Air Quality Prediction Using Programming Language in Konya

Year 2025, Volume: 20 Issue: 2, 116 - 122, 30.06.2025

Emre Dalkılıç , Şükrü Dursun

Abstract

Air quality is a critical factor in terms of human health and environmental sustainability. The aim of this study is to examine the success of machine learning algorithms in air quality prediction. Using air quality data and meteorological data of Konya city, the performances of many algorithms such as Linear Regression, Random Forest, Ridge Regression, AdaBoost and Bayesian Ridge were compared. The results show that Extra Trees Regression model has the highest accuracy rate in predicting SO2 pollutant, while Gradient Boosting Regression model is in second place. Gradient Boosting Regression model has the highest accuracy rate in predicting PM10 pollutant, while Extra Trees Regression model is in second place. This shows that Extra Trees Regression and Gradient Boosting Regression models can successfully learn long-term dependencies especially in time series data. Light Gradient Boosting Machine showed strong performance and ranked third in predicting both pollutants. It was observed that other machine learning algorithms have significant potential in air quality prediction but provide limited accuracy. The study emphasizes that the use of deep learning techniques will provide great benefits for the development of air quality prediction systems and that more generalizable models should be created. In addition, it is anticipated that future studies on larger data sets and different geographical regions will contribute more to air quality prediction.

Keywords

Air Pollution Forecast , Air Quality , Deep Learning , Machine Learning

Ethical Statement

The author has read, understood, and complied as applicable with the statement on "Ethical responsibilities of Authors" as found in the Instructions for Authors

Supporting Institution

There is no funding this study.

References

• Acılar AM, (2020) Adaboost. r2 regresyon algoritması ile konutların ısıtma ve soğutma yüklerinin tahmin edilmesi. Ejons Int.J., 4(13), 1-12. DOI: 10.38063/ejons.173
• Almutiri TM, Alomar KH, Alganmi, NA, (2024) Integrating multi-omics using bayesian ridge regression with iterative similarity bagging. App. Sci., 14(13), 5660. DOI:10.3390/pr12091867
• Aytekin HT, (2021) Makine öğreniminin araştırmacıların veri analizi bağlamında potansiyel önemi. Ufuk Ün. Sosyal Bil. Enst. Der., 10(19), 85-106. https://dergipark.org.tr/tr/download/article-file/1693129
• Baladram, S. (2024). Dummy Regressor, Explained: A Visual Guide with Code Examples for Beginners. Retrieved from https://medium.com/data-science/dummy-regressor-explained-a-visual-guide-with-code-examples-for-beginners-4007c3d16629#:~:text=Definition,of%20more .
• Box GE, Jenkins GM, Reinsel GC, Ljung GM, (2015). Time series analysis: forecasting and control. John Wiley & Sons, 1(1),256. https://www.researchgate.net/publication/299459188_Time_Series_ _
• Dokuz Y, Bozdağ A, Gökçek B, (2020) Hava kalitesi parametrelerinin tahmini ve mekansal dağılımı için makine öğrenmesi yöntemlerinin kullanılması. Niğde Ömer Halisdemir Üni. Müh. Bil. Der., 9(1), 37-47. https://dergipark.org.tr/tr/download/article-file/950166
• Garip E, (2017) OECD ülkelerindeki CO2 emisyonunun makina öğrenmesi ile tahmin edilmesi. İstanbul Medeniyet Üniversitesi Fen Bilimleri Enstitüsü Mühendislik Yönetimi. MSc Thesis. https://acikbilim.yok.gov.tr/handle/20.500.12812/630311
• Gültepe Y, (2019). Makine öğrenmesi algoritmaları ile hava kirliliği tahmini üzerine karşılaştırmalı bir değerlendirme. Avrupa Bilim ve Teknoloji Dergisi, (16), 8-15. https://dergipark.org.tr/tr/download/article-file/764199
• Harwal, A. (2021). Passive Aggressive Regression in Machine Learning. Retrieved from https://thecleverprogrammer.com/2021/07/04/passive-aggressive-regression-in-machine-learning/ Jain R, (2024) What is Orthogonal Array Testing? | Why & How to Perform? Retrieved from https://testsigma.com/blog/orthogonal-array-testing/
• Kaplan Y, Saray U, Azkeskin E, (2014). Hava kirliliğine neden olan PM10 ve SO2 maddesinin yapay sinir ağı kullanılarak tahmininin yapılması ve hata oranının hesaplanması. Afyon Kocatepe Ün. Fen & Müh. Bil. Der., 14(2);1-6. https://dergipark.org.tr/tr/download/article-file/18764
• Li X, Peng L Hu Y, Shao J, Chi T, (2016). Deep learning architecture for air quality predictions. Environ. Sci. & Pol. Res., 23, 22408-22417. DOI: 10.1007/s11356-016-7812-9
• Li X, Rao Y, Wang W, Feng C, (2020) SLBCNN: A improved deep learning model for few-shot charge prediction. Procedia Comp. Sci., 174, 32-39. https://dl.acm.org/doi/10.1155/2022/9051629
• Ranstam J, Cook JA, (2018) LASSO regression. J. British Surgery, 105(10), 1348-1348. https://www.scirp.org/reference/referencespapers?referenceid=3450642
• Scikitlearn. (2025). Huber Regressor. Retrieved from https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.HuberRegressor.html
• Üstüner M, Abdikan S, Bilgin G, Şanlı FB, (2020) Hafif gradyan artırma makineleri ile tarımsal ürünlerin sınıflandırılması. Türk Uzaktan Algılama ve CBS Der., 1(2), 97-105. https://dergipark.org.tr/tr/pub/rsgis/issue/56931/740342
• WHO. (2024). Ambient (outdoor) air pollution. Retrieved from https://www.who.int/news-room/fact-sheets/detail/ambient-(outdoor)-air-quality-and-health