Structural Regimes and Hybrid Forecasting: EU Greenhouse Gas Emissions Beyond Linear Trends

This study investigates the structural evolution and projected trajectory of greenhouse gas (GHG) emissions across the EU27 from 1990 to 2030. Drawing on official sectoral data and employing a multi-method framework, we combine time series modelling (ARIMA), machine learning (Random Forest), regime-switching analysis, and segmented linear regression to assess past dynamics, detect structural shifts, and forecast future trends. Empirical findings indicate a statistically significant regime change around 2014, marking a transition into a new emissions pattern characterised by decelerated reductions. While the energy sector experienced the most significant decline, agriculture and industry have gained relative prominence, underscoring their growing strategic importance. Hybrid ARIMA–ML forecasts suggest that, under current trajectories, the EU is unlikely to meet its 2030 climate targets without adaptive and sector-specific interventions. The results underscore the limitations of legacy mitigation strategies and reveal a clear need for systemic innovation. Without accelerated action and recalibrated governance, the post-2014 regime risks entrenching a plateau in emissions reductions, jeopardising long-term climate objectives.