A5049367457- Hydrological Forecasting Using AI
- Meteorological Phenomena and Simulations
- Climate variability and models
- Video Analysis and Summarization
- 3D Shape Modeling and Analysis
- Mineral Processing and Grinding
- Asphalt Pavement Performance Evaluation
- Anomaly Detection Techniques and Applications
- Video Surveillance and Tracking Methods
- Infrastructure Maintenance and Monitoring
- Geological and Geophysical Studies
- Medical Image Segmentation Techniques
- Precipitation Measurement and Analysis
- Image Retrieval and Classification Techniques
Central South University
2014-2024
Shenzhen Polytechnic
2024
Hong Kong Polytechnic University
2021-2024
Institute of Atmospheric Physics
2024
Chinese Academy of Sciences
2024
Abstract According to HadGEM3 (CMIP6) models, anthropogenic forcing reduced the probability of 2022-like June mean precipitation by about 32% (15%) and increased 5-day rainfall extreme 1.8 (1.3) times.
Abstract In this paper, we present a powerful spectral shape descriptor for analysis, named Anisotropic Spectral Manifold Wavelet Descriptor (ASMWD). We proposed novel manifold harmonic signal processing tool termed Transform (ASMWT) first. ASMWT allows to comprehensively analyse signals from multiple wavelet diffusion directions on local regions of the with series low‐pass and band‐pass frequency filters in each direction. Based coefficients very simple signal, ASMWD is efficiently...
Abstract The research and application of convolutional neural networks (CNNs) on statistical downscaling have been hampered by the fact that deep learning is highly dependent sample size considered to be a black-box model. Therefore, CNN model with transfer (CNN-TL) proposed study pre-rainy season precipitation South China. First, an augmented monthly dataset created sliding fixed-length window over daily circulation field data for entire year. Next, base network pretrained dataset, then...
Most of current background subtraction algorithms have issues ghost and foreground aperture when they process the crowded video sequences in outdoor scenes. In this paper we present a novel method based on pixel state to solve issues. Every steam is assumed own two different states --- active or inactive. Via state, divide whole observing time into many short units. Meanwhile, new concept, confidence, proposed measure significance each cluster. By small units time, our automatically selects...