Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 2, 2026International Journal of Digital EarthOpen Access

A cross-scale synergistic framework integrating UAV LiDAR and sentinel-2 imagery for fine-grained vegetation mapping in coastal wetlands

View Full Paper
Ask AI
Bookmark
Share

Authors

YWYouwen WangYLYunmei LiJLJuhua Luo

Discussion

Loading...

Member takes

Overview

Observational remote sensing study demonstrates high-accuracy cross-scale wetland vegetation mapping in coastal tidal flats, indicating scalable ecological monitoring potential.

Key Points

  • To develop a multi-scale framework combining UAV LiDAR and Sentinel-2 satellite imagery for accurate, fine-grained vegetation mapping in complex coastal muddy tidal flats.
  • Developed CMFF-RandLA-Net for UAV LiDAR point cloud classification incorporating BRDF-corrected intensity, VDVI, and normalized scan angles alongside a feature fusion strategy.
  • Validated the model in the coastal wetlands of Yancheng, China, and used the classified point clouds as ground truth to train satellite classifiers (XGBoost, Random Forest, LightGBM, Linear SVM) on Sentinel-2 data.
  • CMFF-RandLA-Net achieved an overall accuracy of 95.53% for point cloud classification, yielding F1-scores above 0.80 for dominant species Spartina alterniflora and Phragmites australis.
  • XGBoost was the top-performing satellite classifier with an overall accuracy of 92.85% and a Kappa coefficient of 0.8381, uniquely distinguishing minority vegetation classes for regional mapping.

Cite This Study

Wang et al. (2026) studied this question.

synapsesocial.com/papers/6a97e28dc562ede874ec6b69https://doi.org/10.1080/17538947.2026.2714612
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1High-Resolution Mapping Coastal Wetland Vegetation Using Frequency-Augmented Deep Learning Method2026
  2. 2Improved Grass Species Mapping in High-Diversity Wetland by Combining UAV-Based Spectral, Textural, Geometric Measurements2026 · 4 citations
  3. 3Synergistic use of Sentinel-2 and UAV-derived data for plant fractional cover distribution mapping of coastal meadows with digital elevation models2024 · 15 citations
  4. 4Integrating SAR and Optical Data for Aboveground Biomass Estimation of Coastal Wetlands Using Machine Learning: Multi-Scale Approach2024 · 33 citations
  5. 5Evaluating Adaptive Classification Methods for Mangrove Mapping with Multi-Resolution Remote Sensing Imagery2026