Authors:
Ahmed J. Obaid, S. Rubin Bose, J. Angelin Jeba, Ezgi Demir, Sebastiana Salerno, Wilhelmus De Wilde
Addresses:
Department of Computer Science, Faculty of Computer Science and Mathematics, University of Kufa, Kufa, Najaf Governorate, Iraq. School of Computer Science and Engineering, SRM Institute of Science and Technology, Ramapuram, Chennai, Tamil Nadu, India. Department of Electronics and Communication Engineering, S.A. Engineering College, Chennai, Tamil Nadu, India. Department of Artificial Intelligence, Lancaster University, Lancaster, England, United Kingdom. Department of Science, Educandato State Maria Adelaide, Palermo, Sicily, Italy. Faculty of Architecture and the Built Environment, Delft University of Technology, Delft, South Holland, Netherlands.
Abstract:
Electric vehicles (EVs) are fast changing global transportation by being efficient, eco-friendly, and sustainable. EVs are gaining popularity in India due to concerns about air pollution and the depletion of fossil fuels. In recent years, EV registrations in Chennai, a key automotive hub, have skyrocketed. Environmental awareness, favourable government legislation, rising gasoline prices, and developments in battery efficiency and charging infrastructure have propelled this growth. The Chennai Electric Vehicle Adoption Prediction project analyses historical EV registration data to identify significant adoption trends and predict future growth. Data from official and public sources is integrated, preprocessed, and feature-engineered for the study. Model performance was improved by derived variables such as car type, brand popularity, gasoline price variance, annual population growth, and charging station count. Due to its robustness, flexibility, and ability to model complex nonlinear relationships among variables, a Random Forest regression model was used. The dataset was split into training and test sets, and performance was assessed using RMSE and R². Experimental results show that regulatory incentives, infrastructural development, and economic considerations greatly influence EV adoption in Chennai. Two-wheelers dominate the EV market due to their affordability and ease for urban commuters. The suggested system accurately predicted adoption patterns with 98% accuracy. The findings highlight the importance of government measures, awareness campaigns, and infrastructural investments in expediting Chennai's transition to cleaner, smarter, and more sustainable urban mobility.
Keywords: Electric Vehicles (EVs); Adoption Prediction; Machine Learning; Random Forest; Sustainable Transportation; Data Analytics; Charging Infrastructure; Government Policies.
Received on: 08/05/2025, Revised on: 01/08/2025, Accepted on: 04/10/2025, Published on: 07/06/2026
DOI: 10.64091/ATIEL.2026.000325
AVE Trends in Intelligent Energy Letters, 2026 Vol. 2 No. 1 , Pages: 54-66