Table 1.
NRCan dataset-based related work for fuel consumption and CO2 estimation.
Fig 1.
Methodology (A) Overall framework, (B) flowchart.
Table 2.
Descriptive statistics of the combined datasets.
Fig 2.
Average fuel consumption per vehicle brand.
Fig 3.
Average CO2 emission per vehicle brand.
Fig 4.
Heatmap of quantitative independent variables.
Table 3.
Tuned hyperparameters for consumption and emission models.
Table 4.
Energy consumption prediction results.
Fig 5.
Fuel consumption performance metrics of all ML models.
Fig 6.
Actual versus predicted consumption plots: (A) Linear regression, (B) Ridge, (C) Lasso, (D) Elastic Net, (E) SVM, (F) DT, (G) GP, (H) RF, (I) GB, (J) HGB, (K) XGBoost, (L) CatBoost, (M) LightGBM.
Table 5.
CO2 emission prediction results.
Fig 7.
CO2 Emission performance metrics of all ML models.
Fig 8.
Actual versus predicted CO2 emissions plots: (A) Linear regression, (B) Ridge, (C) Lasso, (D) Elastic Net, (E) SVM, (F) DT, (G) GP, (H) RF, (I) GB, (J) HGB, (K) XGBoost, (L) CatBoost, (M) LightGBM.
Fig 9.
Statistical significance testing (A) Fuel consumption, (B) CO2 prediction.
Table 6.
CO2 emission prediction comparison with previous studies.
Table 7.
Fuel consumption prediction comparison with previous studies.