Hava Kalite İndeksinin Tahmin Başarısının Artırılması için Topluluk Regresyon Algoritmalarının Kullanılması

Abstract

Measuring the air quality level in the city at regular intervals and taking the necessary measures by examining the results of the measurement is very important for the health of the people and other living things in these cities. For this purpose, air quality measurement stations have been established in many cities by the relevant ministry. In this study, one of these stations, Adana province provincial station measurement data was used. The data used are the measured values ​​of air pollutant gases such as sulfur dioxide (SO2), nitrogen dioxide (NO2), ozone (O3), carbon monoxide (CO) and dust particles (PM10). The air quality index was determined by applying different machine learning algorithms to these data. Machine learning regression algorithms used; random forest, decision tree, support vector, k-nearest neighbor, linear, artificial neural network, stacking, adaboost, gradient boosting and bagging regression. The results obtained by comparing the success rates of these algorithms in terms of error rates and run times were evaluated.