Where Is the Clean Air? A Bayesian Decision Framework for Personalised Cyclist Route Selection Using R-INLA

Exposure to air pollution in the form of fine particulate matter (PM2.5) is known cause diseases and cancers. Consequently, public are increasingly seeking health warnings associated with levels PM2.5 using mobile phone applications websites. Often, these existing platforms provide one-size-fits-all guidance, not incorporating user specific personal preferences. This study demonstrates an innovative approach Bayesian methods support personalised decision making for quality. We present a novel hierarchical spatio-temporal model city quality that includes buildings as barriers captures covariate information. Detailed high resolution data from single sensor used train model, which fit R-INLA facilitate computation at operational timescales. A method eliciting multi-attribute utility individual journeys within then given, providing Bayes-optimal journey support. As proof-of-concept, methodology demonstrated set collected Brisbane centre, Australia.