20200904_Forecasting PM10 concentrations using neural networks and system for improving air quality

1. Title, Journal and Authors

Title: Forecasting PM10 concentrations using neural networks and systems for improving air quality.

Journal: 2016 IEEE

Authors: Maja Muftic Dedovic, Irfan Turkovic, Tatjana Konjic, Samir Avdakovic, Nedis Dautbasic


2. Summary

This paper using Artificial Neural Network (ANN) are presented forecasting results of PM10 concentrations for the city of Sarajevo.

Two examples were modeled using neural network tools.

The first was related to the collection of input data and predicted the concentration of PM10 a day, a week or two weeks ago. However, there was a big difference between the actual value. Second, we successfully predicted PM10 concentration two weeks ago using expanded input variables and modified models.

The availability of forecasts of PM10 values per hour is particularly important for authorities to establish system measures for air quality in advance, especially for cities affected by increased PM10 concentrations.


3. Originality and Creativity


4. Application to research


5. Contact

Ma, Kyoung Rim / M.S. program


Environmental Systems Engineering Lab.

School of Earth Sciences and Environmental Engineering

Gwangju Institute of Science and Technology

1 Oryong-dong Buk-gu Gwangju, 500-712, Korea


Phone: 010-5058-6832

E-mail: dkvmfhelxp34@gm.gist.ac.kr


첨부 (0)