Metaheuristic algorithms to forecast future carbon dioxide emissions of Turkey

Abstract

This paper proposes the use of five different metaheuristic algorithms for forecasting carbon dioxide emissions (MtCO2) in Turkey for the years between 2019 and 2030. Historical economic indicators and construction permits in square meters of Turkey between 2002 and 2018 are used as independent variables in the forecasting equations, which take the form of two multiple linear regression models: a linear and a quadratic model. The proposed metaheuristic algorithms, including Artificial Bee Colony (ABC), Genetic Algorithm (GA), Simulated Annealing (SA), as well as hybrid versions of ABC with SA and GA with SA, are used to determine the coefficients of these regression models with reduced statistical error. The forecasting performance of the proposed methods is compared using multiple statistical methods, and the results indicate that the hybrid version of ABC with SA outperforms other methods in terms of statistical error for the linear equation model, while the hybrid version of GA with SA performs better for the quadratic equation model. Finally, four different scenarios are generated to forecast the future carbon dioxide emissions of Turkey. These scenarios reveal that if construction permits and the population is strictly managed while the economical wealth of Turkey keeps on improving, the CO2 emissions of Turkey may be less than in other possible cases.

Keywords

• Genetic algorithm
• artificial bee colony
• simulated annealing
• hybrid metaheuristics
• carbon dioxide emission; forecasting
• multiple linear regression

References

1. [1] F. Halicioglu, An econometric study of CO2 emissions, energy consumption, income and foreign trade in Turkey, Energy Policy. 37 (2009) 1156–1164. doi:10.1016/j.enpol.2008.11.012.
2. [2] O.A. Arık, Artificial bee colony algorithm to forecast natural gas consumption of Turkey, SN Applied Sciences. 1 (2019) 1–10. doi:10.1007/s42452-019-1195-8.
3. [3] M.A. Behrang, E. Assareh, M.R. Assari, A. Ghanbarzadeh, Using bees algorithm and artificial neural network to forecast world carbon dioxide emission, Energy Sources, Part A: Recovery, Utilization and Environmental Effects. 33 (2011) 1747–1759. doi:10.1080/15567036.2010.493920.
4. [4] H. Chang, W. Sun, X. Gu, Forecasting energy CO2 emissions using a quantum harmony search algorithm-based dmsfe combination model, Energies. 6 (2013) 1456–1477. doi:10.3390/en6031456.
5. [5] W. Sun, J. Wang, H. Chang, Forecasting carbon dioxide emissions in China using optimization grey model, Journal of Computers (Finland). 8 (2013) 97–101. doi:10.4304/jcp.8.1.97-101.
6. [6] R. Samsami, Comparison between genetic algorithm (GA), particle swarm optimization (PSO) and ant colony optimization (ACO) techniques for NOx emission forecasting in Iran, World Applied Sciences Journal. 28 (2013) 1996–2002. doi:10.5829/idosi.wasj.2013.28.12.1155.
7. [7] L. Abdullah, H. Mohd Pauzi, An effective model for carbon dioxide emissions prediction: Comparison of artificial neural networks learning algorithms, International Journal of Computational Intelligence and Applications. 13 (2014). doi:10.1142/S146902681450014X.
8. [8] X. Wang, Y. Cai, Y. Xu, H. Zhao, J. Chen, Optimal strategies for carbon reduction at dual levels in China based on a hybrid nonlinear grey-prediction and quota-allocation model, Journal of Cleaner Production. 83 (2014) 185–193. doi:10.1016/j.jclepro.2014.07.015.

9. [9] W. Sun, Y. Xu, Using a back propagation neural network based on improved particle swarm optimization to study the influential factors of carbon dioxide emissions in Hebei Province, China, Journal of Cleaner Production. 112 (2016) 1282–1291. doi:10.1016/j.jclepro.2015.04.097.
10. [10] H. Zhao, S. Guo, H. Zhao, Energy-related CO2 emissions forecasting using an improved lssvm model optimized by whale optimization algorithm, Energies. 10 (2017). doi:10.3390/en10070874.
11. [11] L. Wen, Y. Liu, A research about Beijing’s carbon emissions based on the IPSO-BP model, Environmental Progress and Sustainable Energy. 36 (2017) 428–434. doi:10.1002/ep.12475.
12. [12] W. Sun, J. Sun, Prediction of carbon dioxide emissions based on principal component analysis with regularized extreme learning machine: The case of China, Environmental Engineering Research. 22 (2017) 302–311. doi:10.4491/eer.2016.153.
13. [13] W. Sun, C. Wang, C. Zhang, Factor analysis and forecasting of CO2 emissions in Hebei, using extreme learning machine based on particle swarm optimization, Journal of Cleaner Production. 162 (2017) 1095–1101. doi:10.1016/j.jclepro.2017.06.016.
14. [14] A.K. Baareh, Evolutionary design of a carbon dioxide emission prediction model using Genetic Programming, International Journal of Advanced Computer Science and Applications. 9 (2018) 298–303. doi:10.14569/IJACSA.2018.090341.
15. [15] X. Zhao, M. Han, L. Ding, A.C. Calin, Forecasting carbon dioxide emissions based on a hybrid of mixed data sampling regression model and back propagation neural network in the USA, Environmental Science and Pollution Research. 25 (2018) 2899–2910. doi:10.1007/s11356-017-0642-6.
16. [16] E. Assareh, M. Nedaei, A metaheuristic approach to forecast the global carbon dioxide emissions, International Journal of Environmental Studies. 75 (2018) 99–120. doi:10.1080/00207233.2017.1374075.
17. [17] S. Dai, D. Niu, Y. Han, Forecasting of energy-related CO2 emissions in China based on GM(1,1) and least squares support vector machine optimized by modified shuffled frog leaping algorithm for sustainability, Sustainability (Switzerland). 10 (2018). doi:10.3390/su10040958.
18. [18] H. Zhao, G. Huang, N. Yan, Forecasting energy-related CO2 emissions employing a novel ssa-lssvm model: Considering structural factors in China, Energies. 11 (2018). doi:10.3390/en11040781.
19. [19] B. Ameyaw, L. Yao, Analyzing the impact of GDP on CO2 emissions and forecasting Africa’s total CO2 emissions with non-assumption driven bidirectional long short-term memory, Sustainability (Switzerland). 10 (2018). doi:10.3390/su10093110.
20. [20] D. Guo, H. Chen, R. Long, Can China fulfill its commitment to reducing carbon dioxide emissions in the Paris Agreement? Analysis based on a back-propagation neural network, Environmental Science and Pollution Research. 25 (2018) 27451–27462. doi:10.1007/s11356-018-2762-z.
21. [21] C.-C. Lin, R.-X. He, W.-Y. Liu, Considering multiple factors to forecast CO2 emissions: A hybrid multivariable grey forecasting and genetic programming approach, Energies. 11 (2018). doi:10.3390/en11123432.
22. [22] B. Ameyaw, L. Yao, A. Oppong, J.K. Agyeman, Investigating, forecasting and proposing emission mitigation pathways for CO2 emissions from fossil fuel combustion only: A case study of selected countries, Energy Policy. 130 (2019) 7–21. doi:10.1016/j.enpol.2019.03.056.
23. [23] S.M. Hosseini, A. Saifoddin, R. Shirmohammadi, A. Aslani, Forecasting of CO2 emissions in Iran based on time series and regression analysis, Energy Reports. 5 (2019) 619–631. doi:10.1016/j.egyr.2019.05.004.
24. [24] Y. Huang, H. Wang, H. Liu, S. Liu, Elman neural network optimized by firefly algorithm for forecasting China’s carbon dioxide emissions, Systems Science and Control Engineering. 7 (2019) 8–15. doi:10.1080/21642583.2019.1620655.
25. [25] W. Qiao, H. Lu, G. Zhou, M. Azimi, Q. Yang, W. Tian, A hybrid algorithm for carbon dioxide emissions forecasting based on improved lion swarm optimizer, Journal of Cleaner Production. 244 (2020). doi:10.1016/j.jclepro.2019.118612.
26. [26] W. Wu, X. Ma, Y. Zhang, W. Li, Y. Wang, A novel conformable fractional non-homogeneous grey model for forecasting carbon dioxide emissions of BRICS countries, Science of the Total Environment. 707 (2020). doi:10.1016/j.scitotenv.2019.135447.
27. [27] Q. Wu, F. Meng, Prediction of energy-related CO2 emissions in multiple scenarios using a least square support vector machine optimized by improved bat algorithm: a case study of China, Greenhouse Gases: Science and Technology. 10 (2020) 160–175. doi:10.1002/ghg.1939.
28. [28] A. Malik, E. Hussain, S. Baig, M.F. Khokhar, Forecasting CO 2 emissions from energy consumption in Pakistan under different scenarios: The China–Pakistan Economic Corridor, Greenhouse Gases: Science and Technology. (2020) ghg.1968. doi:10.1002/ghg.1968.
29. [29] I. Ozturk, A. Acaravci, CO2 emissions, energy consumption and economic growth in Turkey, Renewable and Sustainable Energy Reviews. 14 (2010). doi:10.1016/j.rser.2010.07.005.
30. [30] C. Hamzacebi, I. Karakurt, Forecasting the energy-related CO2 emissions of Turkey using a grey prediction model, Energy Sources, Part A: Recovery, Utilization and Environmental Effects. 37 (2015) 1023–1031. doi:10.1080/15567036.2014.978086.
31. [31] E.M. Bildirici, T. Bakirtas, The relationship among oil and coal consumption, carbon dioxide emissions, and economic growth in BRICTS countries, Journal of Renewable and Sustainable Energy. 8 (2016). doi:10.1063/1.4955090.
32. [32] U. Şahin, Forecasting of Turkey’s electricity generation and CO2 emissions in estimating capacity factor, Environmental Progress and Sustainable Energy. 38 (2019) 56–65. doi:10.1002/ep.13076.
33. [33] U. Şahin, Forecasting of Turkey’s greenhouse gas emissions using linear and nonlinear rolling metabolic grey model based on optimization, Journal of Cleaner Production. 239 (2019). doi:10.1016/j.jclepro.2019.118079.
34. [34] M.S. Bakay, Ü. Ağbulut, Electricity production based forecasting of greenhouse gas emissions in Turkey with deep learning, support vector machine and artificial neural network algorithms, Journal of Cleaner Production. 285 (2021). doi:10.1016/j.jclepro.2020.125324.
35. [35] S. Ullah, R. Luo, T. S. Adebayo, and M. T. Kartal, “Dynamics between environmental taxes and ecological sustainability: Evidence from top-seven green economies by novel quantile approaches,” Sustain. Dev., vol. 31, no. 2, pp. 825–839, Apr. 2023, doi: 10.1002/SD.2423.
36. [36] T. S. Adebayo and A. Samour, “Renewable energy, fiscal policy and load capacity factor in BRICS countries: novel findings from panel nonlinear ARDL model,” Environ. Dev. Sustain., pp. 1–25, Jan. 2023, doi: 10.1007/S10668-022-02888-1/FIGURES/6.
37. [37] R. Radmehr, S. Shayanmehr, E. A. Baba, A. Samour, and T. S. Adebayo, “Spatial spillover effects of green technology innovation and renewable energy on ecological sustainability: New evidence and analysis,” Sustain. Dev., 2023, doi: 10.1002/SD.2738.
38. [38] M. T. Kartal, A. Samour, T. S. Adebayo, and S. Kılıç Depren, “Do nuclear energy and renewable energy surge environmental quality in the United States? New insights from novel bootstrap Fourier Granger causality in quantiles approach,” Prog. Nucl. Energy, vol. 155, p. 104509, Jan. 2023, doi: 10.1016/J.PNUCENE.2022.104509.
39. [39] EnerData, EnerData, (2020). https://www.enerdata.net/ (accessed March 28, 2020).
40. [40] WorldBank, GDP (current US$) - Turkey | Data, (2020). https://data.worldbank.org/indicator/NY.GDP.MKTP.CD?locations=TR (accessed March 28, 2020).
41. [41] TurkStat, Turkish Statistical Institute, (2020). http://www.turkstat.gov.tr (accessed March 28, 2020).
42. [42] G. Ozdemir, E. Aydemir, M.O. Olgun, Z. Mulbay, Forecasting of Turkey natural gas demand using a hybrid algorithm, Energy Sources, Part B: Economics, Planning and Policy. 11 (2016) 295–302. doi:10.1080/15567249.2011.611580.
43. [43] M.D. Toksarı, Ant colony optimization approach to estimate energy demand of Turkey, Energy Policy. 35 (2007) 3984–3990. doi:10.1016/j.enpol.2007.01.028.
44. [44] D. Karaboga, B. Basturk, On the performance of artificial bee colony (ABC) algorithm, Applied Soft Computing. 8 (2008) 687–697. doi:10.1016/J.ASOC.2007.05.007.
45. [45] O.A. Arık, Comparisons of metaheuristic algorithms for unrelated parallel machine weighted earliness/tardiness scheduling problems, Evolutionary Intelligence. 13 (2020) 415–425. doi:10.1007/s12065-019-00305-7.
46. [46] A. Özmen, Y. Yılmaz, G.-W. Weber, Natural gas consumption forecast with MARS and CMARS models for residential users, Energy Economics. 70 (2018) 357–381. doi:10.1016/j.eneco.2018.01.022.
47. [47] O.A. Arık, Artificial bee colony algorithm including some components of iterated greedy algorithm for permutation flow shop scheduling problems, Neural Computing and Applications. 33 (2021) 3469–3486. doi:10.1007/s00521-020-05174-1.