- Landslides and related hazards
- Remote Sensing in Agriculture
- Remote Sensing and LiDAR Applications
- Fire effects on ecosystems
- Geological and Geochemical Analysis
- Advanced Image Fusion Techniques
- Remote Sensing and Land Use
- Cryospheric studies and observations
- Dark Matter and Cosmic Phenomena
- Anomaly Detection Techniques and Applications
- Paleontology and Stratigraphy of Fossils
- Geology and Paleoclimatology Research
- Climate variability and models
- Rock Mechanics and Modeling
- Soil Moisture and Remote Sensing
- Peatlands and Wetlands Ecology
- earthquake and tectonic studies
- Astrophysics and Cosmic Phenomena
- Plant Water Relations and Carbon Dynamics
- Advanced Measurement and Detection Methods
- Geochemistry and Geologic Mapping
- Remote-Sensing Image Classification
- Precipitation Measurement and Analysis
- COVID-19 diagnosis using AI
- Wood and Agarwood Research
China Geological Survey
2025
Shihezi University
2021-2024
China University of Geosciences
2011-2024
China Academy of Space Technology
2024
State Grid Corporation of China (China)
2023-2024
University of Electronic Science and Technology of China
2024
Electric Power Research Institute
2023
Xinjiang Production and Construction Corps
2021-2022
ITRI International
2021
Industrial Technology Research Institute
2021
Recent change detection (CD) methods focus on the extraction of deep semantic features. However, existing overlook fine-grained features and have poor ability to capture long-range space–time information, which leads micro changes missing edges types smoothing. In this paper, a potential transformer-based (SCD) model, Pyramid-SCDFormer is proposed, precisely recognizes small fine details changes. The SCD model selectively merges different tokens in multi-head self-attention block obtain...
Fire omission and commission errors, the accuracy of fire radiative power (FRP) from satellite moderate-resolution impede studies on regimes FRP-based emissions estimation. In this study, we compared between extensively used 1-km product MYD14 Moderate Resolution Imaging Spectroradiometer (MODIS) 375-m VNP14IMG Visible Infrared Radiometer Suite (VIIRS) in Northeastern Asia using data 2012–2017. We extracted almost simultaneous observation detection FRP MODIS-VIIRS overlapping orbits two...
Tree species classification within shelterbelts is crucial for shelterbelt management. The large-scale satellite-based and low-altitude drone-based approaches serve as powerful tools forest monitoring, especially in tree classification. However, these methods face challenges distinguishing individual complex backgrounds. Additionally, the mixed growth of trees protective suffers from similar crown size among different species. background negatively impacts accuracy You Only Look Once (YOLO)...
Automatic recognition of numerous coseismic landslides after a violent earthquake is crucial for emergency rescue and post-disaster reconstruction. Currently, deep learning techniques have achieved state-of-the-art performance in landslide recognition. However, Convolutional Neural Networks (CNNs) often lose detailed information during downsampling cannot adequately learn changeable shapes, colors, sizes landslides. In addition, complicated backgrounds, e.g., bare slopes dry riverbeds, are...
The traditional measurement method (e.g., field survey) of tree diameter circumference often has high labor costs and is time-consuming. Mobile laser scanning (MLS) a powerful tool for measuring forest at breast height (DBH). However, the accuracy point cloud registration seriously affects results DBH measurements. To address this issue, paper proposes new extracting parameters; it achieves purpose efficient accurate extraction by filtering, single-tree instance segmentation, least squares...
Black soil resources are widely distributed in Morin Dawa Daur Autonomous Banner (Moqi), northwest margin of the Songnen Plain, which is an advanced county grain production China and important agricultural producing area east Hulunbuir City, Inner Mongolia. Carrying out research on distribution characteristics source apportionment heavy metals for preventing controlling ecological environmental risks protecting black Plain. A total 161 surface sites were systematically collected from Moqi...
Abstract Melt‐peridotite interaction is the key process causing lithological and mineralogical modification in lithospheric mantle beneath North China Craton (NCC). However, lithology, kinetic, mineral, melt compositional variations of carbonatite melt‐peridotite reaction are poorly constrained relative to those silicate reaction. Here we report Ca‐rich melt‐harzburgite experiments at 3 GPa 1100–1300°C. The experimental results show that proceeds by diffusion‐governed rapid infiltration into...
Near real-time spatial prediction of earthquake-induced landslides (EQILs) can rapidly forecast the occurrence position widespread just after a violent earthquake; thus, EQIL is very crucial to 72-hour 'golden window' for survivors. This work focuses on series earthquake events from 2008 2022 occurring in Tibetan Plateau, famous seismically-active zone, and proposes novel interpretable self-supervised learning (ISeL) method near EQILs. new innovatively introduces swap noise at unsupervised...
Abstract. Geo-anomalies with complex structures in the earth's crust may be defined as preferable hydrothermal ore-forming targets. The separation and explanation of anomaly from geological background have a profound influence on analysis evolution process. Usually one key steps to identify favorable exploration targets is determine threshold separate background. In this paper, singularity theory concentration–area (C–A) fractal method was applied determination geo-anomalies. According...
DEM super resolution is proposed in our previous publication to improve the for a on basis of some learning examples. Meanwhile, nonlocal algorithm introduced deal with it and lots experiments show that strategy feasible. In publication, examples are defined as partial original their related high measurements due this way can avoid incompatibility between data be processed To further extent applications new strategy, should diverse easy obtain. Yet, may cause problem unrobustness. overcome...
In the oasis area adjacent to desert, there is more complex land cover information with rich details, multiscales of interest objects, and blur edge information, which poses some challenges semantic segmentation task in remote sensing images (RSIs). traditional methods, detailed spatial likely lost feature extraction stage global context effectively integrated into results. To overcome these model, FPN_PSA_DLV3+ network, proposed an encoder–decoder manner capturing fine small objects RSIs....
Accurately understanding the stand composition of shelter forests is essential for construction and benefit evaluation forest projects. This study explores classification methods dominant tree species in using UAV-derived RGB, hyperspectral, LiDAR data. It also investigates impact individual crown (ITC) delineation accuracy, morphological parameters, various data sources classifiers. First, as a result overlap complex structure crowns shelterbelt forests, existing ITC often lead to...
To reduce data acquisition cost, this study proposed a novel method of individual tree height estimation and canopy extraction based on fusion an airborne multispectral image photogrammetric point cloud. A fixed‐wing drone was deployed to acquire the true color images shelter forest. The Structure‐from‐Motion (SfM) algorithm used reconstruct 3D cloud canopy. filtered ground then interpolated Digital Elevation Model (DEM) using Radial Basis Function Neural Network (RBFNN). DEM subtracted from...
Abstract In the Three Gorges major landslides are primary disasters, and endanger normal running of Dam life property residents in region. Hence, it is very important to formulate effective strategies for prevention remediation this region, as part which landslide mechanism analysis an task. paper, carried out based on spatial data mining knowledge discovery. The 1:50000 geological map, 1:10000 relief map China–Brazil Earth Resources Satellite (Cbers) images were adopted produce key factors...