Synergistic Fusion of Sentinel-1 and Sentinel-2 for Global LULC Mapping : The Multimodal Network LULC-Former and Dynamic World+ Dataset
Yu, Hao ; Li, Gen ; Liu, Haoyu ; Zhu, Songyan ; Xu, Jian ; Dong, Wenquan LU
; Li, Changjian
and Shi, Jiancheng
(2025)
In IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
19.
p.2511-2524
- Abstract
Accurate, high-resolution global land use and land cover (LULC) mapping is crucial for environmental monitoring, but remains challenging when relying solely on multispectral data. Most existing global LULC mapping studies rely exclusively on multispectral observations, and even those that incorporate synthetic aperture radar (SAR) data often fail to fully exploit the information it provides. SAR provides an all-weather sensing capability and is uniquely sensitive to surface structure, texture, and moisture—critical information for LULC classes that are often spectrally ambiguous. To address this data gap, we introduce the Dynamic World+ dataset, a new global benchmark that expands the authoritative Dynamic World by aligning it with... (More)
Accurate, high-resolution global land use and land cover (LULC) mapping is crucial for environmental monitoring, but remains challenging when relying solely on multispectral data. Most existing global LULC mapping studies rely exclusively on multispectral observations, and even those that incorporate synthetic aperture radar (SAR) data often fail to fully exploit the information it provides. SAR provides an all-weather sensing capability and is uniquely sensitive to surface structure, texture, and moisture—critical information for LULC classes that are often spectrally ambiguous. To address this data gap, we introduce the Dynamic World+ dataset, a new global benchmark that expands the authoritative Dynamic World by aligning it with Sentinel-1 SAR data. In addition, to facilitate the combination of multispectral and SAR data, we propose a lightweight transformer architecture termed LULC-Former. It incorporates two innovative modules, the dual-modal enhancement module and mutual modal aggregation module, designed to exploit cross-information between the two modalities in a split-fusion manner. These modules enable spectral features to guide the interpretation of SAR texture, and vice versa, thereby improving the overall performance of global LULC semantic segmentation. Furthermore, we adopt an imbalanced parameter allocation strategy, which assigns parameters to different modalities based on the distinct physical information each provides for LULC characterization. Experiments demonstrate that our network outperforms existing transformer and CNN-based models, achieving a mean intersection over union of 59.58%, an overall accuracy of 79.48%, and an F1 score of 71.68% with only 26.70 M parameters. Furthermore, the generated national-scale LULC maps across diverse regions demonstrate the effectiveness of the proposed dataset and network.
(Less)
- author
- Yu, Hao
; Li, Gen
; Liu, Haoyu
; Zhu, Songyan
; Xu, Jian
; Dong, Wenquan
LU
; Li, Changjian
and Shi, Jiancheng
- organization
- publishing date
- 2025-12-09
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Benchmark dataset, efficient transformer, global land use and land cover (LULC), optical–synthetic aperture radar (optical–SAR) fusion, semantic segmentation, Sentinel-1 and -2
- in
- IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- volume
- 19
- pages
- 14 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- external identifiers
-
- scopus:105024607153
- ISSN
- 1939-1404
- DOI
- 10.1109/JSTARS.2025.3641788
- language
- English
- LU publication?
- yes
- additional info
- Publisher Copyright: © 2008-2012 IEEE.
- id
- 5b2a0abc-4a61-4894-b520-4094a043beb1
- date added to LUP
- 2026-03-30 15:02:39
- date last changed
- 2026-03-31 03:32:36
@article{5b2a0abc-4a61-4894-b520-4094a043beb1,
abstract = {{<p>Accurate, high-resolution global land use and land cover (LULC) mapping is crucial for environmental monitoring, but remains challenging when relying solely on multispectral data. Most existing global LULC mapping studies rely exclusively on multispectral observations, and even those that incorporate synthetic aperture radar (SAR) data often fail to fully exploit the information it provides. SAR provides an all-weather sensing capability and is uniquely sensitive to surface structure, texture, and moisture—critical information for LULC classes that are often spectrally ambiguous. To address this data gap, we introduce the Dynamic World+ dataset, a new global benchmark that expands the authoritative Dynamic World by aligning it with Sentinel-1 SAR data. In addition, to facilitate the combination of multispectral and SAR data, we propose a lightweight transformer architecture termed LULC-Former. It incorporates two innovative modules, the dual-modal enhancement module and mutual modal aggregation module, designed to exploit cross-information between the two modalities in a split-fusion manner. These modules enable spectral features to guide the interpretation of SAR texture, and vice versa, thereby improving the overall performance of global LULC semantic segmentation. Furthermore, we adopt an imbalanced parameter allocation strategy, which assigns parameters to different modalities based on the distinct physical information each provides for LULC characterization. Experiments demonstrate that our network outperforms existing transformer and CNN-based models, achieving a mean intersection over union of 59.58%, an overall accuracy of 79.48%, and an F1 score of 71.68% with only 26.70 M parameters. Furthermore, the generated national-scale LULC maps across diverse regions demonstrate the effectiveness of the proposed dataset and network.</p>}},
author = {{Yu, Hao and Li, Gen and Liu, Haoyu and Zhu, Songyan and Xu, Jian and Dong, Wenquan and Li, Changjian and Shi, Jiancheng}},
issn = {{1939-1404}},
keywords = {{Benchmark dataset; efficient transformer; global land use and land cover (LULC); optical–synthetic aperture radar (optical–SAR) fusion; semantic segmentation; Sentinel-1 and -2}},
language = {{eng}},
month = {{12}},
pages = {{2511--2524}},
publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
series = {{IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing}},
title = {{Synergistic Fusion of Sentinel-1 and Sentinel-2 for Global LULC Mapping : The Multimodal Network LULC-Former and Dynamic World+ Dataset}},
url = {{http://dx.doi.org/10.1109/JSTARS.2025.3641788}},
doi = {{10.1109/JSTARS.2025.3641788}},
volume = {{19}},
year = {{2025}},
}