A model for particulate matter (PM2.5) prediction for Delhi based on machine learning approaches

Abstract Particulate matter (PM2.5) remains one of the most dominant contributors to air pollution in Delhi and its acute or chronic exposures have exerted serious health implications. Hence, it is necessary to accurately predict the magnitude of PM2.5 concentrations in order to develop emission reduction strategies for air quality management. In regard to this, few machine learning techniques have been applied to predict daily PM2.5 concentrations in Delhi. Two Different models i.e. SVM and ANN, were built on the inputs of various meteorological and pollutant parameters corresponding to 2-year period from 2016-18. Performance evaluation of the models for PM2.5 prediction has been executed and the results have been discussed. The results of this simulation exercise indicate that the ANN shows better prediction accuracy than SVM for PM2.5 prediction.

[1]  Gurumurthy Ramachandran,et al.  THE CAUSES AND CONSEQUENCES OF PARTICULATE AIR POLLUTION IN URBAN INDIA: A Synthesis of the Science , 2000 .

[2]  Marcella Busilacchio,et al.  Recursive neural network model for analysis and forecast of PM10 and PM2.5 , 2017 .

[3]  F. Meleux,et al.  Predictability of European air quality: Assessment of 3 years of operational forecasts and analyses by the PREV'AIR system , 2008 .

[4]  Musheer Ahmed,et al.  Prediction of Human Ethnicity from Facial Images Using Neural Networks , 2018 .

[5]  Pericles A. Mitkas,et al.  Applying Machine Learning Techniques on Air Quality Data for Real-Time Decision Support , 2003 .

[6]  Vikas Singh,et al.  A cokriging based approach to reconstruct air pollution maps, processing measurement station concentrations and deterministic model simulations , 2011, Environ. Model. Softw..

[7]  Gilles Foret,et al.  Combining deterministic and statistical approaches for PM10 forecasting in Europe , 2009 .

[8]  A. Peters,et al.  Particulate Matter Air Pollution and Cardiovascular Disease: An Update to the Scientific Statement From the American Heart Association , 2010, Circulation.

[9]  G. Brasseur,et al.  Prediction of ground-level ozone concentration in São Paulo, Brazil: Deterministic versus statistic models , 2016 .

[10]  A. Pillarisetti,et al.  Tracking ambient PM2.5 build-up in Delhi national capital region during the dry season over 15 years using a high-resolution (1 km) satellite aerosol dataset , 2019, Atmospheric Environment.

[11]  Andrew Quinn,et al.  Applying machine learning methods in managing urban concentrations of traffic-related particulate matter (PM10 and PM2.5) , 2019, Atmospheric Pollution Research.

[12]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[13]  Beate Ritz,et al.  Multi-pollutant exposure profiles associated with term low birth weight in Los Angeles County. , 2016, Environment international.

[14]  A. Masood,et al.  Prediction and Analysis of Pollution Levels in Delhi Using Multilayer Perceptron , 2018 .

[15]  J M Gorriz,et al.  Prediction of CO maximum ground level concentrations in the Bay of Algeciras, Spain using artificial neural networks. , 2008, Chemosphere.

[16]  A. Srivastava,et al.  Size distribution and source identification of total suspended particulate matter and associated heavy metals in the urban atmosphere of Delhi. , 2007, Chemosphere.

[17]  Rodrigo Herrera,et al.  A dynamic multiple equation approach for forecasting PM2.5 pollution in Santiago, Chile , 2018, International Journal of Forecasting.

[18]  Morton Lippmann,et al.  Toxicological and epidemiological studies of cardiovascular effects of ambient air fine particulate matter (PM2.5) and its chemical components: Coherence and public health implications , 2014, Critical reviews in toxicology.