Species-Level Saltmarsh Vegetation Fractional Cover Estimation Based on Time Series Sentinel-2 Imagery with the Assistance of Sample Expansion

Species-Level Saltmarsh Vegetation Fractional Cover Estimation Based on Time Series Sentinel-2 Imagery with the Assistance of Sample Expansion

Coastal saltmarsh wetlands are vital “blue carbon” ecosystems. Fractional vegetation cover (FVC) is a key indicator revealing the spatial distribution and growth status of vegetation. Remote sensing has proven a vital tool for FVC estimation at regional or landscape scales. Establishing a species-le...

Full description

Saved in:
Bibliographic Details
Main Authors: Jinghan Sha, Zhaojun Zhuo, Qingqing Zhou, Yinghai Ke, Mengyao Zhang, Jinyuan Li, Yukui Min
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Diversity
Subjects:
vegetation coverage
remote sensing
deep learning
coastal wetland
sample expansion
Online Access:https://www.mdpi.com/1424-2818/17/1/3
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Coastal saltmarsh wetlands are vital “blue carbon” ecosystems. Fractional vegetation cover (FVC) is a key indicator revealing the spatial distribution and growth status of vegetation. Remote sensing has proven a vital tool for FVC estimation at regional or landscape scales. Establishing a species-level FVC estimation model usually requires sufficient field measurements as training/validation samples. However, field-based sample collection in wetlands is challenging because of the harsh environment. In this study, we proposed a Fractional Vegetation Cover Wasserstein Generative Adversarial Network (FVC-WGAN) model for FVC sample expansion. We chose the Yellow River Delta as the study area and utilized the time series Sentinel-2 imagery and random forest regression model for species-level FVC estimation with the assistance of FVC-WGAN-generated samples. To assess the efficacy of FVC-WGAN, we designed 13 experimental schemes using different combinations of real and generated samples. Our results show that the FVC-WGAN-generated samples had similar feature values to the real samples. Supplementing 500 real samples with generated samples can achieve good accuracy with an average RMSE < 0.1. As the number of real samples increased, the accuracies of FVC estimation improved. When the number of the generated samples was balanced with the real samples, the accuracy improved in terms of both R<sup>2</sup>, RMSE and the spatial consistency.
ISSN:1424-2818

Similar Items