Evaluating air quality by combining stationary, smart mobile pollution monitoring and data-driven modelling
Evaluating air quality by combining stationary, smart mobile pollution monitoring and data-driven modelling
Journal of Cleaner Production - Volume 221, 1 June 2019, Pages 398-418
Please find a Link providing 50 days’ free access to our last paper with our colleagues from Data61/CSIRO Australia and UL-ERPI Laboratory, France
Highlights
• We proposed an air quality evaluation framework using fixed and mobile sensing units.
• It also integrates machine learning methods to predict the air quality from mobile data.
• Three experimenting protocols for air pollution monitoring have been implemented.
• NO2 pollution at human breathing levels was 3-5 times higher than those of static units.
• Decision trees and neural networks can accurately predict mobile air quality.
• Humidity and noise are the most important factors affecting the NO2 prediction.