A5101742037- Remote Sensing in Agriculture
- Remote-Sensing Image Classification
- Remote Sensing and Land Use
- Land Use and Ecosystem Services
- Advanced Image Fusion Techniques
- Remote Sensing and LiDAR Applications
- Geophysical Methods and Applications
- Urban Heat Island Mitigation
- Soil Moisture and Remote Sensing
- Species Distribution and Climate Change
- Impact of Light on Environment and Health
- Spectroscopy and Chemometric Analyses
- Environmental Changes in China
- Plant Water Relations and Carbon Dynamics
- Landslides and related hazards
- Geochemistry and Geologic Mapping
- Microwave Imaging and Scattering Analysis
- Ecology and Vegetation Dynamics Studies
- Cryospheric studies and observations
- Advanced Image and Video Retrieval Techniques
- Leaf Properties and Growth Measurement
- Rangeland Management and Livestock Ecology
- Machine Learning and Data Classification
- Image and Object Detection Techniques
- Advanced Neural Network Applications
State Key Laboratory of Remote Sensing Science
2010-2025
Beijing Normal University
2016-2025
China University of Mining and Technology
2025
Aerospace Information Research Institute
2022-2023
Chinese Academy of Sciences
2023
Southwest Jiaotong University
2021
National Earthquake Response Support Service
2019-2020
China Industrial Control Systems Cyber Emergency Response Team
2019-2020
Zhaoqing University
2017-2020
State Key Laboratory of Earth Surface Processes and Resource Ecology
2019
Global Land Cover (GLC) information is fundamental for environmental change studies, land resource management, sustainable development, and many other societal benefits. Although GLC data exists at spatial resolutions of 300 m 1000 m, a 30 resolution mapping approach now feasible option the next generation products. Since most significant human impacts on system can be captured this scale, number researchers are focusing such This paper reports operational used in project, which aims to...
Deep learning techniques have boosted the performance of hyperspectral image (HSI) classification. In particular, convolutional neural networks (CNNs) shown superior to that conventional machine algorithms. Recently, a novel type called capsule (CapsNets) was presented improve most advanced CNNs. this paper, we present modified two-layer CapsNet with limited training samples for HSI classification, which is inspired by comparability and simplicity shallower deep models. The trained using two...
This study compared five widely used globally gridded biomass burning emissions inventories for the 2002-2011 period (Global Fire Emissions Database 3 (GFED3), Global 4 (GFED4), Assimilation System 1.0 (GFAS1.0), INventory from NCAR (FINN1.0) and Inventory Chemistry-Climate studies-GFED4 (G-G)). Average annual CO2 range 6521.3 to 9661.5 Tg year(-1) inventories, with extensive amounts in Africa, South America Southeast Asia. Coefficient of Variation Southern America, Northern Africa are 30%,...
Spatiotemporal data fusion, as a feasible and low-cost solution for producing time-series satellite images with both high spatial temporal resolution, has undergone rapid development over the past two decades more than one hundred spatiotemporal fusion methods developed. Accuracy assessment of fused is crucial users to select appropriate real-world applications. However, commonly used metrics do not comprehensively cover multiple aspects image quality, contain redundant information, are...
The diameter of roots is pivotal for studying subsurface root structure geometry. Yet, directly obtaining these parameters challenging due their hidden nature. Ground-penetrating radar (GPR) offers a reproducible, nondestructive method detection, but estimating from B-Scan images remains challenging. To address this, we developed the CycleGAN-guided multi-task neural network (CMT-Net). It comprises two subnetworks, YOLOv4-Hyperbolic Position and Diameter (YOLOv4-HPD) CycleGAN. YOLOv4-HPD...
Postclassification comparison (PCC) and change vector analysis (CVA) have been widely used for land use/cover detection using remotely sensed data. However, PCC suffers from error cumulation stemmed an individual image classification error, while a strict requirement of radiometric consistency in data is bottleneck CVA. This letter proposes new method named CVA posterior probability space (CVAPS), which analyzes the by The CVAPS approach was applied validated case study cover Shunyi...
In the past decades, spectral unmixing has been studied for deriving fractions of spectrally pure materials in a mixed pixel. However, limited attention given to collinearity problem mixture analysis. this paper, quantitative analysis and detailed simulations are provided, which show that high correlation between endmembers, including virtual endmembers introduced nonlinear model, strong impact on errors through inflating Gaussian noise. While distinctive spectra with low correlations often...
Abstract Climate warming on the Tibetan Plateau tends to induce an uphill shift of temperature isolines. Observations and process‐based models have both shown that climate has resulted in increase vegetation greenness recent decades. However, it is unclear whether isolines caused upward two shifts match each other. Our analysis satellite observed during growing season (May–Sep) gridded data for 2000–2016 documented a substantial mismatch between elevational This probably associated with...
As a nondestructive geophysical tool, Ground penetrating radar (GPR) has been applied in tree root study recent years. With increasing amounts of GPR data collected for roots, it is imperative to develop an efficient automatic recognition roots images. However, few works have completed on this topic because the complexity problem. Based datasets from both controlled and situ experiments, randomized Hough transform (RHT) algorithm was evaluated object different center frequencies (400 MHz,...
Accurate mapping of winter wheat over a large area is great significance for guiding policy formulation related to food security, farmland management, and the international trade. Due complex phenological features wheat, cloud contamination in time-series imagery, influence soil/snow background on vegetation indices, there remains no effective method at medium spatial resolution (10–30 m). In this study, we proposed novel called phenology-time weighted dynamic time warping (PT-DTW)...
Abstract Climate warming has delayed the end of growing season (EOS) in temperate and cold ecosystems. However, it is unclear whether asymmetric (higher at night than during day) triggered different responses timing EOS. Here we used satellite‐observed EOS alpine vegetation to reveal its nighttime daytime on Tibetan Plateau. Increased preseason minimum temperature could postpone by 7.92 day K −1 ( P < 0.01), probably slowing low‐temperature induced leaf senescence, whereas increased...
Most previous haze/cloud detection methods for Landsat imagery, e.g., haze optimized transformation (HOT), cannot adequately suppress land surface information and, in particular, often overestimate thickness over bright surfaces. This paper proposes an iterative HOT (IHOT) improving with the help of a corresponding clear image. With procedure regressions among HOT, reflectance difference at top atmosphere (TOA) between hazy and images, TOA reflectances can be removed, result is derived to...
High spatiotemporal resolution normalized difference vegetation index (NDVI) time-series imagery is required for monitoring dynamics with dense observations and spatial details, in recent years, many data fusion methods have been proposed to fulfill this need. However, strict requirements inappropriate modeling strategies often limit their performance, particularly under poor conditions of available input data. In study, we a Spatiotemporal method Simultaneously generate Full-length Index...
Remote sensing of nighttime light can observe the artificial lights at night on planet's surface. The Defense Meteorological Satellite Program's Operational Line Scan (DMSP-OLS) data (1992-2013) provide planet-scale over a long-time span and have been widely used in areas such as urbanization monitoring, socio-economic parameters estimation, disaster assessment. However, due to lack an on-board calibration system, sensor design defects, limited detection range, inadequate quantization...