Model for Forecasting Expressway Fine Particulate Matter and Carbon Monoxide Concentration: Application of Regression and Neural Network Models

Air quality time series near road intersections consist of complex linear and nonlinear patterns and are difficult to forecast. The backpropagation neural network (BPNN) has been applied for air quality forecasting in urban areas, but it has limited accuracy because of the inability to predict extreme events. This study proposed a novel hybrid model called GAWNN that combines a genetic algorithm and a wavelet neural network to improve forecast accuracy. The proposed model was examined through predicting the carbon monoxide (CO) and fine particulate matter (PM2.5) concentrations near a road intersection. Before the predictions, principal component analysis was adopted to generate principal components as input variables to reduce data complexity and collinearity. Then the GAWNN model and the BPNN model were implemented. The comparative results indicated that GAWNN provided more reliable and accurate predictions of CO and PM2.5 concentrations. The results also showed that GAWNN performed better than BPNN did in the capability of forecasting extreme concentrations. Furthermore, the spatial transferability of the GAWNN model was reasonably good despite a degenerated performance caused by the unavoidable difference between the training and test sites. These findings demonstrate the potential of the application of the proposed model to forecast the fine-scale trend of air pollution in the vicinity of a road intersection.

Download Full-text

Fine-scale estimation of carbon monoxide and fine particulate matter concentrations in proximity to a road intersection by using wavelet neural network with genetic algorithm

Atmospheric Environment ◽

10.1016/j.atmosenv.2014.12.058 ◽

2015 ◽

Vol 104 ◽

pp. 264-272 ◽

Cited By ~ 42

Author(s):

Zhanyong Wang ◽

Feng Lu ◽

Hong-di He ◽

Qing-Chang Lu ◽

Dongsheng Wang ◽

...

Keyword(s):

Neural Network ◽

Genetic Algorithm ◽

Carbon Monoxide ◽

Particulate Matter ◽

Fine Particulate Matter ◽

Wavelet Neural Network ◽

Fine Scale ◽

Scale Estimation ◽

Fine Particulate

Download Full-text

Comparison of Fine Particulate Matter and Carbon Monoxide Exposure Concentrations for Selected Transportation Modes

Transportation Research Record Journal of the Transportation Research Board ◽

10.3141/2428-07 ◽

2014 ◽

Vol 2428 (1) ◽

pp. 54-62 ◽

Cited By ~ 14

Author(s):

Wan Jiao ◽

H. Christopher Frey

Keyword(s):

Carbon Monoxide ◽

Particulate Matter ◽

Fine Particulate Matter ◽

Fine Particulate ◽

Transportation Modes

Download Full-text

Levels and Determinants of Fine Particulate Matter and Carbon Monoxide in Kitchens Using Biomass and Non-Biomass Fuel for Cooking

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph17041287 ◽

2020 ◽

Vol 17 (4) ◽

pp. 1287 ◽

Cited By ~ 1

Author(s):

Zafar Fatmi ◽

Georgia Ntani ◽

David Coggon

Keyword(s):

Carbon Monoxide ◽

Particulate Matter ◽

Natural Gas ◽

Fine Particulate Matter ◽

Linear Regression Analysis ◽

Personal Exposure ◽

Mean Difference ◽

Daily Average ◽

Fine Particulate ◽

Good Proxy

To assist interpretation of a study in rural Pakistan on the use of biomass for cooking and the risk of coronary heart disease, we continuously monitored airborne concentrations of fine particulate matter (PM2.5) and carbon monoxide (CO) for up to 48 h in the kitchens of households randomly selected from the parent study. Satisfactory data on PM2.5 and CO respectively were obtained for 16 and 17 households using biomass, and 19 and 17 using natural gas. Linear regression analysis indicated that in comparison with kitchens using natural gas, daily average PM2.5 concentrations were substantially higher in kitchens that used biomass in either a chimney stove (mean difference 611, 95% CI: 359, 863 µg/m3) or traditional three-stone stove (mean difference 389, 95% CI: 231, 548 µg/m3). Daily average concentrations of CO were significantly increased when biomass was used in a traditional stove (mean difference from natural gas 3.7, 95% CI: 0.8, 6.7 ppm), but not when it was used in a chimney stove (mean difference −0.8, 95% CI: −4.8, 3.2 ppm). Any impact of smoking by household members was smaller than that of using biomass, and not clearly discernible. In the population studied, cooking with biomass as compared with natural gas should serve as a good proxy for higher personal exposure to PM2.5.

Download Full-text