Enhancing CO₂ emissions prediction for electric vehicles using Greylag Goose Optimization and machine learning

Area of Science:

• Environmental Science
• Computer Science
• Transportation Engineering

Background:

• Accurate electric vehicle (EV) emissions prediction is vital for global sustainability goals and informed policy decisions.
• Existing forecasting methods require enhancement to meet the demands of environmental impact reduction and resource optimization.

Purpose of the Study:

• To develop a novel approach for improving the accuracy of electric vehicle emissions prediction.
• To integrate the Greylag Goose Optimization (GGO) algorithm with a Multi-Layer Perceptron (MLP) model for enhanced forecasting.

Main Methods:

• Implementation of a novel Greylag Goose Optimization (GGO) algorithm for hyperparameter tuning of a Multi-Layer Perceptron (MLP) model.
• Comparative analysis against established optimization algorithms.
• Application of statistical analyses including ANOVA, sensitivity analysis, and T-test to validate model performance.

Main Results:

• The GGO-optimized MLP model demonstrated superior performance over baseline models and other optimization techniques.
• Achieved minimal error metrics, including high correlation coefficient and low Root Mean Square Error (RMSE) and Mean Squared Error (MSE).
• The developed model provides highly reliable emissions forecasts.

Conclusions:

• The proposed GGO-MLP approach offers a reliable method for electric vehicle emissions forecasting.
• Provides actionable insights for environmental policies, EV adoption strategies, and sustainable transportation system development.
• Enables stakeholders to achieve climate objectives and optimize EV infrastructure planning.