View in EDS

Rethinking reference data quality: the role of mixed pixels in remote sensing classification.

Saved in:
Bibliographic Details
Title: Rethinking reference data quality: the role of mixed pixels in remote sensing classification.
Authors: Correa, Sabrina P. L. P.1 (AUTHOR) sabrina.correa@ufv.br, Reis, M. S.2 (AUTHOR), da Silva, M. P.1 (AUTHOR), dos Santos, J. A.3 (AUTHOR), Oliveira, H. N.1 (AUTHOR), Oliveira, J. C.1 (AUTHOR), Körting, T. S.2 (AUTHOR), dos Santos, A. P.1 (AUTHOR), Dutra, L. V.4 (AUTHOR)
Source: International Journal of Remote Sensing. Jun2026, Vol. 47 Issue 12, p5194-5218. 25p.
Subjects: Pixels, Data quality, Classification algorithms, Environmental mapping, Rain forests, Remote sensing
Abstract: Current recommendations for supervised machine learning classification in Remote Sensing advocate for using only high-quality reference data, which is often associated to pure pixels or endmembers. This focus, however, overlooks a fundamental challenge: real-world environmental images are rarely composed primarily of pure pixels. As a result, using only pure pixels as training data can leave a significant portion of the image unrepresented and hinder adequate classification. To demonstrate this effect, we introduce the Reference Sample Selection (RSS) approach. RSS systematically varies pixel purity in the training dataset to assess its impact on classification results. Pixel purity is determined based on a finer spatial resolution image. In this study, we present a case study within a select region of the Brazilian Amazon Rainforest. We applied RSS to the commonly used medium spatial resolution data from the Sentinel-2 MultiSpectral Imager (MSI) to target four land cover types: forest, water, grassland, and bare soil. The analysis used three common shallow classifiers: K-Nearest Neighbours (KNN), Support Vector Machines (SVM), and Random Forests (RFR). Our results demonstrate that including pixels with varied purity levels can significantly alter classification accuracy, depending on the land cover class. This finding challenges the conventional definition of reference data quality and highlights the need for using training samples that represent the entire image, not just its purest components. This method is readily applicable to a wide range of Remote Sensing studies. The source code and used data are available at and . [ABSTRACT FROM AUTHOR]
Copyright of International Journal of Remote Sensing is the property of Taylor & Francis Ltd 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
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 195040111
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Rethinking reference data quality: the role of mixed pixels in remote sensing classification.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Correa%2C+Sabrina+P%2E+L%2E+P%2E%22">Correa, Sabrina P. L. P.</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> sabrina.correa@ufv.br</i><br /><searchLink fieldCode="AR" term="%22Reis%2C+M%2E+S%2E%22">Reis, M. S.</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22da+Silva%2C+M%2E+P%2E%22">da Silva, M. P.</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22dos+Santos%2C+J%2E+A%2E%22">dos Santos, J. A.</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Oliveira%2C+H%2E+N%2E%22">Oliveira, H. N.</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Oliveira%2C+J%2E+C%2E%22">Oliveira, J. C.</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Körting%2C+T%2E+S%2E%22">Körting, T. S.</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22dos+Santos%2C+A%2E+P%2E%22">dos Santos, A. P.</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Dutra%2C+L%2E+V%2E%22">Dutra, L. V.</searchLink><relatesTo>4</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22International+Journal+of+Remote+Sensing%22">International Journal of Remote Sensing</searchLink>. Jun2026, Vol. 47 Issue 12, p5194-5218. 25p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Pixels%22">Pixels</searchLink><br /><searchLink fieldCode="DE" term="%22Data+quality%22">Data quality</searchLink><br /><searchLink fieldCode="DE" term="%22Classification+algorithms%22">Classification algorithms</searchLink><br /><searchLink fieldCode="DE" term="%22Environmental+mapping%22">Environmental mapping</searchLink><br /><searchLink fieldCode="DE" term="%22Rain+forests%22">Rain forests</searchLink><br /><searchLink fieldCode="DE" term="%22Remote+sensing%22">Remote sensing</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Current recommendations for supervised machine learning classification in Remote Sensing advocate for using only high-quality reference data, which is often associated to pure pixels or endmembers. This focus, however, overlooks a fundamental challenge: real-world environmental images are rarely composed primarily of pure pixels. As a result, using only pure pixels as training data can leave a significant portion of the image unrepresented and hinder adequate classification. To demonstrate this effect, we introduce the Reference Sample Selection (RSS) approach. RSS systematically varies pixel purity in the training dataset to assess its impact on classification results. Pixel purity is determined based on a finer spatial resolution image. In this study, we present a case study within a select region of the Brazilian Amazon Rainforest. We applied RSS to the commonly used medium spatial resolution data from the Sentinel-2 MultiSpectral Imager (MSI) to target four land cover types: forest, water, grassland, and bare soil. The analysis used three common shallow classifiers: K-Nearest Neighbours (KNN), Support Vector Machines (SVM), and Random Forests (RFR). Our results demonstrate that including pixels with varied purity levels can significantly alter classification accuracy, depending on the land cover class. This finding challenges the conventional definition of reference data quality and highlights the need for using training samples that represent the entire image, not just its purest components. This method is readily applicable to a wide range of Remote Sensing studies. The source code and used data are available at and . [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of International Journal of Remote Sensing is the property of Taylor & Francis Ltd 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=195040111
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1080/01431161.2026.2664863
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 25
        StartPage: 5194
    Subjects:
      – SubjectFull: Pixels
        Type: general
      – SubjectFull: Data quality
        Type: general
      – SubjectFull: Classification algorithms
        Type: general
      – SubjectFull: Environmental mapping
        Type: general
      – SubjectFull: Rain forests
        Type: general
      – SubjectFull: Remote sensing
        Type: general
    Titles:
      – TitleFull: Rethinking reference data quality: the role of mixed pixels in remote sensing classification.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Correa, Sabrina P. L. P.
      – PersonEntity:
          Name:
            NameFull: Reis, M. S.
      – PersonEntity:
          Name:
            NameFull: da Silva, M. P.
      – PersonEntity:
          Name:
            NameFull: dos Santos, J. A.
      – PersonEntity:
          Name:
            NameFull: Oliveira, H. N.
      – PersonEntity:
          Name:
            NameFull: Oliveira, J. C.
      – PersonEntity:
          Name:
            NameFull: Körting, T. S.
      – PersonEntity:
          Name:
            NameFull: dos Santos, A. P.
      – PersonEntity:
          Name:
            NameFull: Dutra, L. V.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 15
              M: 06
              Text: Jun2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 01431161
          Numbering:
            – Type: volume
              Value: 47
            – Type: issue
              Value: 12
          Titles:
            – TitleFull: International Journal of Remote Sensing
              Type: main
ResultId 1