Training data in satellite image classification for land cover mapping: a review

The current land cover (LC) mapping paradigm relies on automatic satellite imagery classification, predominantly through supervised methods, which depend on training data to calibrate classification algorithms. Hence, training data have a critical influence on classification accuracy. Although resea...

Full description

Saved in:
Bibliographic Details
Main Authors: Daniel Moraes, Manuel L. Campagnolo, Mário Caetano
Format: Article
Language:English
Published: Taylor & Francis Group 2024-12-01
Series:European Journal of Remote Sensing
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/22797254.2024.2341414
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850127137221115904
author Daniel Moraes
Manuel L. Campagnolo
Mário Caetano
author_facet Daniel Moraes
Manuel L. Campagnolo
Mário Caetano
author_sort Daniel Moraes
collection DOAJ
description The current land cover (LC) mapping paradigm relies on automatic satellite imagery classification, predominantly through supervised methods, which depend on training data to calibrate classification algorithms. Hence, training data have a critical influence on classification accuracy. Although research on specific aspects of training data in the LC classification context exists, a study that organizes and synthetizes the multiplicity of aspects and findings of these researches is needed. In this article, we review the training data used for LC classification of satellite imagery. A protocol of identification and selection of relevant documents was followed, resulting in 114 peer-reviewed studies included. Main research topics were identified and documents were characterized according to their contribution to each topic, which allowed uncovering subtopics and categories and synthetizing the main findings regarding different aspects of the training dataset. The analysis found four research topics, namely construction of the training dataset, sample quality, sampling design and advanced learning techniques. Subtopics included sample collection method, sample cleaning procedures, sample size, sampling method, class balance and distribution, among others. A summary of the main findings and approaches provided an overview of the research in this area, which may serve as a starting point for new LC mapping initiatives.
format Article
id doaj-art-a647b71059e346e79587bd0959aca73d
institution OA Journals
issn 2279-7254
language English
publishDate 2024-12-01
publisher Taylor & Francis Group
record_format Article
series European Journal of Remote Sensing
spelling doaj-art-a647b71059e346e79587bd0959aca73d2025-08-20T02:33:44ZengTaylor & Francis GroupEuropean Journal of Remote Sensing2279-72542024-12-0157110.1080/22797254.2024.2341414Training data in satellite image classification for land cover mapping: a reviewDaniel Moraes0Manuel L. Campagnolo1Mário Caetano2NOVA Information Management School (NOVA IMS), Universidade Nova de Lisboa, Lisbon, PortugalForest Research Centre, School of Agriculture, University of Lisbon, Lisbon, PortugalNOVA Information Management School (NOVA IMS), Universidade Nova de Lisboa, Lisbon, PortugalThe current land cover (LC) mapping paradigm relies on automatic satellite imagery classification, predominantly through supervised methods, which depend on training data to calibrate classification algorithms. Hence, training data have a critical influence on classification accuracy. Although research on specific aspects of training data in the LC classification context exists, a study that organizes and synthetizes the multiplicity of aspects and findings of these researches is needed. In this article, we review the training data used for LC classification of satellite imagery. A protocol of identification and selection of relevant documents was followed, resulting in 114 peer-reviewed studies included. Main research topics were identified and documents were characterized according to their contribution to each topic, which allowed uncovering subtopics and categories and synthetizing the main findings regarding different aspects of the training dataset. The analysis found four research topics, namely construction of the training dataset, sample quality, sampling design and advanced learning techniques. Subtopics included sample collection method, sample cleaning procedures, sample size, sampling method, class balance and distribution, among others. A summary of the main findings and approaches provided an overview of the research in this area, which may serve as a starting point for new LC mapping initiatives.https://www.tandfonline.com/doi/10.1080/22797254.2024.2341414Land coversatellite imagessupervised classificationtraining datasampling designsample quality
spellingShingle Daniel Moraes
Manuel L. Campagnolo
Mário Caetano
Training data in satellite image classification for land cover mapping: a review
European Journal of Remote Sensing
Land cover
satellite images
supervised classification
training data
sampling design
sample quality
title Training data in satellite image classification for land cover mapping: a review
title_full Training data in satellite image classification for land cover mapping: a review
title_fullStr Training data in satellite image classification for land cover mapping: a review
title_full_unstemmed Training data in satellite image classification for land cover mapping: a review
title_short Training data in satellite image classification for land cover mapping: a review
title_sort training data in satellite image classification for land cover mapping a review
topic Land cover
satellite images
supervised classification
training data
sampling design
sample quality
url https://www.tandfonline.com/doi/10.1080/22797254.2024.2341414
work_keys_str_mv AT danielmoraes trainingdatainsatelliteimageclassificationforlandcovermappingareview
AT manuellcampagnolo trainingdatainsatelliteimageclassificationforlandcovermappingareview
AT mariocaetano trainingdatainsatelliteimageclassificationforlandcovermappingareview