Ozone Level Prediction with Machine Learning Algorithms

Authors

  • Atınç Yılmaz Beykent University

Keywords:

Machine Learning Algorithms, Ozone Level, Risk Prediction, Proposed Model, K-Fold Validation

Abstract

The ozone level in the atmosphere not only affects the quality of life of all living things and but also causes deaths. Ozone is a gas that allows it to be put into the radiation value coming from the sun rays. Therefore, when the ozone level exceeds a certain threshold, the risk situation increases. Machine learning algorithms have the ability to make inferences from these data in situations that they have not encountered before, if sufficient data is obtained about the problem to be applied. In this study, a hybrid machine learning algorithm is proposed, and ozone level estimation is aimed to prevent this before there is a risk. The proposed hybrid model results in two stages. In the first stage, clustering is made with the method of genetic algorithms and the cluster result is transmitted as an introduction to the XGBoost classifier method. To show that the proposed model is applicable, support vector machines, random forest, multi-layered neural networks and XGBoost methods, which are among the frequently used machine learning methods, have been applied to the same problem. After the 10-fold validation applied, the proposed model reached the most successful accuracy rate with 94%.

Downloads

Download data is not yet available.

Downloads

Published

30-07-2021

How to Cite

[1]
A. Yılmaz, “Ozone Level Prediction with Machine Learning Algorithms”, JAST, vol. 14, no. 2, pp. 177–183, Jul. 2021.

Issue

Section

Articles