Overcoming spectral and tidal challenges in mangrove mapping with a multi-modal deep learning network fusing phenological and texture features
• A novel multi-modal deep learning framework for mangrove mapping. • Integrates tide-resilient phenology and spatial texture features. • Employs attention mechanisms for adaptive feature fusion. • Achieves superior accuracy across three Chinese coastal sites. • Demonstrates robust performance with limited training samples.
Authors
- Chunpeng Chen (ORCID: https://orcid.org/0009-0007-7649-2178)
- Xiaojin Huang
- Wenting Wu (ORCID: https://orcid.org/0000-0003-4620-7595)
- Mengmeng Li
Institutions
- East China Normal University (CN)
- Fuzhou University (CN)
Publication Details
- Journal
- International Journal of Applied Earth Observation and Geoinformation
- Published
- 2026-05-31
- DOI
- https://doi.org/10.1016/j.jag.2026.105377
- Primary Topic
- Coastal wetland ecosystem dynamics
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China
- State Key Laboratory of Estuarine and Coastal Research