A Big Data and Artificial Intelligence Framework for Smart and Personalized Air Pollution Monitoring and Health Management in Hong Kong. Issue 124 (October 2021)

• Record Type: Journal Article
• Authors: Li, Victor O.K.; Lam, Jacqueline C.K.; Han, Yang; Chow, Kenyon
• Is Part Of: Environmental science & policy. Issue 124(2021)
• Page Start: 441
• Page End: 450
• Publication Date: 2021-10
• Subjects: Air Pollution Monitoring -- Health Management -- Artificial Intelligence -- Big Data -- PM(1.0, 2.5) -- Personalization -- Smart Behavioural Intervention -- Health and Well-being Improvement; 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.2021.06.011
• Languages: English
• ISSNs: 1462-9011

Abstract

Highlights: Big data and artificial intelligence for air pollution monitoring and health management Personalized and synchronized data for personalized advice and alert Smart interventions for effecting behavioral change Causal relationship between PM1.0, 2.5 vs FEV1 and FVC Abstract: All people in the world are entitled to enjoy a clean environment and a good quality of life. With big data and artificial intelligence technologies, it is possible to estimate personalized air pollution exposure and synchronize it with activity, health, quality of life and behavioural data, and provide real-time, personalized and interactive alert and advice to improve the health and well-being of individual citizens. In this paper, we propose an overarching framework outlining five major challenges to personalized air pollution monitoring and health management, and respective methodologies in an integrated interdisciplinary manner. First, urban air quality data is sparse, rendering it difficult to provide timely personalized alert and advice. Second, collected data, especially those involving human inputs such as health perception, are often missing and erroneous. Third, the data collected are heterogeneous, and highly complex, not easily comprehensible to facilitate individual and collective decision-making. Fourth, the causal relationships between personal air pollutants exposure (specifically, PM2.5 and PM1.0 and NO2 ) and personal health conditions, and health-related quality of life perception, of young asthmatics and young healthy citizens in Hong Kong (HK), are yet to be established. Fifth, whether personalized and smart information and advice provided can induce behavioural change and improve health and quality of life are yet to be determined. To overcome these challenges, our first novelty is to develop an AI and big data framework to estimate and forecast air quality in high temporal-spatial resolution and real-time. Our second novelty includes the deployment of mobile pollution sensor platforms to substantially improve the accuracy of estimated and forecasted air quality data, and the collection of activity, health condition and perception data. Our third novelty is the development of visualization tools and comprehensible indexes, by correlating personal exposure with four types of personal data, to provide timely, personalized pollution, health and travel alerts and advice. Our fourth novelty is determining causal relationship, if any, between personal pollutants, PM1.0 and PM2.5, NO2 exposure and personal health condition, and personal health perception, based on a clinical experiment of 150 young asthmatics and 150 young healthy citizens in HK. Our fifth novelty is an intervention study to determine if smart information, presented via our proposed visualized platform, will induce personal behavioural change. Our novel big data AI-driven approach, when integrated with other analytical approaches, provides an integrated interdisciplinary framework for personalized air pollution monitoring and health management, easily transferrable to and applicable in other domains and countries.