A5002864590- Coastal wetland ecosystem dynamics
- Remote Sensing and LiDAR Applications
- Remote Sensing in Agriculture
- Coral and Marine Ecosystems Studies
- Plant and Fungal Species Descriptions
- Remote Sensing and Land Use
- Marine and coastal plant biology
- Flood Risk Assessment and Management
- Environmental Changes in China
- Soil erosion and sediment transport
- Identification and Quantification in Food
- Soil and Land Suitability Analysis
- Forest Ecology and Conservation
- Oil Spill Detection and Mitigation
- Remote-Sensing Image Classification
Vietnam Academy of Science and Technology
2018-2023
Institute of Mechanics
2018
This study investigates the effectiveness of gradient boosting decision trees techniques in estimating mangrove above-ground biomass (AGB) at Can Gio biosphere reserve (Vietnam). For this purpose, we employed a novel gradient-boosting regression technique called extreme (XGBR) algorithm implemented and verified AGB model using data from field survey 121 sampling plots conducted during dry season. The dataset fuses Sentinel-2 multispectral instrument (MSI) dual polarimetric (HH, HV) ALOS-2...
This study proposes a hybrid intelligence approach based on an extreme gradient boosting regression and genetic algorithm, namely, the XGBR-GA model, incorporating Sentinel-2, Sentinel-1, ALOS-2 PALSAR-2 data to estimate mangrove above-ground biomass (AGB), including small shrub patches in Red River Delta biosphere reserve across northern coast of Vietnam. We used novel decision tree (XGBR) technique together with algorithm (GA) optimization for feature selection construct verify AGB model...
Quantifying total carbon (TC) stocks in soil across various mangrove ecosystems is key to understanding the global cycle reduce greenhouse gas emissions. Estimating TC at a large scale remains challenging due difficulty and high cost of measurements when number samples high. In present study, we investigated capability Sentinel-2 multispectral data together with state-of-the-art machine learning (ML) technique, which combination CatBoost regression (CBR) genetic algorithm (GA) for feature...
Blue carbon ecosystems (mangroves, seagrasses and saltmarshes) are highly productive coastal habitats, considered some of the most carbon-dense on earth. They an important nature-based solution for both climate change mitigation adaptation. Quantifying blue stocks assessing their dynamics at large scales through remote sensing remains challenging due to difficulties cloud coverage, spectral, spatial temporal limitations multispectral sensors speckle noise synthetic aperture radar (SAR)....
Aboveground biomass (AGB) of mangrove forest plays a crucial role in global carbon cycle by reducing greenhouse gas emissions and mitigating climate change impacts. Monitoring forests accurately still remains challenging compared to other ecosystems. We investigated the usability machine learning techniques for estimation AGB plantation at coastal area Hai Phong city (Vietnam). The study employed GIS database support vector regression (SVR) build verify model AGB, drawing upon data from...
Quantifying mangrove soil organic carbon (SOC) is key to better understanding the global cycle, a critical phenomenon in reducing greenhouse gas emissions. However, it challenging have large sample size measurements and analysis due high costs associated with them. In current research, we propose novel hybridized artificial intelligence model based on categorical boosting regression (CBR) particle swarm optimization (PSO) algorithm for feature selection, namely, CBR-PSO estimating SOC. We...
A pixel-based algorithm for multi-temporal Landsat (TM/ETM+/OLI/OLI-2) imagery between 1990 and 2022 monitored mangrove dynamics detected their changes in the three provinces (i.e., Thai Binh, Nam Dinh Hai Phong), which are located on Northern coast of Vietnam, through Google Earth Engine (GEE) cloud computing platform. Results showed that area study decreased from 2960 ha to 2408 1995 then significantly increased 4435 2000 but later declined 3502 2005. The areas experienced an increase 4706...
This study employed Sentinel-1A C-band and Sentinel-2A multispectral data combined with the decision tree ensemble algorithms to map spatial distribution of five mangrove communities in a coastal area North Vietnam. The results show that rotation forests (RoFs) model achieved better overall accuracy kappa coefficient mapping species than those canonical correlation (CCFs) random (RFs) models. research demonstrates potential using optical SAR together machine learning techniques tropical areas.
Multispectral remote sensing images with the advantages of low cost, wide area coverage, and increased resolution have been widely used recently for determining bathymetry coastal waters. In this study, correlation equation is developed based on Landsat 8 OLI satellite captured September 22, 2022, survey data measured during time period 12–22, was mapping in Nhat Le Estuary area, Quang Binh Province, a relatively clear from sediment. The between image field quite good, R2 = 0.88. This shows...