Time Series Forecasting of Greenhouse Gas Emissions Using Deep Learning

Unofficial AI-generated summary based on the public title and abstract. Not an official translation.

🔬研究者:This paper offers a comparative evaluation of LSTM and Transformer for GHG forecasting, including uncertainty quantification and robustness tests.

🏛政策担当者:The findings can inform the use of AI-driven forecasts for monitoring emission reduction targets and evaluating policy impacts.

Greenhouse gas (GHG) emissions remain a primary driver of global climate change, and accurate forecasting is critical for evaluating climate policies and supporting sustainable development goals. This study conducts a time series analysis in Python using the EDGAR dataset for 1970–2023, explicitly adopting a sectoral scope that covers Agriculture, Buildings, Fuel Exploitation, Industrial Combustion, Power Industry, Processes, Transport, and Waste. Long Short-Term Memory (LSTM) models were developed and evaluated via rolling/expanding-window backtesting, while Monte Carlo Dropout (MCD) was applied to quantify predictive uncertainty. Out-of-distribution (OOD) tests were further used to assess generalization under distributional shifts, and early stopping with learning-rate scheduling was employed to mitigate overfitting. While the LSTM captures the dominant long-term upward trend, its out-of-sample performance is constrained under regime changes and shocks (Test RMSE = 1228.66; MAE = 991.35; R2=−1.0020) and it underperforms a naïve benchmark. Nested rolling-origin results also indicate rapidly increasing errors at longer horizons. In contrast, a Transformer specification improves performance over the last five years (RMSE = 777.21; MAE = 663.39; R2=0.1989). Sectoral findings suggest that short-term declines around 2020 are concentrated in transport and energy-related sectors, while agriculture and industrial/process-related emissions remain relatively stable.

• crossref https://doi.org/10.35378/gujs.1800123first seen 2026-07-25 06:26:27