Design of an early alert system for PM2.5 through a stochastic method and machine learning models. Issue 127 (January 2022)

• Record Type: Journal Article
• Authors: Celis, Nathalia; Casallas, Alejandro; López-Barrera, Ellie Anne; Martínez, Hermes; Peña Rincón, Carlos A.; Arenas, Ricardo; Ferro, Camilo
• Is Part Of: Environmental science & policy. Issue 127(2022)
• Page Start: 241
• Page End: 252
• Publication Date: 2022-01
• Subjects: Early alert system -- Risk assessment -- Machine learning -- WRF-Chem -- Air quality protocol; Environmental policy -- Periodicals; Environmental sciences -- Periodicals; Environnement -- Politique gouvernementale -- Périodiques; Sciences de l'environnement -- Périodiques; Environmental policy; Environmental sciences; Periodicals; Electronic journals; 363.70561
• DOI: 10.1016/j.envsci.2021.10.030
• Languages: English
• ISSNs: 1462-9011

Abstract

Abstract: In Latin America, the levels of pollution have risen considerably in the last few years. 2019, for example, had one of the largest numbers of air quality alerts. These alerts signal an increase in respiratory diseases among the population. For this reason, this paper designs a preventive early alert system for air quality. This system compares three machine learning models and validates, through statistical and categorical parameters (9), that a stochastic model, combined with a convolution bidirectional recurrent neural network (1D-BDLM), has an accuracy of ≈ 93 ± 4% when forecasting the risk for each population group in all the monitoring stations. Likewise, it is also able to capture high pollution events without producing false alarms ( ≈ 10 ± 5%). This model is utilized to design an alert protocol (24 h in advance) before a pollution event occurs. The protocol distinguishes the level of alert and the type of population at risk, focusing on two objectives: pollution mitigation and risk reduction for the population. To reduce pollutant concentrations, this paper proposes limiting vehicle traffic in the most polluted city zones or, if necessary, throughout the entire area. In relation to stationary sources, this article proposes the implementation of monitoring measures in order to identify the most polluting factories and restrict their operation during a specific period of time. In regards to population risk, the protocol aims to reduce exposure time by recommending the avoidance of outdoor activities (in specific zones) and the use of protective gear, taking into consideration relevant differences between population groups. Graphical abstract: ga1 Highlights: An Early Alert System for PM2.5 based on risk probability forecasts was designed. An 1D-Bidirectional-LSTM network is the best model to simulate PM2.5 behavior. The protocol distinguishes the level of alert and the type of population at risk. The system can be used in any country with air quality measurement stations. People between 12 and 65 years are more impacted than infants, children and the elderly.