DCSF-Net: a dual-branch cross-scale spatiotemporal fusion network for fine-scale mangrove mapping from RGB and Sentinel-2 imagery
Frontiers in Plant Science · 24.08.2026 · 17
DOI: 10.3389/fpls.2026.1931676 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Plant Science, online erschienen am 24.08.2026. Verfasst von Shiyu Zhuang und 6 weiteren Autor:innen. Beteiligte Einrichtung: College of Marine Science and Environment, Dalian Ocean University, Dalian, China. Die Arbeit nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Accurate fine-scale mangrove mapping is essential for coastal resource monitoring, ecological restoration, and shoreline management, yet fragmented boundaries, heterogeneous intertidal backgrounds, and the limited spectral dimensionality of high-resolution RGB imagery continue to constrain class separability. We developed DCSF-Net, a dual-branch cross-scale spatiotemporal fusion network that integrates 0.3 m RGB imagery with a 26-channel Sentinel-2 spectral-phenological feature tensor derived from 2024 dry-season (T1, October-December) and wet-season (T2, April-September) median composites and their differences. The RGB branch uses local boundary attention (LBA) and a directional topology module (DTM) to retain local contrast and elongated morphology, while the Deformable Cross-Scale Attention Bridge (D-CSAB) fuses the high-resolution spatial feature tensor output by the RGB branch with the upsampled Sentinel-2 representation through RGB-guided deformable convolution, cross-attention, and zero-initialized residual injection. On the test set, DCSF-Net achieved an F1-score of 95.68% and an intersection over union (IoU) of 91.72%, outperforming the evaluated RGB-only baselines. In matched-input ablations, replacing D-CSAB with direct fusion reduced IoU by 3.20 percentage points, removing zero-initialized residual injection reduced IoU by 1.86 points, and jointly removing LBA and DTM reduced IoU by 5.36 points. These results demonstrate the value of combining fine spatial detail with complementary spectral-seasonal context for mangrove mapping within the present study area and experimental design.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Marine Science and Environment, Dalian Ocean University, Dalian, China.
- Guangxi Key Laboratory of Marine Environmental Science, Guangxi Academy of Marine Sciences, Nanning, China.
- The State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China.
Zitieren
APA
Zhuang, S., Wen, L., Wang, Y., Wang, Z., He, Y., Chen, L., & Cui, K. (2026). DCSF-Net: a dual-branch cross-scale spatiotemporal fusion network for fine-scale mangrove mapping from RGB and Sentinel-2 imagery. Frontiers in Plant Science, 17. https://doi.org/10.3389/fpls.2026.1931676
Vancouver
Zhuang S, Wen L, Wang Y, Wang Z, He Y, Chen L, et al. DCSF-Net: a dual-branch cross-scale spatiotemporal fusion network for fine-scale mangrove mapping from RGB and Sentinel-2 imagery. Frontiers in Plant Science. 2026;17. doi:10.3389/fpls.2026.1931676
BibTeX
@article{Zhuang2026,
author = {Zhuang, Shiyu and Wen, Lili and Wang, Yushen and Wang, Zhihan and He, Yiduo and Chen, Lei and Cui, Kailong},
title = {DCSF-Net: a dual-branch cross-scale spatiotemporal fusion network for fine-scale mangrove mapping from RGB and Sentinel-2 imagery},
journal = {Frontiers in Plant Science},
year = {2026},
volume = {17},
doi = {10.3389/fpls.2026.1931676}
}
EUVIMED