Prediction of ambient PM10 and toxic metals using artificial neural networks

In this study, an artificial neural network is employed to predict the concentration of ambient respirable particulate matter (PM10) and toxic metals observed in the city of Jaipur, India. A feed-forward network with a back-propagation learning algorithm is used to train the neural network the behavior of the data patterns. The meteorological variables of wind speed, wind direction, relative humidity, temperature, and time are taken as input to the network. The results indicate that the network is able to predict concentrations of PM10 and toxic metals quite accurately.     

Nonlinear dynamical analysis of ground level ozone concentrations at different temporal scales

The nonlinear dynamical analysis of ground level ozone concentration is carried out by using correlation integral method to examine its scale invariance property. The dynamics of the time series is often studied at one temporal scale. It is assumed that if the time series is determined to be chaotic at one temporal scale, its behavior at another scale can be determined as the scale shifts are allowed due to scale invariance property. The actual dynamics at other scales is however not yet analyzed. The assumption of scale invariance of the time series at different time scales is tested in this study. The analysis is carried out for ground ozone levels observed during 2006 at two sites of different land use characteristics, as traffic and mixed-use in Delhi at four temporal scales as 1 h, 4 h, 8 h and 24 h. The chaotic nature is observed for the ozone concentration with 1 h and 4 h frequency, whereas at 8 h and 24 h time scale, the ozone concentration shows random behavior. As expected, a decrease in the variability is observed in the ozone levels with increase in the scales from 1 h to 24 h. The results indicated the temporal scale shifts are allowed from 1 h to 4 h resolution and vice versa. The ozone time series at 8 h and 24 h scalings however, should be dealt separately. Further analysis for corresponding NO₂ concentration at two sites suggested finite d₂ for 1 h, 4 h and 8 h scalings with higher value at traffic site than that at mixed-use site. The analysis also indicated same degrees of freedom for ozone and NO₂ concentration at traffic site whereas at mixed-use site the number of variables governing the NO₂ pollution are less than the ozone concentration.     

Air Quality Assessment in Delhi: Before and After CNG as Fuel

A number of policy measures have been activated in India in order to control the levels of air pollutants such as particulate matter, sulphur dioxide (SO₂) and nitrogen dioxide (NO₂). Delhi, which is one of the most polluted cities in the world, is also going through the implementation phase of the control policies. Ambient air quality data monitored during 2000 to 2003, at 10 sites in Delhi, were analyzed to assess the impact of implementation of these measures, specifically fuel change in vehicles. This paper presents the impact of policy measures on ambient air quality levels and also the source apportionment. CO and NO₂ concentration levels in ambient air are found to be associated with the mobile sources. The temporal variation of air quality data shows the significant effect of shift to CNG (Compressed Natural Gas) in vehicles.     

Nonlinear analysis and prediction of coarse particulate matter concentration in ambient air

This study attempts to characterize and predict coarse particulate matter (PM10) concentration in ambient air using the concepts of nonlinear dynamical theory. PM10 data observed daily from 1999 to 2002 at a site in Mumbai, India, was used to study the applicability of the chaos theory. First, the autocorrelation function and Fourier power spectrum were used to analyze the behavior of the time-series. The dynamics of the time-series was additionally studied through correlation integral analysis and phase space reconstruction. The nonlinear predictions were then obtained using local polynomial approximation based on the reconstructed phase space. The results were then compared with the autoregressive model. The results of nonlinear analysis indicated the presence of chaotic character in the PM10 time-series. It was also observed that the nonlinear local approximation outperforms the autoregressive model, because the observed relative error of prediction for the autoregressive model was greater than the local approximation model. The invariant measures of nonlinear dynamics computed for the predicted time-series using the two models also supported the same findings.     

Prediction of Ambient PM10 and Toxic Metals Using Artificial Neural Networks

Abstract

In this study, an artificial neural network is employed to predict the concentration of ambient respirable particu-late matter (PM₁₀) and toxic metals observed in the city of Jaipur, India. A feed-forward network with a back-propagation learning algorithm is used to train the neural network the behavior of the data patterns. The meteorological variables of wind speed, wind direction, relative humidity, temperature, and time are taken as input to the network. The results indicate that the network is able to predict concentrations of PM₁₀ and toxic metals quite accurately.