Probabilistic Mangrove Species Mapping with Multiple-Source Remote-Sensing Datasets Using Label Distribution Learning in Xuan Thuy National Park, Vietnam

Junshi Xia,Naoto Yokoya,Tien Dat Pham

doi:10.3390/rs12223834

Junshi Xia, Naoto Yokoya + Show 1 more

Open Access

https://doi.org/10.3390/rs12223834

Copy DOI

Abstract

Mangrove forests play an important role in maintaining water quality, mitigating climate change impacts, and providing a wide range of ecosystem services. Effective identification of mangrove species using remote-sensing images remains a challenge. The combinations of multi-source remote-sensing datasets (with different spectral/spatial resolution) are beneficial to the improvement of mangrove tree species discrimination. In this paper, various combinations of remote-sensing datasets including Sentinel-1 dual-polarimetric synthetic aperture radar (SAR), Sentinel-2 multispectral, and Gaofen-3 full-polarimetric SAR data were used to classify the mangrove communities in Xuan Thuy National Park, Vietnam. The mixture of mangrove communities consisting of small and shrub mangrove patches is generally difficult to separate using low/medium spatial resolution. To alleviate this problem, we propose to use label distribution learning (LDL) to provide the probabilistic mapping of tree species, including Sonneratia caseolaris (SC), Kandelia obovata (KO), Aegiceras corniculatum (AC), Rhizophora stylosa (RS), and Avicennia marina (AM). The experimental results show that the best classification performance was achieved by an integration of Sentinel-2 and Gaofen-3 datasets, demonstrating that full-polarimetric Gaofen-3 data is superior to the dual-polarimetric Sentinel-1 data for mapping mangrove tree species in the tropics.

Highlights

Mangrove ecosystems can provide a range of essential ecological services, including (1) impact reduction for natural disasters, (2) habitat provision for coastal wildlife, and (3) blue carbon sequestration in the coastal zone [1,2,3]
We evaluated the performance of six different label distribution learning (LDL) methods using the combination of spectral bands and vegetation indices (VIs) derived from Sentinel-2 as the input features (Table 4)
This observation demonstrated that the full-polarimetric GF-3 synthetic aperture radar (SAR) could provide more beneficial information than dual-polarimetric S1 SAR when combining with S2 optical data to improve the classification accuracy of probabilistic mangrove species mapping

Summary

Introduction

Mangrove ecosystems can provide a range of essential ecological services, including (1) impact reduction for natural disasters, (2) habitat provision for coastal wildlife, and (3) blue carbon sequestration in the coastal zone [1,2,3]. Many approaches have been proposed to map mangrove tree species using optical and synthetic aperture radar (SAR) data with various spectral/spatial/temporal resolutions [7,8,9,10,11,12]. Medium resolutions datasets, including Sentinel and Landsat series [2], have been widely used to map the changes of large areas of mangrove. With the advantages of providing more detailed spectral and texture information, hyperspectral and high-resolution datasets are intensively used for discriminating mangrove species. Wan et al [13] have investigated four mangrove species in Hong Kong using the new hyperspectral Gaofen-5 dataset (330 spectral bands). Mougin et al [22], Proisy [23] analyzed different frequencies (C-/L-/P-band) and polarizations for the mangrove tree species mapping and biomass estimation [18]

Methods

Results

Discussion

Conclusion