Türkiye’deki Farklı Sektörlere Ait Sera Gazı Emisyon Değerlerinin Çok Katmanlı Algılayıcılar ile Tahmin Edilmesi

Year 2020, Volume: 12 Issue: 2, 464 - 478, 30.06.2020

Okan Oral , Sinan Uğuz

https://doi.org/10.29137/umagd.646038

Abstract

Küresel ısınmaya neden olan karbondioksit (CO₂), Nitröz oksit (N₂O) ve Metan (CH₄) çeşitli sektörler tarafından oluşturulan sera gazlarıdır. Birleşmiş milletler iklim değişikliği çerçeve sözleşmesi (UNFCCC) kuralları gereğince Türkiye’nin de içinde olduğu ülkelerin çeşitli sektörleri tarafından oluşturulan sera gazı emisyon değerleri kayıt altına alınarak takip edilmektedir. Ülkelerin oluşturdukları sera gazı emisyon değerleri zaman içinde bir çok etkene göre farklılık oluşturabilir. Bu yüzden bu değerin tahmin edilmesi ülkeler açısından önemlidir. Bu çalışmada kullanılan ve Avrupa Çevre Ajansından elde edilen veriler, Türkiye’deki üretim, enerji endüstrisi, yerleşim ve ulaşım sektörlerine ait 1990-2014 yılları arasındaki sera gazı emisyon değerlerini içermektedir. Veri seti, bir makine öğrenmesi tekniği olan Çok Katmanlı Algılayıcılar (ÇKA) ile eğitilmiştir. Üç farklı sera gazı için kurulan modeller incelendiğinde elde edilen en yüksek  değeri üretim, enerji endüstrisi, yerleşim ve ulaşım sektörleri için sırasıyla 0.86, 0.93, 0.91 ve 0.95 olarak bulunmuştur. Çalışmada ayrıca 2020 yılında doğaya salınımını gerçekleştirmesi öngörülen üç farklı sera gazına ait emisyon değerleri tahmin edilmiş ve sonuçlar 14 yıllık geçmiş dönem verilerinin ortalaması ile kıyaslanmıştır. Buna göre üretim, enerji endüstrisi ve ulaşım sektörlerinde %64’lere varan oranda artışlar gözlenirken yerleşim sektöründe bazı gazlarda ortalama %15 oranında bir düşüş olacağı tahmin edilmiştir.

Keywords

Sera gazı emisyon, Makine öğrenmesi, Çok katmanlı algılayıcılar, Yapay sinir ağları

Prediction with Multi-layer Perceptrons of Greenhouse Gas Emission Belonging to Different Sectors in Turkey

Abstract

Carbon dioxide CO₂ Nitrous oxide N₂O and Methane CH₄ which cause global warming are greenhouse gases generated by various sectors. Greenhouse gas emissions generated by various sectors of the countries, including Turkey are followed and recorded in accordance with The United Nations Framework Convention on Climate Change (UNFCCC) rules. The greenhouse gas emissions generated by countries may change over time depending on many factors. Therefore, it is important for countries to estimate this value. The data used in this study and obtained from the European Environment Agency include greenhouse gas emissions between the years 1990-2014, belonging to Turkey's production, energy industry, residential and transport sectors.  The data set was trained with Multi Layer Perceptrons (MLP), a machine learning technique. When the models established for three different greenhouse gases were examined, the highest  values obtained were 0.86, 0.93, 0.91 and 0.95 for the production, energy industry, residential and transportation sectors, respectively. In addition, the emission values of three different greenhouse gases, which are foreseen to be released to nature in 2020, were estimated and the results were compared with the average of the data of the last 14 years. Accordingly, production, energy industry and transportation sectors have increased by up to 64%, while it is estimated that there will be an average decrease of 15% in some gases in the residential sector.

Keywords

Greenhouse gas, Machine learning, Multi-layer perceptron, Artificial neural networks

References

• Abid, M. (2017). Does economic , fi nancial and institutional developments matter for environmental quality? A comparative analysis of EU and MEA countries. Journal of Environmental Management, 188 (2), 183-194. https://doi.org/10.1016/j.jenvman.2016.12.007
• Ağaçayak, T., & Öztürk, L. (2017). Türki̇ye’ de tarım sektöründen kaynaklanan sera gazı emi̇syonlarinin. İPM - Mercato Poli̇ti̇ka Notu, 3–15.
• Araabi, N. (2012). Prediction of climate change induced temperature rise in regional scale using neural network. International Journal of Environmental Research, 6(3), 677–688.
• Assareh, E., & Nedaei, M. (2018). A metaheuristic approach to forecast the global carbon dioxide emissions. International Journal of Environmental Studies, 75(1), 99–120. https://doi.org/10.1080/00207233.2017.1374075
• Azid, A., Juahir, H., Toriman, M. E., Kamarudin, M. K. A., Saudi, A. S. M., Hasnam, C. N. C., Nor, A. A. A., Azaman, F., Latif, M. T. L., Zainuddin, M. F. S., Osman, M. R., Yamin, M. (2014). Prediction of the level of air pollution using principal component analysis and artificial neural network techniques: A case study in Malaysia. Water, Air, and Soil Pollution, 225(8). https://doi.org/10.1007/s11270-014-2063-1
• Baghban, A., Ahmadi, M. A., & Shahraki, B. H. (2015). Prediction carbon dioxide solubility in presence of various ionic liquids using computational intelligence approaches. Journal of Supercritical Fluids, 98, 50-64. https://doi.org/10.1016/j.supflu.2015.01.002
• Behrang, M. A., Assareh, E., Assari, M. R., & 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. https://doi.org/10.1080/15567036.2010.493920
• Bolanča, T., Strahovnik, T., Ukić, Š., Stankov, M. N., & Rogošić, M. (2017). Modeling of policies for reduction of GHG emissions in energy sector using ANN: case study—Croatia (EU). Environmental Science and Pollution Research, 24(19), 16172–16185. https://doi.org/10.1007/s11356-017-9216-x
• Change, I. P. O. C. (2007). Climate Change 2007: The physical science basis: summary for policymakers. Geneva: IPCC, 996. https://doi.org/10.1038/446727a
• Chen, D., Li, Y., Grace, P., & Mosier, A. R. (2008). N2O emissions from agricultural lands: A synthesis of simulation approaches. Plant and Soil, 309(1-2), 169-189. https://doi.org/10.1007/s11104-008-9634-0
• Cui, H. Z., Sham, F. C., Lo, T. Y., & Lum, H. T. (2011). Appraisal of alternative building materials for reduction of CO2 emissions by case modeling. International Journal of Environmental Research, 5(1), 93-100. https://doi.org/10.22059/ijer.2010.294Dam, M. M. (2014). Sera gazı emisyonlarının makroekonomik değişkenlerle ilişkisi: OECD Ülkeleri için panel veri analizi. Yüksek Lisans Tezi, Sosyal Bilimler Enstitüsü, Adnan Menderes Üniversitesi, 1-159.
• Çoban, O., & Şahbaz Kılınç, N. (2014). Yeni̇lenebi̇li̇r enerji̇ tüketi̇mi̇ ve karbon emi̇syonu i̇li̇şki̇si̇: tr örneği̇. Sosyal Bilimler Enstitüsü Dergisi, (38), 195-208.
• Ergün, S., & Atay Polat, M. (2017). G7 Ülkelerinde CO2 emisyonu, elektrik tüketimi ve büyüme ilişkisi. Siyaset, Ekonomi ve Yönetim Araştırmaları Dergisi, (2).
• Dam, M. M. (2014). Sera gazı emisyonlarının makroekonomik değişkenlerle ilişkisi: OECD Ülkeleri için panel veri analizi. Yüksek Lisans Tezi, Sosyal Bilimler Enstitüsü, Adnan Menderes Üniversitesi, 1-159.
• Ersoy, A. E. (2017). Türkiye’nin hayvansal gübre kaynaklı sera gazı emi̇syonları durumu ve bi̇yogaz enerji̇si potansi̇yeli̇. Yüksek Lisans Tezi, Fen Bilimleri Estitüsü, Hacettepe Üniversitesi, 1–127.
• Fan, J. L., Zhang, X., Zhang, J., & Peng, S. (2015). Efficiency evaluation of CO2 utilization technologies in China: A super-efficiency DEA analysis based on expert survey. Journal of CO2 Utilization, 11 (2015), 54-62. https://doi.org/10.1016/j.jcou.2015.01.004
• Fu, W., Han, W., Xu, T., Kim, Y., Lyu, C., & Zheng, A. (2019). Exploring the Interconnection of greenhouse gas emission and socio-economic factors. SAR Journal, 2(3), 115-120. https://doi.org/10.18421/SAR23-05
• Güçlü, B. S. (2006). Kyoto protokolü ve Türkiye’nin protokol karşisinda durumu. Metalurji Dergisi, 142, 1-4.
• Gurney, K. (2014). An introduction to neural networks. London and New York: CRC press.
• Hamzacebi, C., & Karakurt, I. (2015). Forecasting the energy-related CO2 emissions of Turkey using a grey prediction model. Energy Sources, Part A: Recovery, Utilization and Environmental Effects, 37(9), 1023-1031. https://doi.org/10.1080/15567036.2014.978086
• Hebb, D. O. (1949). The organization of behavior a neuropsychological theory. Central Institute of Education, New York: Wiley (Vol. 65). https://doi.org/10.1901/jaba.1992.25-575
• IPCC. (2014). Climate change 2014 synthesis report. Contribution of Working Groups I, II and III to the Fifth Assessment Report of the Intergovernmental Panel on Climate Change [Core Writing Team, R.K. Pachauri and L.A. Meyer (Eds.)]. IPCC, Geneva, Switzerland, (1), 151. https://doi.org/10.1177/0002716295541001010
• Işık, N. (2014). Sosyo ekonomi ulaştırma sektöründe CO2 emisyonu ve enerji Ar-Ge harcamaları ilişkisi. Sosyoekonomi/, 2014-2(December), 322-346.
• Jatmiko, W., Purnomo, D. M. J., Alhamidi, M., Wibisono, A., Wisesa, H., Mursanto, P., Bowolaksono, A., Hendrayanti, D., Addana, F. (2016). Algal growth rate modeling and prediction optimization using incorporation of MLP and CPSO algorithm. 2015 International Symposium on Micro-Nano Mechatronics and Human Science, MHS 2015, (November), 1–8. https://doi.org/10.1109/MHS.2015.7438293
• Kainuma, M., Matsuoka, Y., & Morita, T. (2000). The AIM/end-use model and its application to forecast Japanese carbon dioxide emissions. European Journal of Operational Research, 122(2), 416–425. https://doi.org/10.1016/S0377-2217(99)00243-X
• Kara, G., Yalınız, İ., & Sayar, M. (2019). Konya ili hayvansal gübre kaynaklı sera gazı emisyonları durumu. Ulusal Çevre Bilimleri Araştırma Dergisi, 2(2), 57–60.
• Khan, S., Rahmani, H., Shah, S. A. A., & Bennamoun, M. (2018). A guide to convolutional neural networks for computer vision. Synthesis Lectures on Computer Vision, 8(1), 1-207. https://doi.org/10.2200/s00822ed1v01y201712cov015
• Khoshnevisan, B., Rafiee, S., Omid, M., Yousefi, M., & Movahedi, M. (2013). Modeling of energy consumption and GHG (greenhouse gas) emissions in wheat production in Esfahan province of Iran using artificial neural networks. Energy, 52, 333–338. https://doi.org/10.1016/j.energy.2013.01.028
• Kolasa-Więcek, A. (2018). Neural modeling of greenhouse gas emission from agricultural sector in european union member countries. Water, Air, and Soil Pollution, 229(6), 7-9. https://doi.org/10.1007/s11270-018-3861-7
• Krstanoski, N. (2006). Defining The policy for reduction of CO2 emissions from the road transport sector ın republic of Macedonia, 1-15.
• Kumar, S., & Muhuri, P. K. (2019). A novel GDP prediction technique based on transfer learning using CO2 emission dataset. Applied Energy, 253(May), 113476. https://doi.org/10.1016/j.apenergy.2019.113476
• Li, S., Zhou, R., & Ma, X. (2010). The forecast of CO2 emissions in China based on RBF neural networks. 2010 2nd International Conference on Industrial and Information Systems, IIS 2010, 1, 319-322. https://doi.org/10.1109/INDUSIS.2010.5565845
• Liao, C. H., Lu, C. S., & Tseng, P. H. (2011). Carbon dioxide emissions and inland container transport in Taiwan. Journal of Transport Geography, 19(4), 722-728. https://doi.org/10.1016/j.jtrangeo.2010.08.013
• Lu, I. J., Lewis, C., & Lin, S. J. (2009). The forecast of motor vehicle, energy demand and CO2 emission from Taiwan’s road transportation sector. Energy Policy, 37(8), 2952-2961. https://doi.org/10.1016/j.enpol.2009.03.039
• Mahesh, G. U. (2018). Prediction of transportation carbon emission using spatio-temporal datasets and multilayer perceptron neural network. International Journal of New Innovations in Engineering and Technology Prediction, 8(2), 39-48.
• Nunes, I., & Da Silva, H. S. (2018). Artificial neural networks: a practical course. Springer.
• Nwulu, N. I., & Agboola, O. P. A. (2012). Modelling CO2 emissions using artificial neural networks. AWER Procedia Information Technology & Computer Science, 2, 407-411.
• Özmen, M. T. (2009). Sera Gazı - Küresel Isınma ve Kyoto Protokolü. Türkiye Mühendislik Haberleri, 42–46.
• Pabuçcu, H., & Bayramoğlu, T. (2016). Yapay sinir ağları ile CO2 emisyonu tahmini: Türkiye örneği. Gazi Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 18(3), 762-778.
• Priddy, K.L., & Keller, P.E., (2005). Artificial neural networks: An introduction. SPIE- The International Society for Optical Engineering, Washington, USA.
• Quesada-Rubio, J. M., Villar-Rubio, E., Mondéjar-Jiménez, J., & Molina-Moreno, V. (2011). Carbon dioxide emissions vs. allocation rights: Spanish case analysis. International Journal of Environmental Research, 5(2), 469-474. https://doi.org/10.22059/ijer.2011.331
• Rosenblat, F. (1958). The perceptron: a probabilistic model for information storage and organization in the brain. Psychological Review, 65(6), 386.
• Saleh, C., Dzakiyullah, N. R., & Nugroho, J. B. (2016). Carbon dioxide emission prediction using support vector machine. IOP Conference Series: Materials Science and Engineering, 114(1). https://doi.org/10.1088/1757-899X/114/1/012148
• Sangeetha, A., & Amudha, T. (2018). A novel bio-ınspired framework for CO2 emission forecast in India. Procedia Computer Science, 125, 367–375. https://doi.org/10.1016/j.procs.2017.12.048
• Solomon, S., Qin, D., Manningm, M., Marquis, M., Averyt, K., Tignor, M. B., … Chen, Z. H. (2007). The Physical science basis. Contribution of working group ı to the fourth assessment report of the intergovernmental panel on climate change. Cambridge University Press: Cambridge, United Kingdom and New York, NY, USA. https://doi.org/10.1017/CBO9781107415324.Summary
• Theodoridis, S., & Koutroumbas, K. (2009). Pattern recognition. 2003. Elsevier Inc.
• UNFCCC, (2019). https://www.eea.europa.eu/data-and-maps/data/national-emissions-reported-to-the-unfccc-and-to-the-eu- greenhouse-gas-monitoring-mechanism-12#tab-data-visualisations
• Wang, T., Li, H., Zhang, J., & Lu, Y. (2012). Influencing factors of carbon emission in china’s road freight transport. Procedia - Social and Behavioral Sciences, 43, 54–64. https://doi.org/10.1016/j.sbspro.2012.04.077
• Yan, X., & Crookes, R. J. (2010). Energy demand and emissions from road transportation vehicles in China. Progress in Energy and Combustion Science, 36(6), 651–676. https://doi.org/10.1016/j.pecs.2010.02.003
• Yılmaz, H., & Yılmaz, M. (2013). Forecasting CO2 emissions for Turkey by using the grey prediction method. Journal of Engineering and Natural Sciences, (444), 141-148.