Benchmarking Deep Learning for Wetland Mapping in Denmark Using Remote Sensing Data

Wetlands are critical ecosystems providing numerous ecological services, yet they face significant threats from human activities and climate change. Therefore, accurate mapping and monitoring of wetlands are crucial for formulating effective conservation and restoration strategies. While remote sens...

Full description

Saved in:
Bibliographic Details
Main Author: Muhammad Rizwan Asif
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10975079/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849728003331850240
author Muhammad Rizwan Asif
author_facet Muhammad Rizwan Asif
author_sort Muhammad Rizwan Asif
collection DOAJ
description Wetlands are critical ecosystems providing numerous ecological services, yet they face significant threats from human activities and climate change. Therefore, accurate mapping and monitoring of wetlands are crucial for formulating effective conservation and restoration strategies. While remote sensing combined with deep learning (DL) offers a promising solution, inconsistencies in wetland classification systems—where different regions define wetland types based on their policy frameworks and conservation priorities—limit the applicability of these models. Such inconsistencies make it difficult to assess their limitations in different contexts. Notably, no study has yet leveraged DL for mapping wetlands within Denmark's unique wetland classification system, as defined by the Danish nature conservation framework. Therefore, this article presents a comprehensive benchmark analysis of several DL models for wetland classification in Denmark. We utilize publicly available high-resolution multispectral aerial imagery and digital elevation models (DEMs) and evaluate the performance of three well-established network architectures: Fully Convolutional Network, U-Net, and DeepLabV3. We also assess the impact of incorporating near-infrared and DEM data in addition to traditional optical imagery. The results show that DeepLabV3 model outperforms other models, particularly when additional data layers are included, achieving the highest overall accuracy and F-measure score. Our findings also reveal that while DL models can effectively classify certain wetlands, challenges remain in distinguishing wetland with ecological similarities and in handling noisy labels. This benchmark provides a foundation for future work aimed at improving DL methods for wetland mapping in Denmark.
format Article
id doaj-art-d108fee5d38947a2b96df74688dbd876
institution DOAJ
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-d108fee5d38947a2b96df74688dbd8762025-08-20T03:09:42ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118119531196210.1109/JSTARS.2025.356395110975079Benchmarking Deep Learning for Wetland Mapping in Denmark Using Remote Sensing DataMuhammad Rizwan Asif0https://orcid.org/0000-0003-1385-8041Department of Electrical and Computer Engineering, Aarhus University, Aarhus N, DenmarkWetlands are critical ecosystems providing numerous ecological services, yet they face significant threats from human activities and climate change. Therefore, accurate mapping and monitoring of wetlands are crucial for formulating effective conservation and restoration strategies. While remote sensing combined with deep learning (DL) offers a promising solution, inconsistencies in wetland classification systems—where different regions define wetland types based on their policy frameworks and conservation priorities—limit the applicability of these models. Such inconsistencies make it difficult to assess their limitations in different contexts. Notably, no study has yet leveraged DL for mapping wetlands within Denmark's unique wetland classification system, as defined by the Danish nature conservation framework. Therefore, this article presents a comprehensive benchmark analysis of several DL models for wetland classification in Denmark. We utilize publicly available high-resolution multispectral aerial imagery and digital elevation models (DEMs) and evaluate the performance of three well-established network architectures: Fully Convolutional Network, U-Net, and DeepLabV3. We also assess the impact of incorporating near-infrared and DEM data in addition to traditional optical imagery. The results show that DeepLabV3 model outperforms other models, particularly when additional data layers are included, achieving the highest overall accuracy and F-measure score. Our findings also reveal that while DL models can effectively classify certain wetlands, challenges remain in distinguishing wetland with ecological similarities and in handling noisy labels. This benchmark provides a foundation for future work aimed at improving DL methods for wetland mapping in Denmark.https://ieeexplore.ieee.org/document/10975079/Deep learning (DL)image segmentationmultispectral imageryremote sensing (RS)wetland mapping
spellingShingle Muhammad Rizwan Asif
Benchmarking Deep Learning for Wetland Mapping in Denmark Using Remote Sensing Data
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Deep learning (DL)
image segmentation
multispectral imagery
remote sensing (RS)
wetland mapping
title Benchmarking Deep Learning for Wetland Mapping in Denmark Using Remote Sensing Data
title_full Benchmarking Deep Learning for Wetland Mapping in Denmark Using Remote Sensing Data
title_fullStr Benchmarking Deep Learning for Wetland Mapping in Denmark Using Remote Sensing Data
title_full_unstemmed Benchmarking Deep Learning for Wetland Mapping in Denmark Using Remote Sensing Data
title_short Benchmarking Deep Learning for Wetland Mapping in Denmark Using Remote Sensing Data
title_sort benchmarking deep learning for wetland mapping in denmark using remote sensing data
topic Deep learning (DL)
image segmentation
multispectral imagery
remote sensing (RS)
wetland mapping
url https://ieeexplore.ieee.org/document/10975079/
work_keys_str_mv AT muhammadrizwanasif benchmarkingdeeplearningforwetlandmappingindenmarkusingremotesensingdata