CO₂ Emission Analysis & Forecasting
A time-series analysis and forecasting project that models global CO₂ emissions using machine learning, feature engineering, and compares recursive and direct prediction strategies.
A time-series analysis and forecasting project that models global CO₂ emissions using machine learning, feature engineering, and compares recursive and direct prediction strategies.
Understanding CO₂ emission trends requires not only historical analysis but also reliable forecasting to anticipate future environmental impact.
Built a system that combines exploratory analysis with machine learning-based forecasting to analyze past trends and predict future emissions.
Global CO₂ emission dataset (Kaggle) covering historical emissions from ~1700 to 2023.
Lag-based baseline model (MAE ≈ 0.35)
Random Forest captured non-linear patterns better, while Linear Regression provided stable trend estimation.
Uses previous predictions as input. More realistic but error accumulates over time.
Predicts future values independently. More stable but less adaptive.
Forecasts indicate slower emission growth and potential stabilization trends, reflecting global sustainability efforts and policy changes.