The Carbon Emission Estimation of the Cement Sector in EU27 Countries: A Comparison with Artificial Neural Networks and ARIMA Methods

Yıl 2025, Cilt: 12 Sayı: 2, 345 - 361, 01.07.2025

Zeliha Semra Kılınç , Selim Şanlısoy

https://doi.org/10.17541/optimum.1661270

Öz

Cement is one of the most widely used building materials worldwide and the increase in its production process contributes significantly to the increase in global CO₂ emissions. The aim of this study is to estimate the amount of carbon (CO₂) emissions that will be generated by the cement sector in European Union (EU) countries by 2030 and to predict possible commercial and environmental liabilities for the sector by comparing the results obtained with different methods. With the Carbon Border Adjustment Mechanism (CBAM) introduced within the scope of the European Green Deal, the cement sector is among the priority sectors where emission reductions are mandated. In this context, the study aims to contribute to the prediction of extra costs that will arise in international trade by analyzing the future course of carbon emissions of the cement sector in EU member countries. Within the scope of the study, EU countries are selected with a focus on the cement sector and emission forecasts are made until 2030. ARIMA model and Artificial Neural Networks (ANN), one of the time series analysis methods, were used in the study and the forecasts obtained with these two methods were compared. The results show that although both methods produce different values, in general, no significant emission reduction is expected in the cement sector. This situation indicates that the sector may face significant costs in the future within the scope of CBAM and carbon mitigation policies should be strengthened.

Anahtar Kelimeler

carbon emission , ARIMA , artificial neural network

AB27 Ülkelerindeki Çimento Sektörünün Karbon Emisyonu Tahmini: Yapay Sinir Ağları ve ARIMA Yöntemleriyle Karşılaştırma

Öz

Çimento, dünya genelinde en çok kullanılan yapı malzemelerinden biri olup, üretim sürecindeki artış, küresel CO₂ emisyonlarının yükselmesine önemli ölçüde katkıda bulunmaktadır. Bu çalışmanın amacı, Avrupa Birliği (AB) ülkelerinde çimento sektörünün 2030 yılı itibarıyla yaratacağı karbon (CO₂) emisyon miktarını tahmin etmek ve farklı yöntemlerle elde edilen sonuçları karşılaştırarak sektöre ilişkin olası ticari ve çevresel yükümlülükleri öngörmektir. Avrupa Yeşil Mutabakatı kapsamında uygulamaya konulan Sınırda Karbon Düzenleme Mekanizması (SKDM) ile çimento sektörü, emisyon azaltımının zorunlu kılındığı öncelikli sektörler arasında yer almıştır. Bu bağlamda çalışma, AB üyesi ülkelerde çimento sektörünün karbon emisyonlarının gelecekteki seyrini analiz ederek, uluslararası ticarette ortaya çıkacak ekstra maliyetlerin öngörülmesine katkı sağlamayı hedeflemektedir. Çalışmanın kapsamında, AB ülkeleri çimento sektörü odaklı olarak seçilmiş ve emisyon tahminleri 2030 yılına kadar yapılmıştır. Araştırmada zaman serisi analiz yöntemlerinden ARIMA modeli ile Yapay Sinir Ağları (YSA) kullanılmış, bu iki yöntemle elde edilen tahminler karşılaştırılmıştır. Sonuçlar, her iki yöntemin farklı değerler üretse de genel olarak çimento sektöründe belirgin bir emisyon azalımı beklenmediğini göstermektedir. Bu durum, sektörün SKDM kapsamında gelecekte önemli maliyetlerle karşılaşabileceğine ve karbon azaltım politikalarının güçlendirilmesi gerektiğine işaret etmektedir.

Anahtar Kelimeler

karbon emisyonu , ARIMA , yapay sinir ağları

Kaynakça

• Acheampong, A. O., & Boateng, E. B. (2019). Modelling carbon emission intensity: Application of artificial neural network. Journal of Cleaner Production, 225, 833-856.
• Alam, T., & AlArjani, A. (2021). A Comparative Study of CO2 Emission Forecasting in the Gulf Countries Using Autoregressive Integrated Moving Average, Artificial Neural Network, and Holt‐Winters Exponential Smoothing Models. Advances in Meteorology, 2021(1), 8322590.
• Amat Bernabéu, A. (2019). ARIMA and Artificial Neural Networks to forecast the CO2 emissions allowances price: application to the design of petrochemical supply chain under uncertainty.
• Boateng, E. B., Pillay, M., & Davis, P. (2019). Predicting the level of safety performance using an artificial neural network. In Human Systems Engineering and Design: Proceedings of the 1st International Conference on Human Systems Engineering and Design (IHSED2018): Future Trends and Applications, October 25-27, 2018, CHU-Université de Reims Champagne-Ardenne, France 1 (pp. 705-710). Springer International Publishing.
• Cho, V. (2003). A comparison of three different approaches to tourist arrival forecasting. Tourism management, 24(3), 323-330.
• Czigler, T., Reiter, S., Schulze, P. & Somers, K., (2020). Laying the foundation for zero-carbon cement, https://www.mckinsey.com/industries/chemicals/our-insights/laying-the-foundation-for-zero-carbon-cement#/
• DeLurgio, S. A. (1998). Forecasting principles and applications (Vol. 49). New York: Irwin/McGraw-Hill. Fradinata, E., Suthummanon, S., Sirivongpaisal, N., & Suntiamorntuthq, W. (2014, August). ANN, ARIMA and MA timeseries model for forecasting in cement manufacturing industry: Case study at lafarge cement Indonesia—Aceh. In 2014 International Conference of Advanced Informatics: Concept, Theory and Application (ICAICTA) (pp. 39-44). IEEE.
• Goh, C., & Law, R. (2002). Modeling and forecasting tourism demand for arrivals with stochastic nonstationary seasonality and intervention. Tourism management, 23(5), 499-510.
• Janhuaton, T., Ratanavaraha, V., & Jomnonkwao, S. (2024). Forecasting Thailand’s Transportation CO2 Emissions: A Comparison among Artificial Intelligent Models. Forecasting, 6(2), 462-484.
• Kour, M. (2023). Modelling and forecasting of carbon-dioxide emissions in South Africa by using ARIMA model. International Journal of Environmental Science and Technology, 20(10), 11267-11274.
• Li, X., & Zhang, X. (2023). A comparative study of statistical and machine learning models on carbon dioxide emissions prediction of China. Environmental Science and Pollution Research, 30(55), 117485-117502.
• Mahasenan, N., Smith, S., & Humphreys, K. (2003, January). The cement industry and global climate change: current and potential future cement industry CO2 emissions. In Greenhouse gas control technologies-6th international conference (pp. 995-1000). pergamon.
• Mikulčić, H., Vujanović, M., Markovska, N., Filkoski, R. V., Ban, M., & Duić, N. (2013). CO2 emission reduction in the cement industry. Chemical engineering transactions, 35, 703-708.
• Nyoni, T., & Bonga, W. G. (2019). Prediction of CO2 emissions in India using ARIMA models. DRJ-Journal of Economics & Finance, 4(2), 01-10.
• https://www.mckinsey.com/industries/chemicals/our-insights/laying-the-foundation-for-zero-carbon-cement#/
• Rehan, R., & Nehdi, M. (2005). Carbon dioxide emissions and climate change: policy implications for the cement industry. Environmental Science & Policy, 8(2), 105-114.
• Kılınç, Z., & Şanlısoy, S. Türkiye'nin AB 27 Ülkelerine Birincil Alüminyum İhracatının Sektörel Karbon Emisyonu Üzerine Etkileri. İzmir İktisat Dergisi, 39(4), 952-971.
• Zhang, G., & Hu, M. Y. (1998). Neural network forecasting of the British pound/US dollar exchange rate. Omega, 26(4), 495-506.
• Zhang, G., Patuwo, B. E. ve Hu, M. Y. (1998). Forecasting with artificial neural networks: The state of the art. International journal of forecasting, 14(1), 35-62.
• Zimwara, D., Mugwagwa, L., & Chikowore, T. R. (2012). Air pollution control techniques for the cement manufacturing industry: A case study for Zimbabwe. CIE42 proceedings, 37, 1-13.
• Wen, T., Liu, Y., he Bai, Y., & Liu, H. (2023). Modeling and forecasting CO2 emissions in China and its regions using a novel ARIMA-LSTM model. Heliyon, 9(11).
• Worrell, E., Price, L., Martin, N., Hendriks, C., & Meida, L. O. (2001). Carbon dioxide emissions from the global cement industry. Annual review of energy and the environment, 26(1), 303-329.