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

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.