucalyptus, Tilia and Celtis yielding top performance results (79–65%) and Quercus, Castanea and Platanus the lowest (62–60%). By integrating satellite observations with large-tree inventory data from the Green Giants citizen science project, this study demonstrates the potential of decentralized, Earth observation-based monitoring to support tree-level loss assessments in fragmented landscapes. The proposed framework provides a transferable foundation for wide-scale monitoring of large trees in peri-urban and mixed-use environments. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=194141044
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/rs18101519
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 38
        StartPage: 1519
    Subjects:
      – SubjectFull: Trees
        Type: general
      – SubjectFull: Tree mortality
        Type: general
      – SubjectFull: Landscapes
        Type: general
      – SubjectFull: Time series analysis
        Type: general
      – SubjectFull: Remote sensing
        Type: general
      – SubjectFull: Change-point problems
        Type: general
      – SubjectFull: Portugal
        Type: general
    Titles:
      – TitleFull: Using Sentinel-2 Time Series to Monitor the Loss of Individual Large Trees in Humanized Landscapes.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Soutinho, João Gonçalo
      – PersonEntity:
          Name:
            NameFull: Vierling, Kerri T.
      – PersonEntity:
          Name:
            NameFull: Vierling, Lee A.
      – PersonEntity:
          Name:
            NameFull: Müller, Jörg
      – PersonEntity:
          Name:
            NameFull: Gonçalves, João F.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 15
              M: 05
              Text: May2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 20724292
          Numbering:
            – Type: volume
              Value: 18
            – Type: issue
              Value: 10
          Titles:
            – TitleFull: Remote Sensing
              Type: main
ResultId 1