Data Driven Air Pollution Modeling

Most of my times I am focused on abstract things around the concept of computational modeling, but recently, in a collaboration with Erik Velasco from CENSAM MIT and my former colleague, Gideon Aschwanden, we developed a practical methodology to estimate air pollution as street level, using the fine grained urban parameters of the locations. The main problem that we are challenged by in this case is that air pollution at ground level is very volatile and complex to be modeled based on traditional theory-driven simulation methods, while regarding the issues of health and the real exposure of people, walking and living in dense urban area, having a good estimate of air pollution at the ground level is valuable.

Therefore, in a data driven methodology we used SOM to capture the nonlinear relationships between urban parameters and air pollution measures such as PM values, Black Carbon, and so on. We used around 80 urban parameters such as land use, street network measures, building topology, and some other factors. We are in the process of submitting our first paper. this is  the Link to the poster I am going to present at MIT CENSAM 2014 annual workshop.



Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s