Determinants of CO2 Emissions in Turkey: An Application with Multilayer Artificial Neural Networks

Year 2023, Volume: 12 Issue: Özel Sayı - Special Issue for the 100th Anniversary of the Republic of Türkiye, 105 - 116, 25.10.2023

Hasan Söyler , Oktay Kızılkaya

https://doi.org/10.33206/mjss.1320873

Cited By: 1

Abstract

CO2, which is released into the nature as a result of the use of fossil fuels, is one of the most important greenhouse gases that cause environmental problems. Therefore, it is very important to investigate how CO2 emissions change over time and to determine the factors that affect CO2 emissions. In this study, CO2 emission estimation is carried out using Artificial Neural Networks (ANN) method and Garson’s Algorithm is used to evaluate the relative importance of the independent variables. The results showed that ANN models are a successful method that can be used in the estimation of CO2 emissions. As a result of the importance analysis, it is determined that the most important factor affecting the CO2 emission in Turkey is the renewable energy consumption.

Keywords

Artificial Neural Networks, CO2 emissions, Garson’s Algorithm

Türkiye’de CO2 Emisyonlarının Belirleyicileri: Çok Katmanlı Yapay Sinir Ağları ile Bir Uygulama

Abstract

Fosil yakıtların kullanılması sonucu doğaya salınan CO2, çevresel sorunlara neden olan en önemli sera gazlarından birisidir. Dolayısıyla CO2 emisyonlarının zaman içinde nasıl değiştiğinin araştırılması ve CO2 emisyonu üzerinde etkili olan faktörlerin belirlenmesi oldukça önemlidir. Bu çalışmada Yapay Sinir Ağları (YSA) metodu kullanılarak CO2 emisyonu tahmini gerçekleştirilmiş ve çalışmada ele alınan bağımsız değişkenlerin bağıl önemlerini değerlendirmek amacıyla Garson Algoritması kullanılmıştır. Elde edilen tahmin sonuçları, YSA modellerinin CO2 emisyonu tahmininde kullanılabilecek başarılı bir yöntem olduklarını göstermektedir. Yapılan önem analizi sonucunda Türkiye’de CO2 emisyonunu etkileyen en önemli faktörün yenilenebilir enerji tüketimi olduğu belirlenmiştir.

Keywords

Yapay Sinir Ağları, CO2 emisyonu, Garson Algoritması

References

• Acheampong, A. O. ve Boateng, E. B. (2019). Modelling carbon emission intensity: Application of artificial neural network. Journal of Cleaner Production, 225, 833-856.
• Adebayo, T. S., Awosusi, A. A. ve Adeshola, I. (2020). Determinants of CO2 emissions in emerging markets: an empirical evidence from MINT economies. International Journal of Renewable Energy Development, 9(3), 411.
• Aggarwal, C. C. (2018). Neural networks and deep learning. Springer, 10(978), 3.
• Ataseven, B. (2013). Yapay sinir ağları ile öngörü modellemesi. Öneri Dergisi, 10(39), 101-115.
• Atay Polat M. (2022). Türkiye’de CO2 emisyonunun belirleyicisi olarak cinsiyet, istihdam ve yenilenebilir enerjinin rolü üzerine bir uygulama. Öneri Dergisi, 17(58), 638-664.
• Behrang, M. A., Assareh, E., Assari, M. R. ve Ghanbarzadeh, A. (2011). Using bees algorithm and artificial neural network to forecast world carbon dioxide emission. Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 33(19), 1747-1759.
• Cetin, M., Ecevit, E., ve Yucel, A. G. (2018). The impact of economic growth, energy consumption, trade openness, and financial development on carbon emissions: empirical evidence from Turkey. Environmental Science and Pollution Research, 25(36), 36589-36603.
• Doğanlar, M., Mike, F., Kızılkaya, O. ve Karlılar, S. (2021). Testing the long-run effects of economic growth, financial development and energy consumption on CO2 emissions in Turkey: new evidence from RALS cointegration test. Environmental Science and Pollution Research, 28(25), 32554-32563.
• Dong, K., Dong, X. ve Dong, C. (2019). Determinants of the global and regional CO2 emissions: what causes what and where?. Applied Economics, 51(46), 5031-5044.
• Fausett, L. (1994). Fundamentals of neural networks: Architecture, algorithms and applications. New Jersey: Printice Hall.
• Fischer, A. (2015). How to determine the unique contributions of input-variables to the nonlinear regression function of a multilayer perceptron. Ecological Modelling, 309, 60-63.
• Garson, G. D. (1991). Interpreting neural-network connection weights. AI Expert, 6(4), 46-51.
• Gevrey, M., Dimopoulos, I. ve Lek, S. (2003). Review and comparison of methods to study the contribution of variables in artificial neural network models. Ecological Modelling, 160(3), 249-264.
• Halicioglu, F. (2009). An econometric study of CO2 emissions, energy consumption, income and foreign trade in Turkey. Energy Policy, 37(3), 1156-1164.
• Ibrahim, O. M. (2013). A comparison of methods for assessing the relative ımportance of input variables in artificial neural networks. Journal of Applied Sciences Research, 9(11), 5692-5700.
• Jena, P. R., Managi, S. ve Majhi, B. (2021). Forecasting the CO2 emissions at the global level: A multilayer artificial neural network modelling. Energies, 14(19), 6336.
• Kemp, S. J., Zaradic, P. ve Hansen, F. (2007). An approach for determining relative input parameter importance and significance in artificial neural networks. Ecological Modelling, 204(3-4), 326-334.
• Lewis, C. D. (1982), Industrial and business forecasting method. Butterworth Scientific. London.
• Lippmann, R.P.(1987), An introduction to computing with neural nets, IEEE ASSP Magazine, April, 4-22.
• Olden, J. D. ve Jackson, D. A. (2002). Illuminating the “Black Box”: A randomization approach for understanding variable contributions in artificial neural networks. Ecological Modelling, 154(1-2), 135-150.
• Olden, J. D., Joy, M. K. ve Death, R. G. (2004). An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data. Ecological Modelling, 178(3-4), 389-397.
• Öztemel, E. (2012). Yapay sinir ağları. Papatya Yayıncılık. İstanbul.
• Pabuçcu, H. ve Bayramoğlu, T. (2016). Yapay sinir ağlari ile CO2 emisyonu tahmini: Türkiye örneği. Gazi Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 18(3), 762-778.
• Paliwal, M. ve Kumar, U. A. (2011). Assessing the contribution of variables in feed forward neural network. Applied Soft Computing, 11(4), 3690-3696.
• Rezaei, M. H., Sadeghzadeh, M., Alhuyi Nazari, M., Ahmadi, M. H. ve Astaraei, F. R. (2018). Applying GMDH artificial neural network in modeling CO2 emissions in four nordic countries. International Journal of Low-Carbon Technologies, 13(3), 266-271.
• Söyler, H. ve Kızılkaya, O. (2018). Para krizlerinin yapay zeka yöntemleri ile tahmini: Türkiye örneği. Uluslararası İktisadi ve İdari İncelemeler Dergisi, 18. EYİ Özel Sayısı, 649-666.
• Tang, Z. ve Fishwick, P. A. (1993), Feedforward neural nets as models for time series forecasting, ORSA Journal on Computing, 5(4):374-385.
• Witt, S. F. ve Witt, C. A. (1992). Modeling and forecasting demand in tourism. Londra: Academic Press.
• Wong, F. S.(1991), Time series forecasting using backpropagation neural networks, Neurocomputing, 2:147-159.
• Xu, G., Schwarz, P. ve Yang, H. (2019). Determining China's CO2 emissions peak with a dynamic nonlinear artificial neural network approach and scenario analysis. Energy Policy, 128, 752-762.