Fine monitoring method for mangrove wetland ecosystem based on sentinel data fusion and RF optimization
Year: 2025
Type: article
Abstract: The study introduces the Sentinel Data Fusion and RF Optimization-Based Monitoring Model for Mangrove Wetlands (SDF-RF). This novel model integrates advanced satellite data processing (Sentinel series) with machine learning (Random Forest algorithm) to achieve fine-grained image segmentation and 3D feature classification for mangrove ecosystems. By weighting the segmented features and organizing them into a 3D framework, the model demonstrated exceptional performance, with a misclassification rate below 0.001 and overall classification accuracy exceeding 98% on benchmark datasets. In the field verification of Zhanjiang Mangrove Reserve, SDF-RF outperformed other models. The accuracy rate in biomass prediction and environmental data classification was as high as 98%, highlighting its potential to completely change mangrove monitoring through precise land feature identification and ecological protection applications. This innovation bridges remote sensing and AI, offering a robust solution for mangrove ecosystem protection.
Source: Systems and Soft Computing
Authors: Shuwen Wang, Taisi Chen, Zimin Li, Haitao Sang
Institution: Lingnan Normal University
Language: English
Subfield: Media Technology
Field: Engineering
Domain: Physical Sciences
SDGs: Life on land, Climate action
Open Access status: gold
Estimated APC paid: $1,870
Funder: Lingnan Normal University
Award: G8887405673
OpenAlex ID: W4413185484