NN-AirPol: A neural-networks-based method for air pollution evaluation and control

Ferhat Karaca, Alexander Nikov, Omar Alagha

Research output: Contribution to journalArticlepeer-review

25 Citations (Scopus)

Abstract

A method for air pollution evaluation and control, based on one of the most popular neural networks - the backpropagation algorithm, is proposed. After the backpropagation training, the neural network, based on weather forecasting data, determines the future concentration of critical air pollution indicators. Depending on these concentrations, relevant episode warnings and actions are activated. A case study is carried out to illustrate and validate the method proposed, based on Istanbul air pollution data. Sulphur dioxide and inhalable participate matter are selected as air pollution indicators (neural network outputs). Relevant episode measures are proposed. Among ten backpropagation algorithms, the BFGS algorithm (Quasi-Newton algorithms) is adopted since it showed the lowest training error. A comparison of NN-AirPol method against regression and perceptron models showed significantly better performance.

Original languageEnglish
Pages (from-to)310-325
Number of pages16
JournalInternational Journal of Environment and Pollution
Volume28
Issue number3-4
DOIs
Publication statusPublished - Dec 18 2006
Externally publishedYes

Keywords

  • Air pollution
  • Backpropagation algorithm
  • Modelling
  • Optimisation

ASJC Scopus subject areas

  • Environmental Science(all)
  • Environmental Chemistry
  • Pollution

Fingerprint Dive into the research topics of 'NN-AirPol: A neural-networks-based method for air pollution evaluation and control'. Together they form a unique fingerprint.

Cite this