About the event
In this talk, we propose a novel hybrid deep learning model that combines Convolutional Neural Networks (CNN) and Long Short Term Memory (LSTM) together to forecast air quality at high resolution. Our model can utilize the spatial correlation characteristic of our air pollutant datasets to achieve higher forecasting accuracy than existing deep learning models of air pollution forecast.
The University of Hong Kong, under the HKU-Cambridge AI to Advance Well-being and Society Research Platform, led by Prof. Victor OK Li and Dr. Jacqueline CK Lam, has been performing research on AI technologies and its application to pressing societal problems, especially those problems related to environment and health.
Poor air quality has become an increasingly critical challenge for many metropolitan cities, and has catastrophic physical and mental consequences on human health and quality of life. However, accurately monitoring and forecasting air quality remains a highly challenging endeavour.vLimited by geographically sparse data, traditional statistical models and newly emerging data-driven methods of air quality forecasting mainly focused on the temporal correlation between the historical temporal datasets of air pollutants. However, in reality, both distribution and dispersion of air pollutants are highly location-dependent.