A5077295889- Cryospheric studies and observations
- Climate change and permafrost
- Medical Image Segmentation Techniques
- Remote Sensing and Land Use
- Hydrology and Watershed Management Studies
- Hydrological Forecasting Using AI
- Advanced Image Fusion Techniques
- Flood Risk Assessment and Management
- Remote Sensing and LiDAR Applications
- Meteorological Phenomena and Simulations
- Remote Sensing in Agriculture
- Scientific Computing and Data Management
- Advanced Computational Techniques and Applications
- Remote-Sensing Image Classification
- Image and Object Detection Techniques
- Landslides and related hazards
- Climate variability and models
- Arctic and Antarctic ice dynamics
- Ultrasound Imaging and Elastography
- Spectroscopy and Chemometric Analyses
- Medical Imaging Techniques and Applications
- Advanced MRI Techniques and Applications
- Advanced Image and Video Retrieval Techniques
- Distributed and Parallel Computing Systems
- Elasticity and Material Modeling
Chinese Academy of Sciences
2016-2025
Northwest Institute of Eco-Environment and Resources
2017-2025
University of Chinese Academy of Sciences
2019-2025
Beijing Microelectronics Technology Institute
2024
Chinese Academy of Medical Sciences & Peking Union Medical College
2024
Gansu Desert Control Research Institute
2022
Lanzhou University
2022
Hebei University of Technology
2021
Northeastern University
2010-2021
National Health and Family Planning Commission
2021
The application of remote sensing technology in grassland monitoring and management has been ongoing for decades. Compared with traditional ground measurements, the overall advantage convenience, efficiency, cost effectiveness, especially over large areas. This paper provides a comprehensive review latest estimation methods some critical parameters, including above-ground biomass, primary productivity, fractional vegetation cover, leaf area index. Then, applications are also reviewed from...
Non-lethal macular diseases greatly impact patients' life quality, and will cause vision loss at the late stages.Visual inspection of optical coherence tomography (OCT) images by experienced clinicians is main diagnosis technique.We proposed a computer-aided (CAD) model to discriminate age-related degeneration (AMD), diabetic edema (DME) healthy macula.The linear configuration pattern (LCP) based features OCT were screened Correlation-based Feature Subset (CFS) selection algorithm.And best...
Abstract. Permafrost over the Qinghai–Tibet Plateau (QTP) has received increasing attention due to its high sensitivity climate change. Numerous spatial modeling studies have been conducted on QTP assess status of permafrost, project future changes in and diagnose contributors permafrost degradation. Due scarcity ground stations QTP, these are often hampered by lack validation references, calibration targets, model constraints; however, a high-quality distribution map would be good option as...
In recent years, deep learning methods utilizing convolutional neural networks have been extensively employed in hyperspectral image classification (HSI) applications. Nevertheless, while a substantial number of stacked 3D convolutions can indeed achieve high accuracy, they also introduce significant parameters to the model, resulting inefficiency. Furthermore, such intricate models often exhibit limited accuracy when confronted with restricted sample data, i.e., small problems. Therefore,...
Lake water body extraction from remote sensing images is a key technique for spatial geographic analysis. It plays an important role in the prevention of natural disasters, resource utilization, and quality monitoring. Inspired by recent years research computer vision on fully convolutional neural networks (FCN), end-to-end trainable model named multi-scale lake network (MSLWENet) proposed. We use ResNet-101 with depthwise separable convolution as encoder to obtain high-level feature...
Abstract Spin‐up is essential to provide initial conditions for land surface models (LSM) when they cannot be given reliably as in the application regional permafrost change studies. In this study, impacts of spin‐up strategy including total length and cycling scheme on modeling dynamics Qinghai‐Tibet Plateau (QTP) were evaluated through two groups experiments using a modified Noah LSM. The first group aims test different lengths second schemes. results show that presence prolongs...
Abstract. Multi-temporal glacier inventories provide key information about the glaciers, their characteristics, and changes are inevitable for modelling investigating geodetic mass changes. However, to date, no consistent multi-temporal inventory whole of Karakoram exists, negatively affecting monitoring spatio-temporal variations in glaciers' geometric parameters related applications. We used a semi-automatic method combining automatic segmentation manual correction produced (KGI) compiled...
Networks are a popular tool for representing elements in system and their interconnectedness. Many observed networks can be viewed as only samples of some true underlying network. Such is frequently the case, example, monitoring study massive, online social networks. We problem how to estimate degree distribution—an object fundamental interest—of network from its sampled In particular, we show that this formulated an inverse problem. Playing key role formulation matrix relating expectation...
As an image-segmentation method based on graph theory, GrabCut has attracted more and researchers to pay attention this new because of its advantages simple operation excellent segmentation. In order clarify the research status GrabCut, we begin with original model, review improved algorithms that are or important in recent years, classify them terms pre-processing superpixel, saliency map, energy function modification, non-interactive improvement some other algorithms. The application...
Advances in methodologies and tools often lead to new insights into cardiovascular diseases. Intravascular ultrasound (IVUS) is a well-established diagnostic method that provides high-resolution images of the vessel wall atherosclerotic plaques. High-frequency (>50 MHz) enables spatial resolution IVUS approach optical imaging methods. However, penetration depth decreases when using higher frequencies due greater acoustic attenuation. An improves would, therefore, be major clinical...
Most previous studies of the Qinghai-Tibet engineering corridor (QTEC) have focused on impacts climate change thaw-induced slope failures, whereas few considered freeze-induced failures. Terrestrial laser scanning was used in combination with global navigation satellite systems to monitor three-dimensional surface changes between 2014 and 2015 permafrost QTEC, which experienced two thawing periods a freezing period. Soil temperature moisture sensors were also deployed at 11 depths reveal...
Plant recognition recently becomes more and attractive in computer vision pattern recognition. Although some researchers have proposed several methods, their accuracy is not satisfactory. Therefore, a novel method of plant based on leaf image the paper. Both shape texture features are employed Texture feature extracted by intersecting cortical model, obtained representation center distance sequence. Support vector machine for classifier. The preprocessed to get better quality extracting...
Merging satellite and rain gauge data by combining accurate quantitative rainfall from stations with spatial continuous information remote sensing observations provides a practical method of estimating rainfall. However, generating high spatiotemporal fields for catchment-distributed hydrological modeling is problem when only sparse network coarse resolution are available. The objective the study to present data-merging framework adapting data-sparse designs. In framework, statistical...
Desertification seriously hinders economic development and ecological security, which has led to increased research on desertification monitoring control. Remote sensing technology is widely used in desert due its large detection range ability obtain target feature information without touching objects. In order better monitor control desertification, the methods mobility dune morphology mobile deserts were reviewed. Among them, an important index distinguish nonmobile vegetation coverage....
Soil temperature (ST) plays a key role in the processes and functions of almost all ecosystems, is also an essential parameter for various applications such as agricultural production, geothermal development, their utilization. Although numerous machine learning models have been used prediction ST, good results obtained, most current studies focused on daily or monthly ST predictions, while hourly predictions are scarce. This paper presents novel scheme forecasting using weather forecast...
Plants are ubiquitous in human life. Recognizing an unknown plant by its leaf image quickly is a very interesting and challenging research. With the development of processing pattern recognition, recognition based on has become possible. Bag features (BOF) one most powerful models for classification, which been used many projects studies. Dual-output pulse-coupled neural network (DPCNN) shown good ability texture such as segmentation. In this paper, method BOF DPCNN (BOF_DP) proposed...