A5057037925- Air Quality and Health Impacts
- Air Quality Monitoring and Forecasting
- Atmospheric chemistry and aerosols
- Atmospheric and Environmental Gas Dynamics
- Agriculture, Soil, Plant Science
- Arctic and Russian Policy Studies
- Food Industry and Aquatic Biology
- Privacy, Security, and Data Protection
- Pharmaceutical industry and healthcare
- Atmospheric Ozone and Climate
- Hate Speech and Cyberbullying Detection
- Underwater Acoustics Research
- Atmospheric aerosols and clouds
- Intellectual Property and Patents
- Climate Change and Health Impacts
- Health Systems, Economic Evaluations, Quality of Life
- Pharmaceutical Economics and Policy
- Underwater Vehicles and Communication Systems
- Freedom of Expression and Defamation
- Innovation and Socioeconomic Development
University of Hong Kong
2021-2024
Ocean University of China
2024
Hong Kong University of Science and Technology
2021-2023
Ambient fine particulate matter (PM2.5) has severe adverse health impacts, making it crucial to reduce PM2.5 exposure for public health. Meteorological and emissions factors, which considerably affect the concentrations in atmosphere, vary substantially under different climate change scenarios. In this work, global from 2021 2100 were generated by combining deep learning technique, reanalysis data, emission bias-corrected CMIP6 future scenario data. Based on estimated concentrations,...
As a ubiquitous mesoscale phenomenon, ocean eddies significantly impact energy and mass exchange. Detecting these accurately efficiently has become research focus in remote sensing. Many traditional detection methods, rooted physical principles, often encounter challenges practical applications due to their complex parameter settings, while effective, deep learning models can be limited by the high computational demands of extensive parameters. Therefore, this paper proposes new approach...
Abstract. Deep-learning frameworks can effectively forecast the air pollution data for individual stations by decoding time-series data. However, most of existing time-series-based deep-learning models use offline spatial interpolation strategies and thus cannot reliably project station-based to region interest. In this study, long short-term memory (LSTM) technique was extended quality forecasting combining a novel layer termed broadcasting layer, which incorporates learnable weight decay...
Abstract. Deep-learning frameworks can effectively forecast the air pollution data for individual stations by decoding time series data. However, most of existing time-series-based deep-learning models use offline spatial interpolation strategies and thus cannot reliably project station-based to region interest. In this study, long short-term memory (LSTM) technique was extended quality forecasting combining a novel layer, termed broadcasting which incorporates learnable weight decay...