A5026572747- Synthetic Aperture Radar (SAR) Applications and Techniques
- Cryospheric studies and observations
- Landslides and related hazards
- Advanced SAR Imaging Techniques
- Remote Sensing and Land Use
- Soil Moisture and Remote Sensing
- Groundwater and Watershed Analysis
- Flood Risk Assessment and Management
- Geophysical Methods and Applications
- Geophysics and Gravity Measurements
- Climate change and permafrost
- Remote-Sensing Image Classification
- Remote Sensing and LiDAR Applications
- Structural Health Monitoring Techniques
- Anomaly Detection Techniques and Applications
- Rock Mechanics and Modeling
- Automated Road and Building Extraction
- Image Processing Techniques and Applications
- Remote Sensing in Agriculture
- Advanced Algorithms and Applications
- Arctic and Antarctic ice dynamics
- Tree Root and Stability Studies
- Geoscience and Mining Technology
- Infrared Target Detection Methodologies
- Geomechanics and Mining Engineering
China Geological Survey
2012-2025
China Centre for Resources Satellite Data and Application
2023-2025
Nanjing University of Posts and Telecommunications
2025
Kyrgyz National University
2025
Ministry of Natural Resources
2021-2024
China Mobile (China)
2023
Naval Postgraduate School
2006-2013
China University of Geosciences (Beijing)
2007-2011
China University of Mining and Technology
2005
Landslide disasters occur frequently in the mountainous areas southwest China, which pose serious threats to local residents. Interferometry Synthetic Aperture Radar (InSAR) provides us ability identify active slopes as potential landslides vast areas, help prevent and mitigate disasters. Quickly accurately identifying based on massive SAR data is of great significance. Taking national highway near Wenchuan County, study area, this paper used a Stacking-InSAR method quickly qualitatively...
China has a significant portion of land in landslide-prone areas, and remote sensing technologies are becoming tool choice to investigate monitor landslides. Although much progress been made with their applications China, there is no systematical summary report. Thus, we summarize Synthetic Aperture Radar (SAR), optical sensing, laser currently being used associated platforms (space-borne, air-borne, ground-based). Multi-temporal images time series SAR often detect active landslides at...
Extracting roads from high-resolution remote sensing images (HRSIs) is vital in a wide variety of applications, such as autonomous driving, path planning, and road navigation. Due to the long thin shape well shades induced by vegetation buildings, small-sized are more difficult discern. In order improve reliability accuracy extraction when multiple sizes coexist an HRSI, enhanced deep neural network model termed Dual-Decoder-U-Net (DDU-Net) proposed this paper. Motivated U-Net model, small...
Landslides are one of the most serious natural hazards along Sichuan-Tibet transportation corridor, which crosses complicated region in world terms topography and geology. Landslide susceptibility mapping (LSM) is high demand for risk assessment disaster reduction this mountainous region. A new model, namely Convolutional-Squeeze Excitation-long short-term memory network (Conv-SE-LSTM), proposed to map landslide corridor. Compared with conventional deep learning models, Conv-SE-LSTM...
Landslide is one of the most dangerous and frequently occurred natural disasters. The semantic segmentation technique efficient for wide area landslide identification from high-resolution remote sensing images (HRSIs). However, considerable challenges exist because effects sediments, vegetation, human activities over long periods time make visually blurred old landslides very challenging to detect based upon HRSIs. Moreover, terrain features like slopes, aspect altitude variations cannot be...
Landslides, a major natural geohazard, obstruct municipal constructions and may destroy villages towns, at worst causing significant casualties economic losses. Interferometric Synthetic Aperture Radar (InSAR) technique offers distinct advantages on landslide detection monitoring. In this paper, more systematic workflow is designed for InSAR study of landslides, in terms three levels: (i) early regional scale, (ii) three-dimensional (3D) surface displacement rates estimation detailed (iii)...
Landslides are a major geohazard that endangers human lives and properties. Recently, efforts have been made to use Synthetic Aperture Radar Interferometry (InSAR) for landslide monitoring. However, it is still difficult effectively automatically identify slow-moving landslides distributed over large area due phase unwrapping errors, decorrelation, troposphere turbulence computational requirements. In this study, we develop new approach combining phase-gradient stacking deep-learning network...
This article proposes deep convolutional neural networks to detect and map localized, rapid subsidence caused by mining activities using time-series Sentinel-1 synthetic aperture radar (SAR) images. A deformation detection network (DDNet) is developed automatically identify rapidly subsiding areas from wrapped interferograms, a phase unwrapping (PUNet) designed unwrap the cropped interferogram patches centered on detected locations. To train two networks, simulation strategies are generate...
Lakes are an important component of global water resources. In order to achieve accurate lake extractions on a large scale, this study takes the Tibetan Plateau as area and proposes Automated Lake Extraction Workflow (ALEW) based Google Earth Engine (GEE) deep learning in response problems low identification accuracy efficiency complex situations. It involves pre-processing massive images creating database examples extraction Plateau. A lightweight convolutional neural network named...
The geological characteristics of old landslides can provide crucial information for the task landslide protection. However, detecting from high-resolution remote sensing images (HRSIs) is great challenges due to their partially or strongly transformed morphology over a long time and thus limited difference with surroundings. Additionally, small-sized datasets restrict in-depth learning. To address these challenges, this paper proposes new iterative classification semantic segmentation...
Phase unwrapping is a critical step of interferometric synthetic aperture radar processing, and its accuracy directly determines the reliability subsequent applications. Many phase methods have been proposed, most which assume that has spatial continuity, while decorrelation noise aliasing fringes invalidate assumptions, resulting in poor performance these methods. To obtain more reliable results, this article, deep convolutional neural network, called discontinuity estimation network...
<title>Abstract</title> Undersampled magnetic resonance imaging (MRI) reconstruction aims to minimize scanning time while maintaining optimal image quality, enhancing patient comfort and clinical efficiency. Currently, parallel strategies in both k-space domains effectively utilize dual-domain information enhance feature capture accuracy. However, most existing fusion methods primarily straightforward techniques, such as weighted cascade processing, neglecting differences spatial features...
Since 2017, many serious geological disasters have been reported, including the 2017 mountain collapse at high altitudes in Xinmo Village Mao County, Sichuan Province, and 2018 Baige landslide Jinsha River, most of which are great destructive power hard to detect advance. It is worth noting that although geohazard prevention has carried out extensively across whole country supported by state, these occur outside potential points estimated The early identification undetectable geohazards...
Early discovery and monitoring of the active deformation areas potential landslides are important for geohazard risk prevention. The objective study is to propose a one-step strategy automatically mapping from Sentinel-1 SAR dataset. First, we built generalized convolutional neural network (CNN) based on activity topographic characteristics. Second, conducted comparative analysis performance various multi-channel combiners detecting landslides. Third, verified transferability pretrained CNN...