01556560

Component

https://doi.org/10.3141/2503-04

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.

01578185

15-1498

English

pp 29–38

2015

Transportation Research Record: Journal of the Transportation Research Board

9780309295802

Print

Figures (6) ; References (21) ; Tables (4)

Carbon monoxide; Exhaust gases; Genetic algorithms; Intersections; Mathematical prediction; Neural networks; Particulates; Pollutants

Principal component analysis

Energy; Environment; Highways; Planning and Forecasting; I15: Environment; I72: Traffic and Transport Planning

PRP, TRIS, TRB, ATRI

Dec 30 2014 12:34PM

• Analysis of Vehicles’ Daily Fuel Consumption Frontiers with Long-Term Controller Area Network Data
• Assessment of Corridors with Different Types of Intersections: Environmental and Traffic Performance Analysis
• Characterization of Real-World Particle Number Emissions During Reignition Events from a 2010 Light-Duty Hybrid Electric Vehicle
• Developing Vehicle Classification Inputs for Project-Level MOVES Analysis
• Development of the Worldwide Harmonized Test Procedure for Light-Duty Vehicles: Pathway for Implementation in European Union Legislation
• Effects of Pavement Surface Roughness and Congestion on Expected Freeway Traffic Energy Consumption
• Emergence of Electric-Powered Two-Wheelers on Asian Roads: Curse or Blessing from a Sustainable Transport Perspective?
• Fusion of Vehicle Weight and Activity Data for Improved Vehicle Emission Modeling
• Incorporating Vehicle Emissions Models into the Geometric Highway Design Process: Application on Horizontal Curves
• Influence of Fuel Injection System and Engine-Timing Adjustments on Regulated Emissions from Four Biodiesel Fuels
• Integrating Truck Emissions Cost in Traffic Assignment
• Measurement and Evaluation of Real-World Speed and Acceleration Activity Envelopes for Light-Duty Vehicles
• Model System to Evaluate Impacts of Vehicle Purchase Tax and Fuel Tax on Household Greenhouse Gas Emissions
• Networkwide Impacts of Vehicle Ecospeed Control in the Vicinity of Traffic Signalized Intersections
• Real-Time Emissions Modeling with Environmental Protection Agency MOVES: Framework Development and Preliminary Investigation
• Transportation Activities Associated with High-Volume Hydraulic Fracturing Operations in the Marcellus Shale Formation: Analysis of Environmental and Infrastructure Impacts