A5100436722- Ocean Waves and Remote Sensing
- Oceanographic and Atmospheric Processes
- Arctic and Antarctic ice dynamics
- Coastal and Marine Dynamics
- Remote-Sensing Image Classification
- Marine and coastal ecosystems
- Synthetic Aperture Radar (SAR) Applications and Techniques
- Soil Moisture and Remote Sensing
- Climate change and permafrost
- Cryospheric studies and observations
- Underwater Acoustics Research
- Remote Sensing and Land Use
- Advanced SAR Imaging Techniques
- Oil Spill Detection and Mitigation
- Maritime Navigation and Safety
- Methane Hydrates and Related Phenomena
- Tropical and Extratropical Cyclones Research
- Radar Systems and Signal Processing
- Advanced Image and Video Retrieval Techniques
- Atmospheric and Environmental Gas Dynamics
- Underwater Vehicles and Communication Systems
- Hydrocarbon exploration and reservoir analysis
- Climate variability and models
- Geological and Geochemical Analysis
- Remote Sensing and LiDAR Applications
Harbin Institute of Technology
2017-2025
First Institute of Oceanography
2015-2024
China University of Petroleum, East China
2017-2024
Ministry of Natural Resources
2013-2024
Shaanxi Normal University
2022-2024
Ministry of Water Resources of the People's Republic of China
2023-2024
Chongqing Normal University
2023-2024
Hong Kong Polytechnic University
2024
Ocean University of China
2015-2023
Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai)
2020-2023
A massive floating green macroalgae bloom (GMB) has occurred for several years consecutively in the Yellow Sea since 2007. In view of rapid growth macroalgae, early detection its patches at first appearance by satellite imagery is importance, and central issue selection appropriate data. As a step towards this goal, based on quasi-synchronous images HJ-1A/B (China Small Satellite Constellation Environment Disaster Monitoring Forecasting) charge-coupled devices (CCDs), Environmental (ENVISAT)...
Selecting discriminate features and constructing an appropriate classifier are two essential factors for ship classification in a synthetic aperture radar (SAR) image. Unfortunately, these rarely considered together by existing studies. We propose joint feature selection method integrating the strategy into wrapper framework. The sequential forward floating searching algorithm is improved to conduct efficient optimal triplet of feature-scaling-classifier. Comprehensive experiments on data...
This work investigates the use of scanning electron microscopy (SEM), low-field nuclear magnetic resonance (NMR) relaxation, and mercury intrusion capillary pressure (MICP) to reveal pore size distribution (PSD) characteristics shales. The comparisons were conducted using six shale samples from Dongying Depression, Bohai Bay Basin, China. results show that SEM can effectively PSD but cannot detect micropores (<100 nm in diameter) smaller than imaging resolution or selected macropores if a...
Background: Fucoxanthin (FX), a xanthophyll pigment which occurs in marine brown algae with remarkable biological properties, has been proven to be safe for consumption by animals. Although FX various pharmacological effects including anti-inflammatory, anti-tumor, anti-obesity, antioxidant, anti-diabetic, anti-malarial, and anti-lipid, vivo protective effect against sepsis not reported. In this study, we aimed at evaluation the efficacy of model mouse. Methods: was successfully isolated...
Marine oil spills are an emergency of great harm and have become a hot topic in marine environmental monitoring research. Optical remote sensing is important means to monitor spills. Clouds, weather, light control the amount available data, which often limit feature characterization using single classifier therefore difficult accurate In this paper, we develop decision fusion algorithm integrate deep learning methods shallow based on multi-scale features for improving spill detection...
Multi-source remote sensing monitoring plays a crucial part in the ecological protection and restoration of coastal wetlands. However, due to inaccessible wetlands environment, lacking labeled samples is challenge wetland classification. In this article, an unsupervised cross-domain feature fusion supervised classification network (UF2SCN) proposed for classification, which fuses hyperspectral image (HSI) light detection ranging (LiDAR) data. First, single branch end developed get HSI LiDAR...
With the development of earth observation technology, hyperspectral image (HSI) and light detection ranging (LiDAR) data collaborative monitoring has shown great potential in ecological protection restoration coastal wetlands. However, due to different working principle adopted by HSI sensor LiDAR sensor, obtained them distribution characteristics. The difference limits fusion data, bringing a challenge for wetland classification. To tackle this problem, multi-source feature embedding...
Sea ice type is one of the most sensitive variables in Arctic monitoring and detailed information about it essential for situation evaluation, vessel navigation, climate prediction. Many machine-learning methods including deep learning can be employed ice-type detection, classifiers tend to prefer different feature combinations. In order find optimal classifier-feature assembly (OCF) sea classification, necessary assess their performance differences. The objective this letter make a...
The Cosmic-Ray Neutron Sensor (CRNS) technique for estimating landscape average soil water content (SWC) is now a decade old and includes many practical methods implementing measurements, such as identification of detection area depth, installation, calibration, validation. However, in order to maximize the societal relevance CRNS SWC data, value-added products need be developed that can estimate both flux (i.e. rainfall, deep percolation, evapotranspiration) root zone storage changes. In...
Storm surge is the most severe marine disaster in China, affecting whole coastal area. Estimating storm loss (SSDL) significant to prevention, sustainability and decision-making. Taking 11 provincial administrative regions areas of China as study area, this paper estimated SSDL grades based on four machine learning (ML) algorithms. A total 132 pieces official open-source data disasters were collected divided into a cross-validation set (CV set) test set. First, comprehensive indicator system...
Federated learning has become a popular method to learn from decentralized heterogeneous data. semi-supervised (FSSL) emerges train models small fraction of labeled data due label scarcity on clients. Existing FSSL methods assume independent and identically distributed (IID) across clients consistent class distribution between unlabeled within client. This work studies more practical challenging scenario FSSL, where is different not only but also client To address this challenge, we propose...
Abstract. This study investigated the statistics of eddy splitting and merging in global oceans based on 23 years altimetry data. Multicore structures were identified using an improved geometric closed-contour algorithm sea surface height. Splitting events discerned from continuous time series maps level anomalies. represent intermediate stage process evolution, similar to generation multiple nuclei a cell as preparatory phase for division. Generally, or can substantially change (by factor 2...
Ren, G.-B.; Wang, J.-J.; A.-D.; J.-B.; Zhu, Y.-L.; Wu, P.-Q.; Ma, Y., and Zhang, J.B., 2019. Monitoring the invasion of smooth cordgrass Spartina alterniflora within modern Yellow River Delta using remote sensing. In: Jung, H.-S.; Lee, S., Ryu, J.-H. (eds.), Advances in Remote Sensing Geoscience Information Systems Coastal Environments. Journal Research, Special Issue No. 90, pp. 135-145. Coconut Creek (Florida), ISSN 0749-0208.The Smooth Cordgrass, alterniflora, was introduced into 1989 to...
In recent years, concern has increased about the depletion of marine resources caused by overexploitation fisheries and degradation ecosystems. The Automatic Identification System (AIS) is a powerful tool increasingly used for monitoring fishing activity. this paper, identification type vessel (trawlers, gillnetters seiners) was carried out using 150 million AIS tracking points in April, June September 2018 northern South China Sea (SCS). vessels’ spatial temporal distribution, duration time...
With the improvement in microwave radar technology, spaceborne synthetic aperture (SAR) is widely used to observe tropical cyclone (TC) wind field. Based on European Space Agency Sentinel-1 Interferometric Wide swath (IW) mode imagery, this paper evaluates correlation between vertical transmitting–horizontal receiving (VH) polarization signals and extreme ocean surface speeds (>40 m/s) under strong TC conditions. A geophysical model function (GMF) IW retrieval after noise removal...
Chlorophyll a concentration and suspended matter concentration, as typical water quality parameters related to spectral characteristics, are essential for characterizing the degree of eutrophication in bodies. They have become crucial indicators assessment inland The support vector regression model (SVR) is suitable small samples, has excellent generalization ability, high prediction accuracy. Still, it problem difficult selection quickly falling into local extremes. To solve this problem,...
Remote sensing monitoring of oil spills is essential for ecological and environmental management. Polarimetric synthetic aperture radar (PolSAR) data have been extensively utilized spill detection owing to the advantages multi-polarization channels all-time, all-weather observation capability. However, suspected phenomenon (algal blooms or wave shadows) wind-caused drifting can lead variable textures irregular boundaries coverage. These increase complexity scenes pose challenges PolSAR...