Time Series Forecasting of Greenhouse Gas Emissions Using Deep Learning

Creative Commons License

Yalciner Cal D., KÜÇÜKSİLLE E. U.

Gazi University Journal of Science, cilt.39, sa.3, ss.1492-1521, 2026 (ESCI, Scopus, TRDizin)

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 39 Sayı: 3
  • Basım Tarihi: 2026
  • Doi Numarası: 10.35378/gujs.1800123
  • Dergi Adı: Gazi University Journal of Science
  • Derginin Tarandığı İndeksler: Emerging Sources Citation Index (ESCI), Scopus, TR DİZİN (ULAKBİM), Academic Search Ultimate (EBSCO), Biomedical Reference Collection: Corporate Edition (EBSCO), Engineering Source (EBSCO)
  • Sayfa Sayıları: ss.1492-1521
  • Anahtar Kelimeler: Greenhouse gas emissions, Long short-term memory, Monte carlo dropout, Out-of-distribution, Time series analysis
  • Açık Arşiv Koleksiyonu: AVESİS Açık Erişim Koleksiyonu
  • Süleyman Demirel Üniversitesi Adresli: Evet

Özet

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.