Call For Paper Volume: V, Issue: 08 | AUGUST 2026 | International Journal of Advanced Trends in Engineering and Management (IJATEM)
Volume V | Issue 2 | 2026 | Paper ID: IJATEM-V05I02P5

Explainable Vehicle 〖CO〗_2 Emission Prediction Using a Hybrid TabNet and Deep Residual MLP Network

, D. Lakshmi

The adverse effects of vehicles that emit Carbon Dioxide (CO₂) on air, causes global warming, reduced air quality and climate change which is necessary for emphasizing the need of advanced and sustainable solutions. Explainable Artificial Intelligence (XAI) plays a major role in predicting and monitoring CO₂ emission on air which is employed with deep learning network for better performance in CO₂ emission prediction. In this paper, dataset is processed initially to remove noise obtained from environment which followed by data visualization that analyse the dataset. Encoding the feature takes place to convert categorical data to numerical form in which the dataset obtained undergoes training and testing phase. Then model selection is done using structure that integrates TabNet model with deep residual Multilayer Perceptron (MLP) that paves a way for accurate measurements and provides clarity in understanding complication faced by environments due to CO₂ emission in vehicles. Features that are segmented and extracted are processed by TabNet classifier that aids in perfect decision making and attention-based feature selection. SHapley Additive exPlanations (SHAP) which is categorized in XAI, addresses model interpretability and transparency in predicting CO₂ emission. The proposed technique analysed using CO₂ emission dataset, achieves improved accuracy and works efficiently than other conventional approaches. This study facilitates decision making based on evidence for better development in urban transportations, which integrates feature extraction and improved predictive model.

Greenhouse Gases, Deep Residual MLP Network, Co2 emission, TabNet, Explainable AI (XAI), Shapley additive exPlanations (SHAP).

  • [1] Neng Ayu Herawati; Asyraf Atthariq Putra Gary; Erna Hikmawati; Kridanto Surendro, Year: 2024, “A Hybrid Predictive Model as an Emission Reduction Strategy Based on Power Plants’ Fuel Consumption Activity”, in IEEE Access, Vol: 12, pp. 47119-47133.

  • [2] Omar Farrag; Ahmad Mansour; Baraa Abed; Amr Abu Alhaj; Taha Landolsi; Abdul-Rahman Al-Ali, Year: 2025, “IVEMPS: IoT-Based Vehicle Emission Monitoring and Prediction System”, in IEEE Access, Vol: 13, pp. 95628-95646.

  • [3] Pankaj Verma; Krishna Gandhi; Salma Idris; Faten S. Alamri; Muhammad I. Khan, Year: 2026, “STDSE-Net: A GIS-Driven AI Framework for Dynamic Ensemble-Based Energy Emission Prediction”, in IEEE Access, Vol: 14, pp. 4305-4326.

  • [4] Pritam Singh Balai; Asaruddin Sheikh; Garima Rabha; Samiran Das; Bhaba Krishna Kuli; Mohit Raj, Year: 2025, “Revolutionizing agricultural machinery: The role of AI, IoT, and renewable energy in enhancing efficiency and sustainability”, International Journal of Scientific Research in Science and Technology, Vol: 12, No: 2, pp. 813–830.

  • [5] Prema Nedungadi; Simi Surendran; Kai-Yu Tang; Raghu Raman, Year: 2024, “Big data and AI algorithms for sustainable development goals: A topic modeling analysis”, IEEE Access, pp. 1.

  • [6] Sundus Munir; Manas Ranjan Pradhan; Sagheer Abbas; Muhammad Adnan Khan, Year: 2024, “Energy Consumption Prediction Based on LightGBM Empowered With eXplainable Artificial Intelligence”, in IEEE Access, Vol: 12, pp. 91263-91271.

  • [7] Hyemin Kim; Jinhyuk Park; Dongbeom Kim; Chulmin Jun, Year: 2025, “Cooperative Control of Intersection Traffic Signals Based on Multi-Agent Reinforcement Learning for Carbon Dioxide Emission Reduction”, in IEEE Access, Vol: 13, pp. 33485-33495.

  • [8] Muhammad Ali; Dost Muhammad Khan; Huda M. Alshanbari; Omalsad H. Odhah, Year: 2025, “Forecasting Carbon Dioxide Emission Using Hybrid Machine Learning and Nonlinear Data Decomposition Methods”, in IEEE Access, Vol: 13, pp. 212942-212958.

  • [9] Rohit Ravi; P. Madhavan, Year: 2026, “MCAF_TabNet: A Multiscale Convolutional–Attention Fusion Network With TabNet Classifier for Interpretable Heart Sound Analysis”, in IEEE Access, Vol: 14, pp. 34137-34150.

  • [10] Archana Sulekha Devi; Milagres Mary John Britto; Zian Fang; Renjith Gopan; Pawan Singh Jassal; Mohammed MH Qazzaz; Sujan Rajbhandari; Farah Mahdi Al-Sallami, Year: 2024, “Internet-of-Vehicles Network for CO₂ Emission Estimation and Reinforcement Learning-Based Emission Reduction”, in IEEE Access, Vol: 12, pp. 110681-110690.

  • [11] Naghmeh Niroomand; Christian Bach, Year: 2024, “Integrating Machine Learning for Predicting Internal Combustion Engine Performance and Segment-Based CO2 Emissions Across Urban and Rural Settings”, in IEEE Access, Vol: 12, pp. 66223-66236.

  • [12] Mukul Singh; Rahul Kumar Dubey, Year: 2023, “Deep Learning Model Based CO2 Emissions Prediction Using Vehicle Telematics Sensors Data”, in IEEE Transactions on Intelligent Vehicles, Vol: 8, No: 1, pp. 768-777.

  • [13] Liang Zheng; Shenshen Li; Xuefei Hu; Kun Cai; Yang Liu, Year: 2025, “The Downscaling Prediction Algorithm of Traffic Source Carbon Emissions Based on Multisource Remote Sensing Data and Deep Learning”, in IEEE Transactions on Geoscience and Remote Sensing, Vol: 63, pp. 1-18, Art no. 4112018.

  • [14] Talysson Santos; Michel Bessani; Ivan Da Silva, Year: 2023, “Evolving Dynamic Bayesian Networks for CO2 Emissions Forecasting in Multi-Source Power Generation Systems”, in IEEE Latin America Transactions, Vol: 21, No. 9, pp. 1022-1031.