Modeling the Energy Transition in Türkiye’s Transportation Sector: A Machine Learning Approach

Abstract

The global shift toward clean energy is reshaping supply chains, with road transportation, a carbon-emitting sector, at the center. Electric vehicles (EVs) offer a decarbonization pathway with minimal consumer disruption. In Türkiye, cleaner road transportation aligns with national energy strategies, the Paris Agreement, and the EU Green Deal. Although fossil-fuel mobility dominates, rising EV adoption reflects technological progress, regulatory incentives, and market dynamics. The study applies the Multi-Level Perspective (MLP) and machine learning (ML) to examine Türkiye's road-transport energy transition. Results show entrenched fossil fuel infrastructures, taxation structures, and supply chain dependencies hinder EV diffusion, while niche innovations—domestic production (e.g., TOGG) and expanding charging networks—transform the sector. Perceptron and Decision Tree models identify adoption drivers: charging availability, fuel prices, and macroeconomic conditions. GDP per capita and diesel, gasoline, and LPG price increases boost EV sales, whereas inflation, interest rates, and exchange rates reduce them. Accelerating the transition requires coordinated governance, tax incentives, infrastructure investment, and decarbonized electricity generation.

Keywords

• Energy Transition
• Multi-Level Perspective
• Electric Vehicles
• Road Transportation
• Türkiye
• Machine Learning

Türkiye’nin Ulaşım Sektöründe Enerji Dönüşümünün Modellenmesi: Bir Makine Öğrenmesi Yaklaşımı

Abstract

Küresel temiz enerji geçişi, tedarik zincirlerini yeniden şekillendirirken, yüksek karbon emisyonlu sektörlerden biri olan karayolu taşımacılığı dönüşümün merkezindedir. Elektrikli araçlar (EA'lar), tüketici davranışını değiştirmeden karbon azaltımı için bir fırsat sunmaktadır. Türkiye'de karayolu taşımacılığının temiz enerjiye yönelmesi; ulusal enerji politikaları, Paris Anlaşması ve AB Yeşil Mutabakatı hedefleriyle uyumludur. Fosil yakıtlı ulaşım baskın olsa da, artan EA kullanımı teknolojik gelişmeler, düzenleyici teşvikler ve piyasa dinamikleriyle şekillenmektedir. Çalışma, Türkiye'nin karayolu taşımacılığındaki enerji dönüşümünü incelemek için Çok Düzeyli Perspektif (MLP) ve makine öğrenmesi (MÖ) tekniklerini kullanır. Bulgular, fosil yakıt altyapıları, vergi yapıları ve tedarik zinciri bağımlılıklarının EA yayılımını sınırladığını; TOGG gibi yerli üretim ve genişleyen şarj ağları gibi yeniliklerin sektörü dönüştürdüğünü gösterir. Perceptron ve Karar Ağacı modelleri, benimsemenin temel etkenlerini şarj erişimi, akaryakıt fiyatları ve makroekonomik koşullar olarak belirler. Kişi başı gelir ile dizel, benzin ve LPG fiyatlarındaki artış EA satışlarını olumlu; enflasyon, faiz oranı ve döviz kuru olumsuz etkiler. Dönüşümün hızlanması; eşgüdümlü yönetişim, vergi teşvikleri, altyapı yatırımı ve elektrik üretiminde karbon azaltımını gerektirir.

Keywords

• Enerji Dönüşümü
• Çok Düzeyli Perspektif
• Elektrikli Araçlar
• Karayolu Ulaşımı
• Türkiye
• Makine Öğrenmesi

References

1. Ağbulut, Ü., Yıldız, G., Bakır, H., Polat, F., Biçen, Y., Ergün, A. and Gürel, A.E. (2023). Current practices, potentials, challenges, future opportunities, environmental and economic assumptions for Türkiye’s clean and sustainable energy policy: A comprehensive assessment. Sustainable Energy Technologies and Assessments, 56, 103019. https://doi.org/10.1016/j.seta.2023.103019
2. Ahmad, T., Zhang, H. and Yan, B. (2020). A review on renewable energy and electricity requirement forecasting models for smart grid and buildings. Sustainable Cities and Society, 55, 102052. https://doi.org/10.1016/j.scs.2020.102052
3. Alagoz, E. and Alghawi, Y. (2023). The energy transition: Navigating the shift towards renewables in the oil and gas industry. Journal of Energy and Natural Resources, 12(1), 21–24. https://doi.org/10.11648/j.jenr.20231202.12
4. Alghoul, M.A., Hammadi, F.Y., Amin, N. and Asim, N. (2018). The role of existing infrastructure of fuel stations in deploying solar charging systems, electric vehicles and solar energy: A preliminary analysis. Technological Forecasting and Social Change, 137, 317–326. https://doi.org/10.1016/j.techfore.2018.06.040
5. Al-Hanahi, B., Ahmad, I., Habibi, D. and Masoum, M.A. (2021). Charging infrastructure for commercial electric vehicles: Challenges and future works. IEEE Access, 9, 121476–121492. https://doi.org/10.1109/access.2021.3108817
6. Amjad, S., Neelakrishnan, S. and Rudramoorthy, R. (2010). Review of design considerations and technological challenges for successful development and deployment of plug-in hybrid electric vehicles. Renewable and Sustainable Energy Reviews, 14, 1104–1110. https://doi.org/10.1016/j.rser.2009.11.001
7. Antonopoulos, I., Robu, V., Couraud, B., Kirli, D., Norbu, S., Kiprakis, A., Flynn, D., Elizondo-Gonzalez, S. and Wattam, S. (2020). Artificial intelligence and machine learning approaches to energy demand-side response: A systematic review. Renewable and Sustainable Energy Reviews, 130, 109899. https://doi.org/10.1016/j.rser.2020.109899
8. Ates, A., Rogge, K. and Lovell, K. (2022). New methodological approach for multi-system actor analysis: UK's energy-mobility transition (SSRN Paper No. 4269003). https://doi.org/10.2139/ssrn.4269003

9. Avci, A.C. and Kaygusuz, K. (2020). Renewable and sustainable energy policies in Turkey after the Paris Agreement: Economic and environmental analysis. Journal of Engineering Research and Applied Sciences, 9, 1618–1629.
10. Barbanente, A. and Grassini, L. (2022). Fostering transitions in landscape policies: A multi-level perspective. Land Use Policy, 112, 105869. https://doi.org/10.1016/j.landusepol.2021.105869
11. Beaufils, T., Ward, H., Jakob, M. and Wenz, L. (2023). Assessing different European carbon border adjustment mechanism implementations and their impact on trade partners. Communications Earth & Environment, 4, 131. https://doi.org/10.1038/s43247-023-00788-4
12. Berkeley, N., Bailey, D., Jones, A. and Jarvis, D. (2017). Assessing the transition towards battery electric vehicles: A multi-level perspective on drivers of, and barriers to, take-up. Transportation Research Part A: Policy and Practice, 106, 320–332. https://doi.org/10.1016/j.tra.2017.10.004
13. Bigazzi, A. and Wong, K. (2020). Electric bicycle mode substitution for driving, public transit, conventional cycling, and walking. Transportation Research Part D: Transport and Environment, 85, 102412. https://doi.org/10.1016/j.trd.2020.102412
14. BP. (2023). SOCAR and BP to cooperate on potential renewable projects. Retrieved from https://www.bp.com/en_az/azerbaijan/home/news/press-releases/SOCAR-and-bp-to-cooperate-on-potential-renewable-projects.html
15. Cherp, A., Vinichenko, V., Jewell, J., Brutschin, E. and Sovacool, B. (2018). Integrating techno-economic, socio-technical and political perspectives on national energy transitions: A meta-theoretical framework. Energy Research & Social Science, 37, 175–190. https://doi.org/10.1016/j.erss.2017.09.015
16. Crowther, A., Petrova, S. and Evans, J. (2021). Toward regional low-carbon energy transitions in England: A relational perspective. Frontiers in Sustainable Cities, 3, 635970. https://doi.org/10.3389/frsc.2021.635970
17. De Rubens, G.Z., Noel, L., Kester, J. and Sovacool, B.K. (2020). The market case for electric mobility: Investigating electric vehicle business models for mass adoption. Energy, 194, 116841. https://doi.org/10.1016/j.energy.2019.116841
18. Deng, D.L., Li, X. and Das Sarma, S. (2017). Machine learning topological states. Physical Review B, 96(19), 195145. https://doi.org/10.1103/physrevb.96.195145
19. Dubey, A. K., Kumar, A., Ramirez, I. S. and Marquez, F. P. G. (2022). A review of intelligent systems for the prediction of wind energy using machine learning. In J. Xu, F. Altiparmak, M.H.A. Hassan, F.P.G. García Márquez & A. Hajiyev (Eds.), Proceedings of the sixteenth international conference on management science and engineering management – volume 1, lecture notes on data engineering and communications technologies (pp. 476–491). https://doi.org/10.1007/978-3-031-10388-9_35
20. Elmaz, F., Yücel, Ö. and Mutlu, A.Y. (2020). Predictive modeling of biomass gasification with machine learning-based regression methods. Energy, 191, 116541. https://doi.org/10.1016/j.energy.2019.116541
21. EMRA. (2024). Charging station summary inquiry. Energy Market Regulatory Authority. Retrieved from https://lisans.epdk.gov.tr/epvys-web/faces/pages/lisans/elektrikSarjAgiIsletmeci/sarjIstasyonuOzetSorgula.xhtml
22. Falchetta, G. and Noussan, M. (2021). Electric vehicle charging network in Europe: An accessibility and deployment trends analysis. Transportation Research Part D: Transport and Environment, 94, 102813. https://doi.org/10.1016/j.trd.2021.102813
23. Franke, T., Schmalfuß, F. and Rauh, N. (2018). Human factors and ergonomics in the individual adoption and use of electric vehicles. In A. Thatcher and P.H.P. Yeow (Eds.), Ergonomics and human factors for a sustainable future (pp. 135–160). https://doi.org/10.1007/978-981-10-8072-2_6
24. Geels, F.W. (2011). The multi-level perspective on sustainability transitions: Responses to seven criticisms. Environmental Innovation and Societal Transitions, 1, 24–40. https://doi.org/10.1016/j.eist.2011.02.002
25. Geels, F.W. (2014). Regime resistance against low-carbon transitions: Introducing politics and power into the multi-level perspective. Theory, Culture & Society, 31, 21–40. https://doi.org/10.1177/0263276414531627
26. Geels, F.W., McMeekin, A. and Pfluger, B. (2020). Socio-technical scenarios as a methodological tool to explore social and political feasibility in low-carbon transitions: Bridging computer models and the multi-level perspective in UK electricity generation (2010–2050). Technological Forecasting and Social Change, 151, 119258. https://doi.org/10.1016/j.techfore.2018.04.001
27. Geels, F.W., Sovacool, B.K., Schwanen, T. and Sorrell, S. (2017). The socio-technical dynamics of low-carbon transitions. Joule, 1, 463–479. https://doi.org/10.1016/j.joule.2017.09.018
28. Genus, A. (2014). Governing sustainability: A discourse-institutional approach. Sustainability, 6, 283–305. https://doi.org/10.3390/su6010283
29. Ghoddusi, H., Creamer, G.G. and Rafizadeh, N. (2019). Machine learning in energy economics and finance: A review. Energy Economics, 81, 709–727. https://doi.org/10.1016/j.eneco.2019.05.006
30. Gomez, W., Wang, F.-K. and Lo, S.-C. (2024). A hybrid approach based machine learning models in electricity markets. Energy, 289, 129988. https://doi.org/10.1016/j.energy.2023.129988
31. Gönül, Ö., Duman, A.C. and Güler, Ö. (2021). Electric vehicles and charging infrastructure in Turkey: An overview. Renewable and Sustainable Energy Reviews, 143, 110913. https://doi.org/10.1016/j.rser.2021.110913
32. Hoffmann, S., Weyer, J. and Longen, J. (2017). Discontinuation of the automobility regime? An integrated approach to multi-level governance. Transportation Research Part A: Policy and Practice, 103, 391–408. https://doi.org/10.1016/j.tra.2017.06.016
33. Hofmann, M., Hofmann, H., Hagelüken, C. and Hool, A. (2018). Critical raw materials: A perspective from the materials science community. Sustainable Materials and Technologies, 17, e00074. https://doi.org/10.1016/j.susmat.2018.e00074
34. Isaksson, K. and Heikkinen, S. (2018). Sustainability transitions at the frontline. Lock-in and potential for change in the local planning arena. Sustainability, 10, 840. https://doi.org/10.3390/su10030840
35. Jørgensen, U. (2012). Mapping and navigating transitions—The multi-level perspective compared with arenas of development. Research Policy, 41, 996–1010. https://doi.org/10.1016/j.respol.2012.03.001
36. Khalid, M.R., Khan, I.A., Hameed, S., Asghar, M.S.J. and Ro, J.-S. (2021). A comprehensive review on structural topologies, power levels, energy storage systems, and standards for electric vehicle charging stations and their impacts on grid. IEEE Access, 9, 128069–128094. https://doi.org/10.1109/access.2021.3112189
37. Krishnan, R. and Butt, B. (2022). "The gasoline of the future:” points of continuity, energy materiality, and corporate marketing of electric vehicles among automakers and utilities. Energy Research & Social Science, 83, 102349. https://doi.org/10.1016/j.erss.2021.102349
38. Li, L. (2020). The governance of low-carbon transitions in a multilevel perspective framework: How does the concept of 'system transformation' work. Energy Research Journal, 11, 45–53. https://doi.org/10.3844/erjsp.2020.45.53
39. Magacho, G., Espagne, E. and Godin, A. (2023). Impacts of the CBAM on EU trade partners: Consequences for developing countries. Climate Policy, 1–17. https://doi.org/10.1080/14693062.2023.2200758.
40. Marquardt, J. (2017). Conceptualizing power in multi-level climate governance. Journal of Cleaner Production, 154, 167–175. https://doi.org/10.1016/j.jclepro.2017.03.176 Ministry of Industry and Technology. (2024). Global giant invests in Türkiye. Retrieved from https://www.sanayi.gov.tr/medya/haber/dunya-devinden-turkiyeye-yatirim-karari.
41. Needell, Z., Wei, W. and Trancik, J.E. (2023). Strategies for beneficial electric vehicle charging to reduce peak electricity demand and store solar energy. Cell Reports Physical Science, 4, 101287. https://doi.org/10.1016/j.xcrp.2023.101287
42. Nieto, P.J.G., Gonzalo, E.G., García, L.A.M., Álvarez–de Prado, L. and Sánchez, A.B. (2024). Predicting the critical superconducting temperature using the random forest, MLP neural network, M5 model tree and multivariate linear regression. Alexandria Engineering Journal, 86, 144–156. https://doi.org/10.1016/j.aej.2023.11.034
43. Nilsson, M. and Nykvist, B. (2016). Governing the electric vehicle transition–Near term interventions to support a green energy economy. Applied Energy, 179, 1360–1371. https://doi.org/10.1016/j.apenergy.2016.03.056
44. Patella, S.M., Scrucca, F., Asdrubali, F. and Carrese, S. (2019). Traffic simulation-based approach for a cradle-to-grave greenhouse gases emission model. Sustainability, 11, 4328. https://doi.org/10.3390/su11164328
45. Pedraza, J.M. (2014). The future role of renewable energy sources for the generation of electricity in the European region. Journal of Reviews on Global Economics, 3, 117–130. https://doi.org/10.6000/1929-7092.2014.03.09
46. Pelegov, D.V. and Pontes, J. (2018). Main drivers of battery industry changes: Electric vehicles—A market overview. Batteries, 4, 65. https://doi.org/10.3390/batteries4040065
47. Plantinga, A. and Scholtens, B. (2021). The financial impact of fossil fuel divestment. Climate Policy, 21, 107–119. https://doi.org/10.1080/14693062.2020.1806020
48. Qadir, S.A., Ahmad, F., Al-Wahedi, A.M.A., Iqbal, A. and Ali, A. (2024). Navigating the complex realities of electric vehicle adoption: A comprehensive study of government strategies, policies, and incentives. Energy Strategy Reviews, 53, 101379. https://doi.org/10.1016/j.esr.2024.101379
49. Qiu, X., Ren, Y., Suganthan, P.N. and Amaratunga, G.A. (2017). Empirical mode decomposition based ensemble deep learning for load demand time series forecasting. Applied Soft Computing, 54, 246–255. https://doi.org/10.1016/j.asoc.2017.01.015
50. Reuters. (2024). Turkey's Erdogan announces $30 bln in incentives for high-tech areas. Retrieved from https://www.reuters.com/business/autos-transportation/turkeys-erdogan-announces-30-bln-incentives-high-tech-areas-2024-07-26/
51. Sartor, O., Donat, L., Duwe, M. and Umpfenbach, K. (2017). Developing 2050 decarbonization strategies in the EU: Insights on good practice from national experiences. Study, 3, 2017. https://doi.org/10.1021/acssuschemeng.4c09854.s001
52. Schot, J., Kanger, L. and Verbong, G. (2016). The roles of users in shaping transitions to new energy systems. Nature Energy, 1, 1–7. https://doi.org/10.1038/nenergy.2016.54
53. Shobana, G. and Umamaheswari, K. (2021). Forecasting by machine learning techniques and econometrics: A review. In 2021 6th international conference on inventive computation technologies (ICICT) (pp. 1010–1016). IEEE. https://doi.org/10.1109/icict50816.2021.9358514
54. Sioshansi, F. and Webb, J. (2019). Transitioning from conventional to electric vehicles: The effect of cost and environmental drivers on peak oil demand. Economic Analysis and Policy, 61, 7–15. https://doi.org/10.1016/j.eap.2018.12.005
55. Sovacool, B.K. (2016). How long will it take? Conceptualizing the temporal dynamics of energy transitions. Energy Research & Social Science, 13, 202–215. https://doi.org/10.1016/j.erss.2015.12.020
56. Sovacool, B.K. and Griffiths, S. (2020). Culture and low-carbon energy transitions. Nature Sustainability, 3, 685–693. https://doi.org/10.1038/s41893-020-0519-4
57. Tüpraş. (2022). 2022 integrated report. Retrieved from https://tprstaticfilessa.blob.core.windows.net/assets/uploads/srrapor/2022_tupras_entegre_rapor.pdf
58. Ugwu, M.C. and Adewusi, A.O. (2024). Navigating legal and policy challenges in the energy transition: Case studies from the United States and Nigeria. International Journal of Applied Research in Social Sciences, 6, 506–517. https://doi.org/10.51594/ijarss.v6i4.988
59. Voland, N., Saad, M.M. and Eicker, U. (2022). Public policy and incentives for socially responsible new business models in market-driven real estate to build green projects. Sustainability, 14, 7071. https://doi.org/10.3390/su14127071
60. Wang, K., Ouyang, L. and Wang, Y. (2023). Study of energy transition paths and the impact of carbon emissions under the dual carbon target. Sustainability, 15, 1967. https://doi.org/10.3390/su15031967
61. Yurtsever, O., Celik, M.C. and Ozil, E. (2023). Estimation of the cost of converting all road transportation vehicles in Turkey to net zero emitting electrical vehicles by 2035 (SSRN Paper No. 4663375). https://doi.org/10.2139/ssrn.4663375
62. Zhang, Y. (2023). The economic impact of global warming. Highlights of Business, Economics, and Management, 15, 8–11. https://doi.org/10.54097/hbem.v15i.9220