A multi-city air pollution population exposure study: Combined use of chemical-transport and random-Forest models with dynamic population data

Gariazzo, Claudio; Carlino, Giuseppe; Silibello, Camillo; Renzi, Matteo; Finardi, S.; Pepe, Nicola; Radice, Paola; Forastiére, Francesco; Michelozzi, Paola; Viegi, Giovanni; Stafoggia, Massimo

doi:10.1016/j.scitotenv.2020.138102

Cited by 59 publications

(32 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It is necessary to identify the exposure distribution of air pollutants for an entire population [ 81 , 82 ]. Traditional methods are used to assess the air pollutant exposure of a population by collecting data from outdoor fixed air monitoring stations, and assign them to the home address of an individual using atmospheric dispersion models and spatial interpolation techniques [ 40 , 41 , 83 ]. However, the determination of a population’s exposure to air pollutants using measurements from fixed air monitoring stations may be insufficient in terms of their spatio-temporal resolution [ 83 ].…”

Section: Discussionmentioning

confidence: 99%

“…Traditional methods are used to assess the air pollutant exposure of a population by collecting data from outdoor fixed air monitoring stations, and assign them to the home address of an individual using atmospheric dispersion models and spatial interpolation techniques [ 40 , 41 , 83 ]. However, the determination of a population’s exposure to air pollutants using measurements from fixed air monitoring stations may be insufficient in terms of their spatio-temporal resolution [ 83 ]. With the development of modern industrial society, sources of pollution and environmental change are becoming increasingly complex and the factors required to be accommodated in the model are increasing; this has led to a rise in calculation costs, uncertainty, and a decline in model accuracy [ 35 ].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Environmental Health Surveillance System for a Population Using Advanced Exposure Assessment

Yang

Park

Cho

et al. 2020

Toxics

View full text Add to dashboard Cite

Human exposure to air pollution is a major public health concern. Environmental policymakers have been implementing various strategies to reduce exposure, including the 10th-day-no-driving system. To assess exposure of an entire population of a community in a highly polluted area, pollutant concentrations in microenvironments and population time–activity patterns are required. To date, population exposure to air pollutants has been assessed using air monitoring data from fixed atmospheric monitoring stations, atmospheric dispersion modeling, or spatial interpolation techniques for pollutant concentrations. This is coupled with census data, administrative registers, and data on the patterns of the time-based activities at the individual scale. Recent technologies such as sensors, the Internet of Things (IoT), communications technology, and artificial intelligence enable the accurate evaluation of air pollution exposure for a population in an environmental health context. In this study, the latest trends in published papers on the assessment of population exposure to air pollution were reviewed. Subsequently, this study proposes a methodology that will enable policymakers to develop an environmental health surveillance system that evaluates the distribution of air pollution exposure for a population within a target area and establish countermeasures based on advanced exposure assessment.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Environmental Health Surveillance System for a Population Using Advanced Exposure Assessment

Yang

Park

Cho

et al. 2020

Toxics

View full text Add to dashboard Cite

show abstract

“…Daily mean concentrations of air pollutants for the years 2013-2015 at the resolution of 200 m were estimated using an RFMLA as well. The spatiotemporal predictors were the concentration fields computed by a flexible air quality regional (FARM) model, the Normalized Difference Vegetation Index (NDVI), Julian day, day of week and month, resident population, mean elevation and daily traffic volumes [18]. The RFMLA model was then applied in two phases: a tuning (or training) phase in which the monitoring sites were used for choosing the best set of model predictors, and a generalization phase aimed to estimate the concentrations elsewhere.…”

Section: Pm 10 and Pm 25 1 Km Resolutionmentioning

confidence: 99%

“…The "Big data in Environmental and occupational EPidemiology" (BEEP) project aimed to assess the health effects of air pollution considering the whole Italian territory, including specific urban, suburban and rural areas, and using measures of air pollutant exposure estimated at residential level, with a resolution of 1 km [15][16][17] and 200 m [18].…”

Section: Introductionmentioning

confidence: 99%

Short-Term Effects of Air Pollution on Cardiovascular Hospitalizations in the Pisan Longitudinal Study

Fasola

Maio

Baldacci

et al. 2021

IJERPH

Self Cite

View full text Add to dashboard Cite

Air pollution effects on cardiovascular hospitalizations in small urban/suburban areas have been scantly investigated. Such effects were assessed among the participants in the analytical epidemiological survey carried out in Pisa and Cascina, Tuscany, Italy (2009–2011). Cardiovascular hospitalizations from 1585 subjects were followed up (2011–2015). Daily mean pollutant concentrations were estimated through random forests at 1 km (particulate matter: PM10, 2011–2015; PM2.5, 2013–2015) and 200 m (PM10, PM2.5, NO2, O3, 2013–2015) resolutions. Exposure effects were estimated using the case-crossover design and conditional logistic regression (odds ratio—OR—and 95% confidence interval—CI—for 10 μg/m3 increase; lag 0–6). During the period 2011–2015 (137 hospitalizations), a significant effect at lag 0 was observed for PM10 (OR = 1.137, CI: 1.023–1.264) at 1 km resolution. During the period 2013–2015 (69 hospitalizations), significant effects at lag 0 were observed for PM10 (OR = 1.268, CI: 1.085–1.483) and PM2.5 (OR = 1.273, CI: 1.053–1.540) at 1 km resolution, as well as for PM10 (OR = 1.365, CI: 1.103–1.690), PM2.5 (OR = 1.264, CI: 1.006–1.589) and NO2 (OR = 1.477, CI: 1.058–2.061) at 200 m resolution; significant effects were observed up to lag 2. Larger ORs were observed in males and in subjects reporting pre-existent cardiovascular/respiratory diseases. Combining analytical and routine epidemiological data with high-resolution pollutant estimates provides new insights on acute cardiovascular effects in the general population and in potentially susceptible subgroups living in small urban/suburban areas.

show abstract

“…Existing studies show that machine learning-and deep learning-based models have been widely applied in atmospheric environmental modeling for the monitoring and prediction of air pollutants, such as the multilayer perceptron (MLP) model [26,27], the backpropagation neural network (BPNN) model [28], support vector regression (SVR) [28,29], the random forest (RF) model [30][31][32], the general regression neural network (GRNN) model [28,33], the recurrent neural network (RNN) model [34], and long short-term memory (LSTM)-based models [11,[35][36][37][38]. The careful reasoning process in machine learningbased models (such as MLP, SVR, and RF) is comparable to mathematical reasoning [11].…”

Section: Introductionmentioning

confidence: 99%

A Novel Recursive Model Based on a Convolutional Long Short-Term Memory Neural Network for Air Pollution Prediction

et al. 2021

View full text Add to dashboard Cite

Deep learning provides a promising approach for air pollution prediction. The existing deep learning-based predicted models generally consider either the temporal correlations of air quality monitoring stations or the nonlinear relationship between the PM2.5 (particulate matter with an aerodynamic diameter of less than 2.5 μm) concentrations and explanatory variables. Spatial correlation has not been effectively incorporated into prediction models, therefore exhibiting poor performance in PM2.5 prediction tasks. Additionally, determining the manner by which to expand longer-term prediction tasks is still challenging. In this paper, to allow for spatiotemporal correlations, a spatiotemporal convolutional recursive long short-term memory (CR-LSTM) neural network model is proposed for predicting the PM2.5 concentrations in long-term prediction tasks by combining a convolutional long short-term memory (ConvLSTM) neural network and a recursive strategy. Herein, the ConvLSTM network was used to capture the complex spatiotemporal correlations and to predict the future PM2.5 concentrations; the recursive strategy was used for expanding the long-term prediction tasks. The CR-LSTM model was used to realize the prediction of the future 24 h of PM2.5 concentrations for 12 air quality monitoring stations in Beijing by configuring both the appropriate time lag derived from the temporal correlations and the spatial neighborhood, including the hourly historical PM2.5 concentrations, the daily mean meteorological data, and the annual nighttime light and normalized difference vegetation index (NDVI). The results showed that the proposed CR-LSTM model achieved better performance (coefficient of determination (R2) = 0.74; root mean square error (RMSE) = 18.96 μg/m3) than other common models, such as multiple linear regression (MLR), support vector regression (SVR), the conventional LSTM model, the LSTM extended (LSTME) model, and the temporal sliding LSTM extended (TS-LSTME) model. The proposed CR-LSTM model, implementing a combination of geographical rules, recursive strategy, and deep learning, shows improved performance in longer-term prediction tasks.

show abstract

A multi-city air pollution population exposure study: Combined use of chemical-transport and random-Forest models with dynamic population data

Cited by 59 publications

References 49 publications

Environmental Health Surveillance System for a Population Using Advanced Exposure Assessment

Environmental Health Surveillance System for a Population Using Advanced Exposure Assessment

Short-Term Effects of Air Pollution on Cardiovascular Hospitalizations in the Pisan Longitudinal Study

A Novel Recursive Model Based on a Convolutional Long Short-Term Memory Neural Network for Air Pollution Prediction

Contact Info

Product

Resources

About