Score contribution per author:
α: calibrated so average coauthorship-adjusted count equals average raw count
This paper proposes a methodology based on a system of dynamic multiple linear equations that incorporates hourly, daily and annual seasonal characteristics for predicting hourly pm2.5 pollution concentrations for 11 meteorological stations in Santiago, Chile. It is demonstrated that the proposed model has the potential to match or even surpass the accuracy of competing nonlinear forecasting models in terms of both fit and predictive ability. In addition, the model is successful at predicting various categories of high concentration events, between 53% and 76% of mid-range events, and around 90% of extreme-range events on average across all stations. This forecasting model is considered a useful tool for helping government authorities to anticipate critical episodes of poor air quality so as to avoid the detrimental economic and health impacts of extreme pollution levels.