Vehicle emission prediction using remote sensing data and machine learning techniques

More and more researchers are using remote sensing technology to measure real-world, on-road automobile emissions of nitric oxide (NO), one of the most important and frequently studied pollutants. Partnered with the National Institute of Water and Atmospheric Research (NIWA) in New Zealand, we aim to establish a robust NO emission factor prediction model using remote sensing data to forecast future emissions. This model can be extremely useful to local transport authorities for monitoring urban pollution levels and validating the effectiveness of existing traffic control policies. We have conducted this research using real-world data that were collected over a 10-year span between 2005 and 2015. The experimental results have shown that the vehicle emission patterns are continuously changing and the relevance of remote sensing data for future predictions decays as they get older.

We propose a 3-step machine learning approach to establish this model. Most notably we use quantile regression forest (a variation of random forest) as the base algorithm and use random forest's variable importance measure to validate and interpret the features. The model yields error rates that compare favourably to linear model based recursive partitioning and the original random forest model.