Dataset Information

Heavy metals in submicronic particulate matter (PM1) from a Chinese metropolitan city predicted by machine learning models.

ABSTRACT: The aim of this study was to establish a method for predicting heavy metal concentrations in PM1 (aerosol particles with an aerodynamic diameter ? 1.0 ?m) based on back propagation artificial neural network (BP-ANN) and support vector machine (SVM) methods. The annual average PM1 concentration was 26.31 ?g/m3 (range: 7.00-73.40 ?g/m3). The concentrations of most metals were higher in winter and lower in autumn and summer. Mn and Ni had the highest noncarcinogenic risk, and Cr the highest carcinogenic risk. The hazard index was below safe limit, and the integrated carcinogenic risk was less than precautionary value. There were no obvious differences in the simulation performances of BP-ANN and SVM models. However, in both models many elements had better simulation effects when input variables were atmospheric pollutants (SO2, NO2, CO, O3 and PM2.5) rather than PM1 and meteorological factors (temperature, relative humidity, atmospheric pressure and wind speed). Models performed better for Pb, Tl and Zn, as evidenced by training R and test R values consistently >0.85, whereas their performances for Ti and V were relatively poor. Predicted results by the fully trained models showed atmospheric heavy metal pollution was heavier in December and January and lighter in August and July of 2019. For the period covering the COVID-19 outbreak in China, from January to March 2020, most of the predicted element concentrations were lower than in 2018 and 2019, and the concentrations of nearly all metals were lowest during the nationwide implementation of countermeasures taken against the pandemic.

SUBMITTER: Li H

PROVIDER: S-EPMC7340598 | biostudies-literature | 2020 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Heavy metals in submicronic particulate matter (PM1) from a Chinese metropolitan city predicted by machine learning models.

Li Huiming H Dai Qian'ying Q Yang Meng M Li Fengying F Liu Xuemei X Zhou Mengfan M Qian Xin X

Chemosphere 20200708

The aim of this study was to establish a method for predicting heavy metal concentrations in PM1 (aerosol particles with an aerodynamic diameter ≤ 1.0 μm) based on back propagation artificial neural network (BP-ANN) and support vector machine (SVM) methods. The annual average PM1 concentration was 26.31 μg/m3 (range: 7.00-73.40 μg/m3). The concentrations of most metals were higher in winter and lower in autumn and summer. Mn and Ni had the highest nonc ...[more]

PMID: 32721685

Similar Datasets

Project description:BackgroundThe rise in particulate matter (PM) concentrations is a serious problem for the environment. Heavy metals associated with PM10, PM2.5, and road dust adversely affect human health. Different methods have been used to assess heavy metal contamination in PM10, PM2.5, and road dust and source apportionment of these heavy metals. These assessment tools utilize pollution indices and health risk assessment models.ObjectivesThe present study evaluates the total mass and average concentrations of heavy metals in PM10, PM2.5, and road dust along selected road networks in Dhanbad, India, analyzes the source apportionment of heavy metals, and assesses associated human health risks.MethodsA total of 112 PM samples and 21 road dust samples were collected from six stations and one background site in Dhanbad, India from December 2015 to February 2016, and were analyzed for heavy metals (iron (Fe), lead (Pb), cadmium (Cd), nickel (Ni), copper (Cu), chromium (Cr), and zinc (Zn)) using atomic absorption spectrophotometry. Source apportionment was determined using principal component analysis. A health risk assessment of heavy metal concentrations in PM10, PM2.5, and road dust was also performed.ResultsThe average mass concentration was found to be 229.54±118.40 μg m-3 for PM10 and 129.73 ±61.74 μg m-3 for PM2.5. The average concentration of heavy metals was found to be higher in PM2.5 than PM10. The pollution load index value of PM10 and PM2.5 road dust was found to be in the deteriorating category. Vehicles were the major source of pollution. The non-carcinogenic effects on children and adults were found to be within acceptable limits. The heavy metals present in PM and road dust posed a health risk in the order of road dust> PM10> and PM2.5. Particulate matter posed higher health risks than road dust due to particle size.ConclusionsThe mass concentration analysis indicates serious PM10 and PM2.5 contamination in the study area. Vehicle traffic was the major source of heavy metals in PM10, PM2.5, and road dust. In terms of non-carcinogenic risks posed by heavy metals in the present study, children were more affected than adults. The carcinogenic risk posed by the heavy metals was negligible.Competing interestsThe authors declare no competing financial interests.

Dataset Information

Heavy metals in submicronic particulate matter (PM1) from a Chinese metropolitan city predicted by machine learning models.

Publications

Heavy metals in submicronic particulate matter (PM<sub>1</sub>) from a Chinese metropolitan city predicted by machine learning models.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets