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

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.

Enhancing monitoring of mangrove spatiotemporal tree diversity and distribution patterns

“…Herein, the literature pertaining to the application of SAR and combined multispectral imagery with SAR for mangrove species identification was compiled and reviewed, including WORLDVIEW‐3 and RADARSAT‐2 (Zhang et al, 2018); ALOS PALSAR, ALOS PRISM, and IKONOS (Brown et al, 2016); ALOS PALSAR‐2 and RADARSAT‐2 (Ferrentino et al, 2020); WORLDVIEW‐2 and TANDEM‐X SAR (Rahman et al, 2019); and SENTINEL‐1 SAR and SENTINEL‐2 MSI (Xia, Yokoya, & Pham, 2020). Notably, none of these studies considered the tidal influence on SAR backscatter values.…”

Green Energy Sources Assessment Using Sentinel-1 Satellite Remote Sensing

“…In these conditions, optical multispectral satellites lose their capability and can only be complementary to the measurement capabilities of SAR satellites. These satellites can understand valuable data for forest mapping, predicting forest area (Schmullius, 2020), forest change (Hansen et al, 2013), forest species identification (Xia et al, 2020), and harvest management (Shang et al, 2020) by considering the geometric structure of forests with the ability to use passive sensors.…”

Impacts of changes in mangrove ecosystems in the Ba and Rewa deltas, Fiji using multi-temporal Landsat data and social survey

“…Future research should focus on the exploration of high-resolution optical images, SAR images, and hyperspectral images combined with ground data to provide more precise information about the mangrove area, species, biomass, and rate of degradation (Pham et al 2019). Advanced technique in mapping species by remote sensing technique is also worth to explore, with the pixel-based, object-based classification, as well as machine learning algorithm (Kamal and Phinn 2011;Xia, Yokoya, and Pham 2020). The ecological impacts of the degradation of the mangrove ecosystem should also be assessed to identify appropriate solutions and management strategies.…”