19th Annual CMAS Conference Sessions: (Click session to expand and see presentations in that session)
Typically, a limited number of specific simulations using chemical transport models (CTMs) or Gaussian plume models are used to derive relationships between emissions from particular sources and a response variable (pollutant concentration, health impact, etc.) for specific locations. We want to discuss here the potential usages/applications of Machine Learning (ML) and Reduced form models (RFM) that are computationally efficient and allow users to rapidly assess air quality impacts for a large number of emission scenarios, making them especially useful as screening tools for evaluating policy scenarios.
There have been many ML and RFM implementations on air quality forecasting in recent years and this session focuses on the development, evaluation, and application of ML and RFMs. Topics include, but are not limited to, the following: