Loading...

Prediction of Air Pollutants’ Hourly Concentration in Tehran Using Artificial Neural Network and Specteral Decomposition of Time Series Data

Kamali, Nima | 2014

731 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 45521 (09)
  4. University: Sharif University of Technology
  5. Department: Civil Engineering
  6. Advisor(s): Arhami, Mohammad
  7. Abstract:
  8. Recent progress in developing Artificial Neural Network (ANN) meta-models has paved the way for reliable use of these models in the prediction of air pollutant concentrations in urban atmosphere. However, improvement of prediction performance, proper selection of input parameters and model architecture remain key challenges to their practical use. This study’s main objectives are: selecting proper input parameters for ANN meta-models, optimizing the ANN models to achieve the most accurate hourly prediction for a case study (City of Tehran), coupling the ANN method with filtered input data and evaluating its privilege. In the current study the ANNs were constructed to predict criteria pollutants of NOx, O₃, CO and PM₁₀ in Tehran based on the data collected at a monitoring station in the densely populated central area of the city. The best combination of input variables was comprehensively investigated taking into account the predictability of meteorological input variables and the study of model performance. Among numerous meteorological variables wind speed, air temperature, relative humidity and wind direction were chosen as input variables for the ANN models. The complex nature of pollutant source conditions was reflected through the use of hour of the day and month of the year as input variables and the development of different models for each day of the week. High correlations were obtained with R2 of more than 0.87 between modeled and observed hourly pollutant levels for CO, NOx, and PM10. However, predicted O3 levels were less accurate. This study also proved that to use filtered data in ANN, each time series component must get trained and used separately. Using filtered data in ANNs showed slight improvement in prediction ability of the models especially in modeling the peak points, but its most important privilege is the possibily of modeling the time series components of pulltants separately, achieving the changing trend of each pollutants and making the long term prediction for baseline component of pollutants. This study also showed that models’ overall prediction ability is mostly depended on their short term components modeling
  9. Keywords:
  10. Air Pollution ; Artificial Neural Network ; Data Filtering ; Meteorological Parameters ; Air Pollutants Prediction

 Digital Object List

 Bookmark

No TOC