Carbon Footprint Tracker Using IoT and AI for Vehicle Emission Control

Abstract

This project focuses on developing an IoT and AI-based Carbon Footprint Tracker for vehicle emission control. The system continuously monitors exhaust gases such as CO, CO?, and hydrocarbons (HC) using gas sensors (MQ135, MQ7, MQ2) interfaced with an ESP32 microcontroller. The collected sensor data is transmitted to a cloud database for real-time analysis. Using AI algorithms, the system classifies vehicles as low or high emitters and provides instant alerts through a Progressive Web App (PWA) when emission levels exceed permissible limits.The application also offers maintenance recommendations and trend visualization, enabling users to track their vehicle’s environmental impact. This integrated system promotes predictive maintenance, fuel efficiency, and compliance with emission standards. Overall, it contributes to reducing pollution and supports sustainable transportation through smart, data-driven monitoring.

Introduction

The project addresses the growing problem of vehicular pollution, which traditional emission tests like PUC fail to monitor continuously. With advancements in IoT and AI, the proposed system—“Carbon Footprint Tracker Using IoT and AI for Vehicle Emission Control”—aims to monitor exhaust gases in real time, analyze pollution levels intelligently, and provide instant alerts and maintenance suggestions through a Progressive Web App (PWA). This promotes eco-friendly transportation and ensures timely detection of harmful emissions such as CO, CO?, and hydrocarbons.

The research problem centers on developing an automated system that overcomes the limitations of periodic emission checks by integrating real-time sensing and AI-based analysis. The project contributes a low-cost, portable IoT device using MQ-series gas sensors and an ESP32 microcontroller, coupled with cloud analytics and AI classification models to identify high-emitting vehicles. A PWA interface displays live data, alerts, and predictive maintenance recommendations, making the solution practical, accessible, and user-friendly.

The paper is organized into sections covering related work, system design, implementation methods, testing, and future scope. The literature review highlights prior research in IoT-based monitoring, AI-driven prediction, and environmental analytics. While earlier studies explore IoT sensing, AI modeling, or user adoption separately, they lack a unified framework for continuous vehicular emission monitoring. Existing systems also tend to be reactive, rely on static datasets, or lack user-centered interfaces.

The identified research gaps include limited integration of IoT and AI, lack of real-time predictive intelligence, insufficient user accessibility, and poor scalability. The proposed system addresses these gaps by combining real-time IoT data acquisition, AI-based emission prediction, cloud connectivity, and an interactive PWA, offering a comprehensive solution for sustainable and intelligent vehicle emission control.

Conclusion

The proposed Carbon Footprint Tracker Using IoT and AI for Vehicle Emission Control offers a practical and intelligent solution for real-time vehicular emission monitoring. By integrating IoT sensors, cloud communication, and AI analytics, the system accurately detects pollutants, classifies emission levels, and provides predictive maintenance alerts. The results demonstrate high accuracy, low latency, and strong usability, proving the system’s potential to promote eco-friendly driving and reduce carbon emissions. Overall, the framework establishes a scalable and cost-effective foundation for future smart transportation and sustainability initiatives.

References

[1] S. Li and X. Liu, “Exploring the Influencing Factors of Carbon Footprint Tracking Application Usage Intention,” IEEE Transactions on Green Computing, vol. 8, no. 4, pp. 215–224, 2024. [2] B. Chaudhari, R. Patil, and S. Joshi, “Vehicle Emission Monitoring and Control using IoT,” YMER Journal of Engineering and Technology, vol. 14, no. 2, pp. 45–53, 2024. [3] A. Gupta, N. Sharma, and R. Verma, “Integration of IoT and Artificial Intelligence for Smart Environmental Monitoring Systems,” International Journal of Advanced Research in Computer Science (IJARCS), vol. 14, no. 2, pp. 55–61, 2023. [4] M. Patel, D. Shah, and R. Mehta, “Predictive Analytics for Vehicle Emission Control using Machine Learning Techniques,” International Journal of Innovative Research in Science, Engineering and Technology (IJIRSET), vol. 12, no. 4, pp. 120–128, 2024. [5] E. Yildiz and S. Ersoy, “Organic Data-Driven Approach for Environmental IoT Systems and LLMs,” arXiv Preprint, arXiv:2403.15472, 2024. [6] C. Bryant, M. Felice, and T. Briscoe, “Grammatical Error Correction: A Survey of the State of the Art,” Computational Linguistics, MIT Press, vol. 49, no. 3, pp. 567–589, 2023

Copyright

Copyright © 2025 Neer A. Patel, Atharv M. Kasar, Tanmay S. Lokhande, Prof. S. R. Bedse. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.