D-8 Ülkeleri İçin Karbondioksit Emisyonun Yapay Sinir Ağları ile Tahmin Edilmesi: Levenberg-Marquardt Algoritması

Year 2024, , 363 - 382, 31.01.2024

Ayşe Çay Atalay

https://doi.org/10.17233/sosyoekonomi.2024.01.16

Abstract

Son yıllarda büyüme, kalkınma ve sürdürülebilirlik odaklı yaşam tarzı özellikle gelişmekte olan ülkeler için ayrı bir sorunsalı oluşturmaktadır. Bu çalışmada 1990-2020 yılları arasında tamamı gelişmekte olan ülkelerden oluşan D8 ülkeleri (Endonezya, Bangladeş, İran, Mısır, Malezya, Pakistan, Nijerya ve Türkiye) için kişi başı GSYH, kişi başı enerji tüketimi (yenilenebilir, fosil, toplam), kentsel nüfus artışı ve karbondioksit emisyonu, verileri kullanılarak yapay sinir ağları (YSA) yöntemi ile ülkelere ait karbondioksit emisyonu oranları tahmin edilmiştir. Çalışmada kurulan YSA modelinde veri tabanı verilerinin rastgele olarak %70’i eğitim, %15’i doğrulama ve %15’i test verilerine ayrılmıştır. Oluşturulan bu yapay sinir ağı, Levenberg-Marquardt algoritması ile eğitilmiştir. Modelin performans göstergelerinden Regresyon R değerleri eğitim verileri için 0,99, doğrulama verileri için 0,97 ve test verileri için 0,99 olarak belirlenmiştir. Modelde kullanılan tüm veriler için regresyon R değeri 0,99 olarak belirlenmiştir.

Keywords

D8 Ülkeleri, Yapay Sinir Ağları (YSA), Levenberg-Marquardt Yöntemi, Karbondioksit Emisyonu

Supporting Institution

HAYIR

Project Number

HAYIR

Forecasting Carbon Dioxide Emissions for D-8 Countries by Artificial Neural Networks: Levenberg-Marquardt Algorithm

Abstract

In recent years, growth, development, and sustainability-oriented lifestyles have created a separate problem, especially for developing countries. In this study, GDP per capita, energy consumption per capita (renewable, fossil, total), and urban population for D-8 countries (Indonesia, Bangladesh, Iran, Egypt, Malaysia, Pakistan, Nigeria, and Türkiye), all of which are developing countries, between 1990 and 2020. The carbon dioxide emission rates of the countries were estimated using the artificial neural networks (ANN) method by using the data of increase and carbon dioxide emission. In the ANN model established in the study, 70% of the database data was randomly divided into training, 15% validation and 15% test data. This artificial neural network is trained with the Levenberg-Marquardt method. Regression R values, one of the performance indicators of the model, were determined as 0,99 for training data, 0,97 for validation data and 0,99 for test data. The regression R-value for all data used in the model was determined as 0,99.

Keywords

D8 Countries, Artificial Neural Networks (ANN), Levenberg-Marquardt Method, Carbon Dioxide Emission

Project Number

HAYIR

References

• Acheampong, A.O. & E.B. Boateng (2019), “Modelling Carbon Emission Intensity: Application of Artificial Neural Network”, Journal of Cleaner Production, 225, 833-856.
• Ahmadi, M.H. et al. (2023), “Carbon Dioxide Emissions Prediction of Five Middle Eastern Countries Using Artificial Neural Networks”, Energy Sources, Part A: Recovery, Utilization, And Environmental Effects, 45(3), 9513-9525.
• Aktaş, M.T. (ed.) (2023), İklim ve Enerji Krizi Kıskacında İktisadi Kalkınma, Efe Akademi Yayınları.
• Ashin-Nishan, M.K. & M.A. Villanthenkodath (2020), “Role of Energy Use in The Prediction of CO2 Emissions And Economic Growth in India: Evidence from Artificial Neural Networks (ANN)”, Environmental Science And Pollution Research, 27, 23631-23642.
• Ashraf, S. et al. (2020), “Relationships among environmental pollution, energy use and economic growth: a global perspective”, OPEC Energy Review, 44(4), 511-534.
• Aslan, A. et al. (2021), “The link between urbanization and air pollution in Turkey: evidence from dynamic autoregressive distributed lag simulations”, Environmental Science and Pollution Research, 28(37), 52370-52380.
• Association Internationale Pour L'évaluationdu Rendement Scolaire (2017), Energy Access Outlook 2017: From Poverty to Prosperity, IEA.
• Aytun, C. vd. (2017), “Gelişen Ülkelerde Çevresel Bozulma, Gelir ve Enerji Tüketimi İlişkisi”, Ömer Halis Demir Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 10(1), 1-11.
• Baloch, M.A. et al. (2019), “Effect of Natural Resources, RenewableEnergy and Economic Development on CO2 Emissions in BRICS Countries”, Science of the Total Environment, 678, 632-638.
• BP (2023), Statistical Review of World Energy, <https://www.bp.com/en/global/corporate/energy-economics/statistical-review-of-world-energy.html>, 20.05.2023.
• Cantarero, M.M.V. (2020), “Of Renewable Energy, Energy Democracy, And Sustainable Development: A Roadmap To Accelerate The Energy Transition in Developing Countries”, Energy Research & Social Science, 70, 101716.
• Cherni, A. & S.E. Jouini (2017), “An ARDL approach to the CO2 emissions, renewable energy and economic growth nexus: Tunisian evidence”, International Journal of Hydrogen Energy, 42(48), 29056-29066.
• Çizmeci, H. vd. (2018), “Yapay Sinir Ağları Kullanılarak Yükseköğretimde Öğrenci Adaylarının Başarı Durumlarının Tahmin Edilmesi”, 20. Akademik Bişim Konferansı (183-186), Karabük, Türkiye.
• Endonezya İstatistik Ofisi (2023), <https://www.bps.go.id/>, 18.04.2023.
• Ercan, U. (2021), “Ev Dışı Gıda Tüketim Sınıflarının Yapay Sinir Ağları ile Tahmin Edilmesi”, İşletme Araştırmaları Dergisi, 13(4), 3265-3277.
• Fullwood, M.J. et al. (2009), “An Oestrogen-Receptor-Α-Bound Human Chromatin Interactome”, Nature, 462(7269), 58-64.
• Garcés, E.F.M. et al. (2019), “Artificial Neuronal Networks to Predict The Emissions of Carbon Dioxide (CO2) Using A Multilayer Network With The Levenberg-Marquadt Training Method”, WSEAS Transactions On Environment And Development, 16, 346-354.
• Giudici, P. (2003), Applied Data Mining Statistical Methods for Business and Industry, West Sussex, England: John Wiley&Sons.
• Grossman, G.M. & A.B. Krueger (1991), “Environmental impacts of a North American free trade agreement”, NBER Working Paper No: 3914.
• Gürlük, S. (2010), “Sürdürülebilir kalkınma gelişmekte olan ülkelerde uygulanabilir mi”, Eskişehir Osmangazi Üniversitesi İİBF Dergisi, 5(2), 85-99.
• Hagan, M.T. & M. Menhaj (1994), “Training feed-forward networks with the Marquardt algorithm”, IEEE Transactions on Neural Networks, 5(6), 989-993.
• Hagan, M.T. et al. (1996), Neural Network Design, Boston, MA: PWS Publishing.
• Haykin, S. (2008), Neural Networks and Learning Machines Third Edition, New Jersey: Pearson, Prentice Hall.
• Jena, P.R. et al. (2021), “Forecasting The CO2 Emissions At The Global Level: A Multilayer Artificial Neural Network Modelling”, Energies, 14(19), 6336.
• Kamel, A. (2001), “D-8 Ekonomik Birliği Örgütü”, Avrasya Dosyası, 7(2), 250-260.
• Karaaslan, A. & S. Çamkaya (2022), “The relationship between CO2 emissions, economic growth, health expenditure, and renewable and non-renewable energy consumption: Empirical evidence from Turkey”, Renewable Energy, 190, 457-466.
• Kendall, M.G. et al. (1963), The advanced theory of statistics, Griffin, London.
• Komeili-Birjandi, A. et al. (2022), “Modeling Carbon Dioxide Emission of Countries in Southeast of Asia by Applying Artificial Neural Network”, International Journal of Low-Carbon Technologies, 17, 321-326.
• Larose, D.T. (2005), Discovering Knowledge in Data an Introduction to Data Mining, New Jersey: John Wiley&Sons, Inc.
• Liang, W. & M. Yang (2019), “Urbanization, economic growth and environmental pollution: Evidence from China”, Sustainable Computing: Informatics and Systems, 21, 1-9.
• Luger, G.F. (2002), Artificial Intelligence: Structures and Strategies for Complex Problem Solving, 4th edition, Addison Wesley.
• Marjanović, V. et al. (2016), “Prediction of GDP Growth Rate Based on Carbon Dioxide (CO2) Emissions”, Journal of CO2 Utilization, 16, 212-217.
• Marquardt, D. (1963), “An Algorithm for Least-Squares Estimation of Nonlinear Parameters”, SIAM Journal on Applied Mathematics, 11(2), 431-441.
• Muhumuza, R. et al. (2018), “Energy consumption levels and technical approaches for supporting development of alternative energy technologies for rural sectors of developing countries”, Renewable and Sustainable Energy Reviews, 97, 90-102.
• Musah, M. et al. (2021), “Trade openness and CO2 emanations: a heterogeneous analysis on the developing eight (D8) countries”, Environmental Science and Pollution Research, 28, 44200-44215.
• Nepal, R. & N. Paija (2019), “A multivariate time series analysis of energy consumption, real output and pollutant emissions in a developing economy: new evidence from Nepal”, Economic Modelling, 77, 164-173.
• Nilsson, N.J. (1998), Artifical Intelligence: A New Synthesis, Morgan Kaufmann Publishers.
• Ouedraogo, N.S. (2017), “Africa Energy Future: Alternative Scenarios And Their Implications for Sustainable Development Strategies”, Energy Policy, 106, 457-471.
• Özhan, E. (2020), “Yapay Sinir Ağları ve Üstel Düzleştirme Yöntemi ile Türkiye’deki CO2 Emisyonunun Zaman Serisi ile Tahmini”, Avrupa Bilim ve Teknoloji Dergisi, (19), 282-289.
• Öztürk, K. & M.E. Şahin (2018), “Yapay Sinir Ağları ve Yapay Zekâ’ya Genel Bir Bakış”, Takvim-i Vekayi, 6(2), 25-36.
• Pabuçcu, H. & T. Bayramoğlu (2016), “Yapay Sinir Ağları İle CO2 Emisyonu Tahmini: Türkiye Örneği”, Gazi Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 18(3), 762-778.
• Pakistan Federal İstatistik Bürosu (2023), <https://www.pbs.gov.pk/>, 15.04.2023.
• Patterson, D. et al. (2021), “Carbon Emissions And Large Neural Network Training”, Arxiv Preprint Arxiv: 2104.10350.
• REN21 (2023), Renewables Global Status Report 2020, <https://www.ren21.net/wp-content/uploads/2019/05/gsr_2020_full_report_en.pdf>, 15.04.2023.
• Russell, S. & P. Norvig (1995), Artificial Intelligence: A Modern Approach, Prentice-Hall.
• Sel, A. & B. Tekgün (2022), “Anfis Yöntemi ile Türkiye Karbondioksit Salınımı Tahmini”, Vizyoner Dergisi, 13(34), 486-504.
• Solarin, S.A. (2020), “An environmental impact assessment of fossil fuel subsidies in emerging and developing economies”, Environmental Impact Assessment Review, 85, 106443.
• The Worldbank Orgazitation (2023), <http://www.worldban.org>, 15.03.2023.
• Türkiye Cumhuriyeti Dışişleri Bakanlığı (2023), <https://www.mfa.gov.tr.>, 10.04.2023.
• Türkiye İstatistik Ofisi (2023), <https://www.tuik.gov.tr/Kurumsal/Istatistik_Ofisleri>, 10.04.2023.
• UNEP (2023), Renewables Global Status Report 2021, <https://www.unep.org/resources/report/renewables-2021-global-status-report>, 15.04.2023.
• URL 1 (2023), <https://ennurcitir.wordpress.com/2020/02/19/yapay-sinir-aglari/>, 24.08.2023..
• URL 2 (2023), <https://www.akanesen.com/2017/09/yapay-sinir-agnn-ana-ogeleri.html>, 24.08.2023.
• V.V. Nabiyev (2016), Yapay Zeka, Seçkin Yayıncılık, Ankara.
• Vlahov, D. et al. (2007), “Urban As A Determinant of Health”, J Urban Health, 84 (1), 16-26.
• Wang, S. et al. (2021), “Global value chains, technological progress, and environmental pollution: Inequality towards developing countries”, Journal of Environmental Management, 277, 110999.
• Wang, W. & Y. Lu (2018), “Analysis of the Mean Absolute Error (MAE) and the Root Mean Square Error (RMSE) in Assessing Rounding Model”, in: IOP Conference Series: Materials Science And Engineering, 324, 012049.
• Xing, L. et al. (2023), “Investigating the impact of economic growth on environment degradation in developing economies through STIRPAT model approach”, Renewable and Sustainable Energy Reviews, 182, 113365.
• Zeng, Y.R. et al. (2017), “Multifactor-Influenced Energy Consumption Forecasting Using Enhanced Back-Propagation Neural Network”, Energy, 127, 381-396.
• Zhou, Y. et al. (2018), “The impact of economic growth and energy consumption on carbon emissions: evidence from panel quantile regression”, Journal of Physics: Conference Series, 1053, 012118.