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
Description
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]
ISSN:01431161
DOI:10.1080/01431161.2026.2664863