A5103227976- Remote Sensing and Land Use
- Remote Sensing in Agriculture
- Remote Sensing and LiDAR Applications
- Cryospheric studies and observations
- Landslides and related hazards
- Robotics and Sensor-Based Localization
- Synthetic Aperture Radar (SAR) Applications and Techniques
- Atmospheric and Environmental Gas Dynamics
- Precipitation Measurement and Analysis
- Advanced Computational Techniques and Applications
- Topic Modeling
- Meteorological Phenomena and Simulations
- Geographic Information Systems Studies
- Automated Road and Building Extraction
- Soil Moisture and Remote Sensing
- Land Use and Ecosystem Services
- Geological Modeling and Analysis
- Hydrology and Watershed Management Studies
- Disaster Management and Resilience
- 3D Surveying and Cultural Heritage
- CO2 Sequestration and Geologic Interactions
- Climate variability and models
- 3D Modeling in Geospatial Applications
- Groundwater and Watershed Analysis
- Remote-Sensing Image Classification
Aerospace Information Research Institute
2022-2025
Chinese Academy of Sciences
2014-2025
Institute of Remote Sensing and Digital Earth
2013-2017
State Key Laboratory of Remote Sensing Science
2009
Characterizing the errors in satellite-based precipitation estimation products is crucial for understanding their effects hydrological applications. Six derived from three algorithms are comprehensively evaluated against gauge data over mainland China December 2006 to November 2010. These include satellite-only estimates: Global Satellite Mapping of Precipitation Microwave-IR Combined Product (GSMaP_MVK), Climate Prediction Center (CPC) MORPHing (CMORPH), and Estimation Remotely Sensed...
As with the fast advances in technologies of big Earth data and information communication, Web-based 3D GIS system has come a long way from few years ago. These reflect many aspects such as higher real-time performance, enhanced interactivity, more realistic visualization effect improved user interface. This paper aims to present comprehensive up-to-date Web for Emergency Response using current vue.js web application framework well-known Cesium API, taking landslide disaster an example....
The precise prevention and control of forest pests diseases has always been a research hotspot in ecological environmental protection. With the continuous advancement sensor technology, fine-grained identification discolored tree crowns based on UAV technology become increasingly important monitoring. Existing deep learning models face challenges such as prolonged training time low recognition accuracy when identifying caused by or from airborne images. To address these issues, this study...
Drought is a critical hydrological challenge with ecological and socio-economic impacts, but its long-term variability drivers remain insufficiently understood. This study proposes deep learning-based framework to explore drought dynamics their underlying across China’s major basins over the past four decades. The Long Short-Term Memory network was employed reconstruct gaps in satellite-derived soil moisture (SM) datasets, achieving high accuracy (R2 = 0.928 RMSE 0.020 m3m−3). An advanced...
With the launch of ICESat-2 satellite, global-scale forest parameter monitoring has entered a new phase. However, background noise in lidar data significantly impairs accuracy signal photon extraction. This study introduces direction-adaptive DBSCAN method for denoising point clouds, integrating elevation histogram-based coarse with adaptive clustering fine denoising. The is applied to from Gongbella River Nature Reserve. An innovative aspect this approach introduction elliptical tilt angle...
Single tree detection is essential in forest resource surveys. Efficient, accurate, and rapid extraction of individual trees facilitates the timely acquisition information. Traditional surveys rely on manual field measurements, which are limited coverage, costly, time-consuming. To address these issues, this study utilizes multispectral imagery captured by unmanned aerial vehicles (UAVs) as data foundation applies deep learning methods for species segmentation area. An enhanced ECA-Unet...
Rainstorm disasters have wide-ranging impacts on communities, but traditional information collection methods are often hampered by high labor costs and limited coverage. Social media platforms such as Weibo provide new opportunities for monitoring analyzing disaster-related in real-time. In this paper, we present ETEN_BERT_QA, a novel model extracting event arguments from rainstorm disaster texts. The incorporates the text enhancement network (ETEN) to enhance extraction process improving...
The high spatial-temporal variability of soil moisture necessitates monitoring at a resolution in order to improve our understanding Earth system processes. Current large-scale moistures inferred from the microwave satellites have limited spatial resolution, typically range tens kilometers. Recent studies revealed that synthetic aperture radar (SAR) backscatter exhibits qualitative relationships with moisture, suggesting potential for high-resolution mapping moisture. Here, we proposed...
Land subsidence has become a challenging problem with urbanization and underground exploitation. The land in Wuhan, China, was inferred from 47 Sentinel-1A images acquired between June 2015 to October 2020 based on Synthetic Aperture Radar (SAR) Interferometric Point Target Analysis (IPTA) technology. Results show that significant mainly occurred Houhu, Qinshan, Baishazhou, Zhuankou areas, the most reaching an annual rate of 41.0 mm/a accumulated 219.4 mm., more carbonate solution zone...
With the deepening use of public information resources in smart cities, platforms have been paid more attention as basic support platform for intelligent city application. At present, new urbanization construction is full swing China. Fine security management communities has become core urbanization. Smart community needs to integrate Internet Things (IOT), Mobile and other technologies seamlessly manage indoor outdoor data. In this paper, development technical framework Public Information...
Inverting grassland above-ground biomass (AGB) presents a significant challenge due to difficulties in characterizing leaf physiological states and obtaining accurate ground-truth data. This study introduces an innovative hybrid model for AGB inversion based on the = mass per area (LMA) * index (LAI) paradigmn Ewenki Banner region of Inner Mongolia. The integrates PROSAIL radiative transfer model, machine learning regression, LEnKF data assimilation theory, multisource remote sensing,...
As the demand for spatial positioning continues to grow, methods based on inertial measurement units (IMUs) are emerging as a promising research topic due their low cost and robustness against environmental interference. These particularly well suited global navigation satellite system (GNSS)-denied environments challenging visual scenarios. While existing algorithms position estimation using IMUs have demonstrated some effectiveness, there is still significant room improvement in terms of...
Visual geo-localization using prior map of known environments has extensive applications in the fields such as self-driving, augmented reality and navigation. Currently, maps are usually constructed by visual SLAM or SFM. However, recent advances LiDAR technology with RGB camera demonstrate great potential efficient accurate construction geo-localization. In this research, we developed a novel approach which seamlessly integrates handheld system, global localization algorithm sparse set...
Monitoring the dynamic distribution of irrigated cropland and assessing its cooling effects are essential for advancing sustainable agriculture amid climate change. This study presents an integrated framework monitoring effect assessment. Leveraging dense time series vegetation indices with Google Earth Engine (GEE), we evaluated multiple machine learning algorithms within to identify most robust approach (random forest algorithm) mapping in Inner Mongolia from 2010 2020. Furthermore,...
The difference and the complementarity on agriculture decides that there is a wide-ranging cooperation between China GMS. So research GMS's has important significance. objective of this to produce phenology-based classification map for crop in GMS by investigating spatial temporal patterns multiple cropping systems. Although resolution MODIS-NDVI data not very high, it still useful detecting large-scale phenomenon. In paper 16-day time-series MODIS from 2001 2015 were used exploer...
The remote sensing data have become the irreplaceable source of for regions with little or without rainfall data, but these also require scientific analysis, correction and application. This paper uses FY-2 case studies droughts occurred in Weihe River Basin from 2006 to 2009 monitor spatial temporal evolution climatic droughts. monitoring results indicate that: (1) Except 2008 which was a dry year, other years had normal dry/wet conditions; (2) From October January 2009, significantly...
Coverage rates of vegetation and exposed bedrock are two key indicators karst rocky desertification (KRD) envionmnents. Based on spectral unmixing algorithm, abundance rock were retrieved from the hyperspectral Hyperion image. They verified by indices Karst (SIRD) chlorophyll index. It showed that had significant linear correlation with SIRD. The determinate coefficients (R<sup>2</sup>) 0.93,0.66, 0.84 for vegetation, soil respectively, indicating abundances can characterize their coverage...