I aim to use artificial intelligence combined with traditional model data to get more accurate air quality predictions in urban areas.
Air quality is an issue that involves economic interests, affects our environment, and is linked to health issues. Better understanding of it in models can lead to more accurate exposure assessments and mitigation strategies.
I am using a combination of physical models, machine learning models, and measurement data from air quality stations. Examples of the machine learning models used are gradient boosting, neural networks, and Bayesian models.
