Applicability of machine learning in modeling of atmospheric particle pollution in Bangladesh
- PDF / 903,257 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 38 Downloads / 167 Views
Applicability of machine learning in modeling of atmospheric particle pollution in Bangladesh Shihab Ahmad Shahriar 1 & Imrul Kayes 1
&
Kamrul Hasan 1 & Mohammed Abdus Salam 1
&
Shawan Chowdhury 2
Received: 16 April 2020 / Accepted: 9 July 2020 # Springer Nature B.V. 2020
Abstract Atmospheric particle pollution causes acute and chronic health effects. Predicting the concentrations of PM2.5 and PM10, therefore, is a prerequisite to avoid the consequences and mitigate the complications. This research utilized the machine learning (ML) models such as linear-support vector machine (L-SVM), medium Gaussian-support vector machine (M-SVM), Gaussian process regression (GPR), artificial neural network (ANN), random forest regression (RFR), and a time series model namely PROPHET. Atmospheric NOX, SO2, CO, and O3, along with meteorological variables from Dhaka, Chattogram, Rajshahi, and Sylhet for the period of 2013 to 2019, were utilized as exploratory variables. Results showed that the overall performance of GPR performed better particularly for Dhaka in predicting the concentration of both PM2.5 and PM10 while ANN performed best in case of Chattogram and Sylhet for predicting PM2.5. However, in terms of predicting PM10, M-SVM and RFR were selected respectively. Therefore, this study recommends utilizing “ensemble learning” models by combining several best models to advance application of ML in predicting pollutants’ concentration in Bangladesh. Keywords Machine learning . SVM . ANN . RFR . GPR . PROPHET . Particulate matter . Bangladesh
Introduction Atmospheric particulate matter (PM) pollution, particularly PM2.5 and PM10, poses a severe and growing threat to global public health (Orioli et al. 2018). Exposure to the high concentration of PM has a strong association with different health hazards such as respiratory diseases, cancer, and cardiovascular disease. (Kim et al. 2015). In a clinical meta-analysis, Kim et al. (2015) revealed that about 3% of cardiopulmonary and 5% of lung cancer deaths are attributable to PM exposure globally. The study also argued that the existence of PM in the atmosphere poses more threat to public health than that of other ambient air pollutants. Moreover, a new study revealed Electronic supplementary material The online version of this article (https://doi.org/10.1007/s11869-020-00878-8) contains supplementary material, which is available to authorized users. * Imrul Kayes [email protected] 1
Department of Environmental Science and Disaster Management, Noakhali Science and Technology University, Noakhali 3814, Bangladesh
2
School of Biological Sciences, The University of Queensland, Brisbane, Australia
that an increase of 1 g m−3 in PM2.5 could accelerate the death rate of the coronavirus disease 2019 (COVID-19) by 15% (Wu et al. 2020). Thus, numerous scientific studies illustrated the strong evidence of the association between health hazards and PM concentration. It occurs, mostly, for the size and composition of the particles. Both particles are constituted by other subclasse
Data Loading...
