A5015410049- Hydrology and Watershed Management Studies
- Complex Network Analysis Techniques
- Flood Risk Assessment and Management
- Hydrological Forecasting Using AI
- Data Stream Mining Techniques
- Time Series Analysis and Forecasting
- Advanced Clustering Algorithms Research
- Advanced Neuroimaging Techniques and Applications
- Text and Document Classification Technologies
- Functional Brain Connectivity Studies
- Opinion Dynamics and Social Influence
- Precipitation Measurement and Analysis
- Advanced MRI Techniques and Applications
- Domain Adaptation and Few-Shot Learning
- Face and Expression Recognition
- Cryospheric studies and observations
- Human Mobility and Location-Based Analysis
- Machine Learning and Data Classification
- Climate variability and models
- Peer-to-Peer Network Technologies
- Land Use and Ecosystem Services
- Anomaly Detection Techniques and Applications
- Complex Systems and Time Series Analysis
- Hydrology and Drought Analysis
- Data Management and Algorithms
University of Electronic Science and Technology of China
2015-2024
Huzhou University
2021-2023
Shandong Academy of Forestry
2022
State Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering
2018-2019
Nanjing Hydraulic Research Institute
2018-2019
Technical University of Munich
2017
University of Edinburgh
2008-2013
Institut für Urheber- und Medienrecht
2013
Ludwig-Maximilians-Universität München
2012
University of Salford
2012
The Source Region of the Yellow River Basin (SRYRB), China To improve daily runoff prediction accuracy in data-scarce areas, this study focuses on incorporating multiple grid-based data (precipitation, EVI, soil moisture (SM)) to drive CNN-LSTM hybrid model. spatial features precipitation and underlying surface basin can be extracted by CNN, while temporal input series captured LSTM. model is compared with single models (CNN, LSTM), performances under different driven are also investigated....
In this paper, we introduce a new community detection algorithm, called Attractor, which automatically spots communities in network by examining the changes of "distances" among nodes (i.e. distance dynamics). The fundamental idea is to envision target as an adaptive dynamical system, where each node interacts with its neighbors. interaction will change distances nodes, while affect interactions. Such interplay eventually leads steady distribution distances, sharing same move together and...
Runoff prediction is of great significance to flood defense. However, due the complexity and randomness runoff process, it hard predict daily accurately, especially for peak runoff. To address this issue, study proposes an enhanced long short-term memory (LSTM) model prediction, where novel loss functions are introduced feature extractors integrated. Two (peak error tanh (PET), swish (PES)) designed strengthen importance runoff's while weakening weight normal prediction. The extractor...
Synchronization is a powerful basic concept in nature regulating large variety of complex processes ranging from the metabolism cell to social behavior groups individuals. Therefore, synchronization phenomena have been extensively studied and models robustly capturing dynamical process proposed, e.g. Extensive Kuramoto Model. Inspired by synchronization, we propose Sync, novel approach clustering. The idea view each data object as phase oscillator simulate interaction objects over time. As...
Alzheimer's disease (AD) progressively degrades the brain's gray and white matter. Changes in matter reflect changes structural connectivity pattern. Here, we established individual networks (ISCNs) to distinguish predementia dementia AD from healthy aging scans. Diffusion tractography was used construct ISCNs with a fully automated procedure for 21 control subjects (HC), 23 patients mild cognitive impairment conversion within 3 years (AD-MCI), 17 dementia. Three typical pattern classifiers...
In this paper, we propose a prototype-based classification model for evolving data streams, called SyncStream, which allows dynamically modeling time-changing concepts, making predictions in local fashion. Instead of learning single on fixed or adaptive sliding window historical ensemble set weighted base classifiers, SyncStream captures concepts by maintaining prototypes proposed P-Tree, are obtained based the error-driven representativeness and synchronization-inspired constrained...
In this study, 6 widely used precipitation products APHRODITE, CPC_UNI_PRCP, CN05.1, PERSIANN-CDR, Princeton Global Forcing (PGF), and TRMM 3B42 V7 (TMPA), were evaluated against gauge observations (CMA data) from 1998 to 2014, applied streamflow simulation over the Upper Yellow River basin (UYRB), using 4 hydrological models (DWBM, RCCC-WBM, GR4J, VIC). The relative membership degree (u), as comprehensive evaluation index in evaluation, was calculated by optimum fuzzy model. results showed...
Synchronization is a powerful and inherently hierarchical concept regulating large variety of complex processes ranging from the metabolism in cell to opinion formation group individuals. phenomena nature have been widely investigated models concisely describing dynamical synchronization process proposed, e.g., well-known Extensive Kuramoto Model. We explore potential Model for data clustering. regard each object as phase oscillator simulate behavior objects over time. By interaction with...
Stream flow plays a crucial role in the environment, society, and economy, identifying causes of changes runoff is important to understanding impact climate change human activity. This study examines variation trends recorded for Xinshui River, tributary Yellow River on Loess Plateau, uses hydrological simulations investigate how activity have contributed those trends. Results show that at Daning station declined significantly from 1955–2008 with an abrupt occurring 1973. The Simplified...
Abstract Variations of precipitation, temperature, and runoff in the Yellow River source region were analyzed with Mann–Kendall Spearman rank correlation tests over past 60 years. Based on seven climate scenarios from CMIP5 models under RCP2.6, RCP4.5, RCP8.5, responses hydrological process to change simulated using Variable Infiltration Capacity (VIC) model. Variation analysis results indicated that recorded temperature presented significant increasing trend. Daily minimum higher trend than...
Global reanalysis precipitation products could provide valuable meteorological information for flow forecasting in poorly gauged areas, helping to overcome a long-standing challenge the field. But not all data sources are suitable regions or perform same way hydrological modeling, so it is essential test suitability of before applying them. In this study, five widely used global high-resolution products—Asian Precipitation Highly Resolved Observational Data Integration Towards Evaluation...
Streamflow simulation is of great importance for water engineering design and resource management. Most existing models simulate streamflow by establishing a quantitative relationship among climate, human activities, assuming the stationary in long term. However, changing environment, this may vary over time, resulting poor performance many models. In study, inspired data stream mining, adapting gradient-boosted regression tree (XGBoost) to work an online setting, new statistically based...
Community detection and link prediction are highly dependent since knowing cluster structure as a priori will help identify missing links, in return, clustering on networks with supplemented links improve community performance. In this paper, we propose Cluster-driven Low-rank Matrix Completion (CLMC), for performing simultaneously unified framework. To end, CLMC decomposes the adjacent matrix of target network three additive matrices: matrix, noise supplement matrix. The community-structure...