- Landslides and related hazards
- Synthetic Aperture Radar (SAR) Applications and Techniques
- Cryospheric studies and observations
- Flood Risk Assessment and Management
- Arctic and Antarctic ice dynamics
- Soil Moisture and Remote Sensing
- Remote-Sensing Image Classification
- Air Quality Monitoring and Forecasting
- Shape Memory Alloy Transformations
- Soil Geostatistics and Mapping
- Advanced Materials and Mechanics
- Advanced Image Fusion Techniques
- Image Enhancement Techniques
- Remote Sensing in Agriculture
- Geophysical Methods and Applications
- Climate change and permafrost
- Aeroelasticity and Vibration Control
- Soft Robotics and Applications
- Soil and Unsaturated Flow
- Winter Sports Injuries and Performance
- Dam Engineering and Safety
- Dielectric materials and actuators
- Optical Systems and Laser Technology
- earthquake and tectonic studies
- Advanced machining processes and optimization
Southwest Jiaotong University
2020-2024
Seoul National University
2010-2013
Previous wildfire risk assessments have problems such as subjectivity of weight allocation and the linearization statistical models, resulting in generally low robustness generalization ability fire assessment models. Therefore, this paper, we explored potential integration machine learning algorithms to build Based on analyzing data’s spatial temporal distribution, selected 10 triggering factors topography, meteorology, vegetation, human activities, using frequency ratio (FR) provide...
Edge optimization of semantic segmentation results is a challenging issue in remote sensing image processing. This article proposes model guided by block-in-block edge detection network named BIBED-Seg. two-stage model, where edges are extracted first and then segmented. We do two key works: The work detection, we present BIBED, network, to extract the accurate boundary features. Here, multiscale feature fusion realized creating residual structure devising multilevel loss function. Second,...
Free and open access to the earth observation synthetic aperture radar (SAR) satellite images has enabled implementation of landslide time-series monitoring. However, with restriction low revisit period satellite, it is difficult meet requirements dynamic monitoring high temporal resolution. Moreover, multiplication SAR platforms, a corresponding data integration algorithm needed obtain complementary displacement information from every single orbit. In this work, an integrated for...
Being built on the reclamation area, Shanghai Pudong International Airport (SPIA) has been undergoing uneven subsidence since beginning of its operation in 1999. In order to explore evolution characteristics ground deformation SPIA area and further provide assurance for airport’s safe operation, 141 Sentinel-1A images from October 2016 September 2021 were selected acquire time-series observations by StaMPS PSI processing procedure. We subsequently a prediction model using Long Short Term...
Clouds seriously limit the application of optical remote sensing images. In this paper, we remove clouds from satellite images using a novel method that considers ground surface reflections and cloud top as linear mixture image elements perspective superposition. We use two-step convolutional neural network to extract transparency information then recover thin regions. Given poor balance generated samples, paper also improves binary Tversky loss function applies it on multi-classification...
Glacial lakes (GLs), a vital link between the hydrosphere and cryosphere, participate in local hydrological process, their interannual dynamic evolution is an objective reflection indicator of regional climate change. The complex terrain climatic conditions mountainous areas where GLs are located make it difficult to employ conventional remote sensing observation means obtain stable, accurate, comprehensive data. In view this situation, study presents algorithm with high generalization...
Shape memory alloy (SMA) wire embedded composites (SMAECs) are widely used as morphing structures in small-size and high-output systems. However, conventional SMAECs cannot keep deformed shapes without additional energy. In this paper, a new kind of smart structure named the woven type soft composite (SSC) beam is introduced, which not only capable morphing, but also maintaining its shape The SSC consists two parts: wires matrix. selected nitinol (Ni–Ti) SMA glass fibers, while matrix part...
The characteristics of active fault movements are essential for estimating the earthquake potential on Tibetan Plateau (TP) in a complex geological setting. 2022 Menyuan Mw6.7 was studied by joint seismological and geodetic methodology to deepen scientific understanding source parameters deformation mechanisms. Firstly, entire InSAR co-seismic field is obtained based ascending descending Sentinel-1A imagery. Subsequently, Bayesian algorithm applied geometry slip distribution determination...
Abstract The use of low earth orbit (LEO) satellites to enhance the performance global navigation satellite system and positioning services has become a popular research topic. In this study, NSGA‐III optimisation algorithm was used design two hybrid configurations 177 186 LEO constellations for enhancing BeiDou Satellite Navigation System (BDS). Under enhanced effect constellation, average geometric dilution precision (GDOP) BDS reduced 0.8 ± 0.1, maximum GDOP from 2.4 less than 1.1 (54.2%...
Monitoring changes in glacial lake (GL) area is of great significance for revealing climate change and analyzing the risk GL outburst floods (GLOFs). However, case Southeastern Tibet Plateau (SETP), availability optical images high mountain areas low, Synthetic Aperture Radar (SAR) amplitude have significant geometric distortions. Most extraction studies are mainly focused on autumn winter seasons. In order to obtain accurate boundaries at any time capture seasonal GLs a wide area, this...
The smart structure is broadly applied in various fields. One of main part actuator. To develop structure, many kinds actuators were studied. Shape Memory Alloy (SMA) one them. SMA actuator demonstrates large deformation and good repeatability, spite hysteresis, it the most generally structure. In this research, a flexible was developed, which comprise spring, Polydimethylsiloxane (PDMS) body Acrylonitrile Butadiene Styrene (ABS) cover. It developed to be robot as manipulator module showing...
This study investigates the effects of glacial lakes on flow velocities Duiya Glacier, southern Tibetan Plateau, by employing satellite Synthetic Aperture Radar (SAR) Pixel-Offset-Tracking Small-Baseline-Subset (PO-SBAS) technology. which terminates in a lake, exhibits approximately 10 m/yr higher horizontal speed and melting rate with vertical Non-Surface-Parallel-Flow (nSPF) velocity – 7 than those its land-terminating counterpart West Duosangpu Glacier. Notably, Glacier experiences...
Clouds are the major source of clutter in optical remote sensing (RS) images. Approximately 60% Earth’s surface is covered by clouds, with equatorial and Tibetan Plateau regions being most affected. Although implementation techniques for cloud removal can significantly improve efficiency imagery, its use severely restricted due to poor timeliness time-series distortion-prone nature single-frame techniques. To thoroughly remove thin clouds from we propose Saliency Cloud Matting Convolutional...