- Turkish Journal of Science and Technology
- Cilt: 19 Sayı: 1
- Prediction of Air Pollution with Machine Learning Algorithms
Prediction of Air Pollution with Machine Learning Algorithms
Authors : Kahraman Oğuz, Muhammet Ali Pekin
Pages : 1-12
Doi:10.55525/tjst.1224661
View : 245 | Download : 276
Publication Date : 2024-03-28
Article Type : Research
Abstract :Air pollution has become an important problem due to its threats. Air pollutants are in complex interaction with atmosphere and environment. For this reason, it is important to study air pollution issues. In recent years, studies on prediction of air pollutants with machine learning methods have gained momentum. In this study, some air pollutants are predicted with various machine learning algorithms considering meteorological factors. In machine learning phase, a separate study is conducted with various machine learning algorithms (multilayer perceptron neural network, stochastic gradient descent, ridge regression, cross decomposition) considering temperature, relative humidity, wind, pressure and air pollutant measurements of previous hour. Consistencies of these algorithms in estimating pollutant concentrations are compared. Various statistical metrics are used to analyze the consistencies. As a result, the coefficient of determination of all algorithms are found above 0.67, considering the test section. It is found that the coefficient of determination of the multilayer perceptron neural network algorithm provides better results than other algorithms.Keywords : Hava kirliliği, makine öğrenmesi, sinir ağı, modelleme, Çanakkale ili