Extraction of built-up areas using Sentinel-1 and Sentinel-2 data with automated training data sampling and label noise robust cross-fusion neural networks

Up-to-date mapping of built-up areas is of paramount importance for urban planning, environmental monitoring, and disaster management. In recent years, there has been a growing interest in employing supervised machine learning and deep learning methods to map built-up areas using satellite SAR and o...

Full description

Saved in:
Bibliographic Details
Main Authors: Yu Li, Patrick Matgen, Marco Chini
Format: Article
Language:English
Published: Elsevier 2025-05-01
Series:International Journal of Applied Earth Observations and Geoinformation
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1569843225001712
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850279134948753408
author Yu Li
Patrick Matgen
Marco Chini
author_facet Yu Li
Patrick Matgen
Marco Chini
author_sort Yu Li
collection DOAJ
description Up-to-date mapping of built-up areas is of paramount importance for urban planning, environmental monitoring, and disaster management. In recent years, there has been a growing interest in employing supervised machine learning and deep learning methods to map built-up areas using satellite SAR and optical data. However, the laborious and expensive task of gathering and maintaining a vast array of diverse training data poses a challenge to the widespread adoption of these methods for large-scale built-up area mapping. This paper presents a two-step framework enabling an automated extraction of built-up areas using Sentinel-1 and Sentinel-2 data. Initially, training data for built-up and non-built-up classes are automatically sampled and labeled from Sentinel-1 and Sentinel-2 data for a given area of interest. Subsequently, a cross-fusion neural network is trained using the samples from the first step to produce a built-up map for the entire study area. To enhance the network’s resilience to label noise, a contextual virtual adversarial training (CVAT) regularization is introduced within the mean-teacher architecture. Our proposed framework was tested on 48 different study areas across the world. Both quantitative and qualitative evaluations demonstrate its robustness and effectiveness for large-scale built-up area extraction. The versatility of our framework in generating accurate and up-to-date built-up information, which is essential for monitoring urban environments and assessing economic losses resulting from natural disasters, is highlighted through comparisons with four state-of-the-art global built-up products: Global Human Settlement Built-up map based on 2018 Sentinel-2 composites (GHS-BUILT-S2), World Settlement Footprint 2019 (WSF 2019), ESA World Cover, and Dynamic World.
format Article
id doaj-art-54a1998c2b2f44cebc02fa52dbcc1a99
institution OA Journals
issn 1569-8432
language English
publishDate 2025-05-01
publisher Elsevier
record_format Article
series International Journal of Applied Earth Observations and Geoinformation
spelling doaj-art-54a1998c2b2f44cebc02fa52dbcc1a992025-08-20T01:49:12ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322025-05-0113910452410.1016/j.jag.2025.104524Extraction of built-up areas using Sentinel-1 and Sentinel-2 data with automated training data sampling and label noise robust cross-fusion neural networksYu Li0Patrick Matgen1Marco Chini2Corresponding author.; Department of Environmental Research an Innovation (ERIN), Luxembourg Institute of Science and Technology (LIST)Department of Environmental Research an Innovation (ERIN), Luxembourg Institute of Science and Technology (LIST)Department of Environmental Research an Innovation (ERIN), Luxembourg Institute of Science and Technology (LIST)Up-to-date mapping of built-up areas is of paramount importance for urban planning, environmental monitoring, and disaster management. In recent years, there has been a growing interest in employing supervised machine learning and deep learning methods to map built-up areas using satellite SAR and optical data. However, the laborious and expensive task of gathering and maintaining a vast array of diverse training data poses a challenge to the widespread adoption of these methods for large-scale built-up area mapping. This paper presents a two-step framework enabling an automated extraction of built-up areas using Sentinel-1 and Sentinel-2 data. Initially, training data for built-up and non-built-up classes are automatically sampled and labeled from Sentinel-1 and Sentinel-2 data for a given area of interest. Subsequently, a cross-fusion neural network is trained using the samples from the first step to produce a built-up map for the entire study area. To enhance the network’s resilience to label noise, a contextual virtual adversarial training (CVAT) regularization is introduced within the mean-teacher architecture. Our proposed framework was tested on 48 different study areas across the world. Both quantitative and qualitative evaluations demonstrate its robustness and effectiveness for large-scale built-up area extraction. The versatility of our framework in generating accurate and up-to-date built-up information, which is essential for monitoring urban environments and assessing economic losses resulting from natural disasters, is highlighted through comparisons with four state-of-the-art global built-up products: Global Human Settlement Built-up map based on 2018 Sentinel-2 composites (GHS-BUILT-S2), World Settlement Footprint 2019 (WSF 2019), ESA World Cover, and Dynamic World.http://www.sciencedirect.com/science/article/pii/S1569843225001712Built-up areaCross-attentionSARData fusionConvolutional neural networksNoisy label learning
spellingShingle Yu Li
Patrick Matgen
Marco Chini
Extraction of built-up areas using Sentinel-1 and Sentinel-2 data with automated training data sampling and label noise robust cross-fusion neural networks
International Journal of Applied Earth Observations and Geoinformation
Built-up area
Cross-attention
SAR
Data fusion
Convolutional neural networks
Noisy label learning
title Extraction of built-up areas using Sentinel-1 and Sentinel-2 data with automated training data sampling and label noise robust cross-fusion neural networks
title_full Extraction of built-up areas using Sentinel-1 and Sentinel-2 data with automated training data sampling and label noise robust cross-fusion neural networks
title_fullStr Extraction of built-up areas using Sentinel-1 and Sentinel-2 data with automated training data sampling and label noise robust cross-fusion neural networks
title_full_unstemmed Extraction of built-up areas using Sentinel-1 and Sentinel-2 data with automated training data sampling and label noise robust cross-fusion neural networks
title_short Extraction of built-up areas using Sentinel-1 and Sentinel-2 data with automated training data sampling and label noise robust cross-fusion neural networks
title_sort extraction of built up areas using sentinel 1 and sentinel 2 data with automated training data sampling and label noise robust cross fusion neural networks
topic Built-up area
Cross-attention
SAR
Data fusion
Convolutional neural networks
Noisy label learning
url http://www.sciencedirect.com/science/article/pii/S1569843225001712
work_keys_str_mv AT yuli extractionofbuiltupareasusingsentinel1andsentinel2datawithautomatedtrainingdatasamplingandlabelnoiserobustcrossfusionneuralnetworks
AT patrickmatgen extractionofbuiltupareasusingsentinel1andsentinel2datawithautomatedtrainingdatasamplingandlabelnoiserobustcrossfusionneuralnetworks
AT marcochini extractionofbuiltupareasusingsentinel1andsentinel2datawithautomatedtrainingdatasamplingandlabelnoiserobustcrossfusionneuralnetworks