A5019539636- Marine and coastal ecosystems
- Oceanographic and Atmospheric Processes
- Climate variability and models
- Data Management and Algorithms
- Advanced Computational Techniques and Applications
- Geographic Information Systems Studies
- Marine and fisheries research
- Arctic and Antarctic ice dynamics
- Data Mining Algorithms and Applications
- Meteorological Phenomena and Simulations
- Geophysics and Gravity Measurements
- Hydrological Forecasting Using AI
- Tropical and Extratropical Cyclones Research
- Coral and Marine Ecosystems Studies
- Computational Physics and Python Applications
- Remote Sensing and Land Use
- Rough Sets and Fuzzy Logic
- Environmental Changes in China
- Regional Economic and Spatial Analysis
- Coastal and Marine Management
- Oil Spill Detection and Mitigation
- Ocean Waves and Remote Sensing
- Methane Hydrates and Related Phenomena
- Environmental Monitoring and Data Management
- Water Quality Monitoring Technologies
Chinese Academy of Sciences
2015-2025
Aerospace Information Research Institute
2018-2025
Beijing Institute of Big Data Research
2022-2024
University of Chinese Academy of Sciences
2023-2024
Chinese Academy of Meteorological Sciences
2024
Institute of Remote Sensing and Digital Earth
2009-2021
Sanya University
2015-2017
Tsinghua University
2016
Abstract With the rapid development of wireless communication technology, WiFi indoor positioning has become an important method for achieving localization. Achieving high accuracy in is a challenging issue. To enhance systems, this paper proposes algorithm that uses Random Forest (RF) AP selection and Crested Porcupine Optimizer (CPO) to optimize Support Vector Regression (SVR), referred as RF-CPO-SVR. The RF selects APs by evaluating feature importance each AP, reducing negative impact...
Visualization of marine environmental field elements is one the core technologies in science research. Particularly context “digital twin ocean” (DTO) construction and application, accurately reproducing dynamic evolution remains a critical challenge. Existing visualization methods are primarily limited to static displays fail achieve deep integration expression sea conditions. To address this, this paper proposes new method for element fields twin-space framework. This first constructs wave...
We have created a new image analysis pipeline to reprocess images taken by the Near Earth Asteroid Tracking survey and applied it ten nights of observations. This work is first large-scale reprocessing from an asteroid discovery in which thousands archived are re-calibrated, searched for minor planets, resulting observations reported Minor Planet Center. describe software used extract, calibrate, clean sources images, including specific techniques that accommodate unique features these...
Dissolved oxygen (DO) is essential for assessing and monitoring the health of marine ecosystems. The phenomenon ocean deoxygenation widely recognized. Nevertheless, limited availability observations poses a challenge in achieving comprehensive understanding global DO dynamics trends. study addresses unevenly distributed Argo data by developing time–space–depth machine learning (TSD-ML), novel learning-based model designed to enhance reconstruction accuracy data-sparse regions. TSD-ML...
Abstract Oceanic primary production (OPP) is crucial for ecosystem services and global carbon cycle. However, sensitivity to geographic environmental characteristics limits the application of semi‐empirical OPP estimate models, such as vertically generalized productivity model (VGPM) its modified version, particularly in coastal regions. In addition, difficulty collecting necessary parameters also hampers long‐term estimates. Data‐driven machine learning (ML) methods can automatically...
Oceanic dissolved oxygen (DO) is crucial for oceanic material cycles and marine biological activities. However, obtaining subsurface DO values directly from satellite observations limited due to the restricted observed depth. Therefore, it essential develop a connection between surface parameters values. Machine learning (ML) methods can effectively grasp complex relationship input attributes target variables, making them valuable approach estimating based on parameters. In this study,...
Spatiotemporal clustering patterns of marine anomaly variations are the focus much current global climate change research. Marine have multidimensional attributes and spatiotemporally continuous; existing methods for face challenges in mining effectively their spatiotemporal patterns. Using long-term remote sensing products, we present <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">dual-constraint approach</i> (DcSTCA) exploring The DcSTCA...
There exists a sort of dynamic geographic phenomenon in the real world that has property which is maintained from production through development to death. Using traditional storage units, e.g., point, line, and polygon, researchers face great challenges exploring spatial evolution phenomena during their lifespan. Thus, this paper proposes process-oriented two-tier graph model named PoTGM store phenomena. The core ideas are as follows. 1) A abstracted into process with consists sequences...
The northwestern Pacific Ocean (NWPO) is a region sensitive to global climate change and regional sea–air interactions. A number of remote-sensing images from the past three decades were used define marine regions, which then applied determine spatiotemporal association patterns abnormal variations in environmental parameters using quantitative rule-mining method. NWPO object 1 (NWPO-obj1) (130°–150° E, 2°–15° N) 2 (NWPO-obj2) (170°–180° 0°–8° showed more pronounced changes than elsewhere,...
A process-orientated El Niño index (PEI) is constructed to determine the detailed classification of two major types events during 1985–2009 from remote-sensing monthly sea surface temperature (SST) anomaly data sets. Four revised regions are defined in tropical Pacific, and uses SST anomalies their duration each region. Based on varying evolution, allows eastern Pacific (EP) be either weak or strong EP type, central (CP) CP, mixed EPCP type. The identified by this compared those obtained...
Extreme rainstorms have important socioeconomic consequences, but understanding their fine spatial structures and temporal evolution still remains challenging. In order to achieve this, in view of an evolutionary property rainstorms, this paper designs a process-oriented algorithm for identifying tracking named PoAIR. PoAIR uses time-series raster datasets consists three steps. The first step combines accumulated rainfall connectivity identify rainstorm objects at each time snapshot....
Using the long term marine remote sensing imagery, we develop an object-oriented spatial-temporal association rules mining framework to explore among environmental elements. Within framework, two key issues are addressed. They how effectively deal with related lattices and reduce dimensions? To first issues, this paper develops method for abstracting sensitive objects from raster pixels representing them a quadruple. second by embedding mutual information theory, construct direct pattern...
The daily sea surface temperatures (SSTs) derived from the visible and infrared scanning radiometer (VIRR) microwave radiation imager (MWRI) aboard Fengyun-3C (FY-3C) satellite are evaluated against measurements of in-situ SST Reynolds optimum interpolation 0.25° (OISST) products. Statistical results for 2015 reveal a mean bias ± standard deviation error () daytime VIRR SST, night-time MWRI (MWRID), (MWRIN) 0.5877 1.3279°C, −0.4801 1.2588°C, 0.6044 3.9064°C, 0.7653 3.7307°C, respectively....
The northwestern Pacific Ocean is a complex region with significant biological spatial variations on seasonal timescale. To investigate the joint variation patterns both and interannual timescales, season-reliant empirical orthogonal function (S-EOF) analysis was applied to mean chlorophyll-a concentration (chl-a) anomalies in during period 1998–2010. first two dominant modes accounted for nearly 31% of total variance, second S-EOF mode (S-EOF2) lagging behind (S-EOF1) by one year. S-EOF1...
A bias correction method was proposed for correcting the significant negative sea surface temperature (SST) biases in Fengyun-3C (FY-3C) visible and infrared radiometer (VIRR) products. The multichannel SST algorithm (MCSST) daytime night-time of VIRR products are modified estimating debiased SSTs, optimal local matchup data selected each observations based on distance to parts regressors R-space. Compared with probability density function matching technique correction, can better remove...
El Niño–Southern Oscillation (ENSO) and its relationships with marine environmental parameters comprise a very complicated interrelated system. Traditional spatiotemporal techniques face great challenges in dealing which, how, where the different zones help to drive, respond to, ENSO events. Remote sensing products covering 15-year period from 1998 2012 were used quantitatively explore these patterns Pacific Ocean (PO) by prevail quantitative association rule mining algorithm, that is,...
There exists a kind of trajectories dynamic geographic phenomena, which have splitting, merging, or merging-splitting branches. Clustering these complex may help to more deeply explore and analyze the evolution mechanism phenomena. However, few methods clustering patterns such trajectories. Thus, we propose Process-oriented Spatiotemporal Method (PoSCM) for with multiple The PoSCM includes following three parts: first represents "process-sequence-node" structure inspired by process-oriented...