Skip to main content

Artificial Intelligence, Air Pollution, and Human Health


Exposure to outdoor air pollution has been recognized as a preeminent global health concern, responsible for 4.2 million deaths every year. More than 90% of the world’s population are breathing hazardous air, especially people in China and India. Monitoring and modelling/predicting air pollution are crucial to understanding the links between emissions and air pollution levels, to supporting air quality management, and to reducing human exposure. However, current monitoring networks and modelling capabilities are woefully inadequate to fully understand the formation of air pollution, and to support air quality management. The depiction of air pollutants in the vertical in current chemical transport models is recognized as an important deficiency. Furthermore, often there is unequal allocation of monitoring sites in rural and less-settled areas. The fragmented and incomplete sketch of the evolution of air pollution provided by current observation networks hinders our ability to better understand and manage air pollution. In the meanwhile, there are many important technical bottlenecks in monitoring/modeling air pollution that need to be broken. This project aims to beat down these uncertainties with advanced artificial intelligence/machine learning methods, to improve air quality and to reduce human exposure to air pollution.

Required skills

Familiar with basic programming languages (Python, R, MATLAB, etc.), interested in air pollution and climate research.

Principal Investigator


Dr. Gao

Dr. Meng Gao

Assistant Professor, Department of Geography



Dr. Yang

Dr. Xian Yang 

Assistant Professor, Department of Computer Science

Prof. Yung

Prof. Ken Yung

Professor and Associate Head, Department of Biology