Time Series Forecasting of Greenhouse Gas Emissions Using Deep Learning
- 1 September 2026
- journal article
- Published by Gazi University Journal of Science in Gazi University Journal of Science
- Vol. 39 (3) , 1492-1521
Abstract
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.Keywords
Funding Information
- This study did not require approval from any ethics committee.
This publication has 62 references indexed in Scilit:
- An examination of daily CO2 emissions prediction through a comparative analysis of machine learning, deep learning, and statistical modelsEnvironmental Science and Pollution Research, 2025
- Tests for equal forecast accuracy under heteroskedasticityJournal of Applied Econometrics, 2024
- Forecasting Methane Data Using Multivariate Long Short-Term Memory Neural NetworksEnvironmental Modeling & Assessment, 2024
- Forecast evaluation for data scientists: common pitfalls and best practicesData Mining and Knowledge Discovery, 2022
- Statistical Analysis with Missing Data, Third Edition2019
- A note on the validity of cross-validation for evaluating autoregressive time series predictionComputational Statistics & Data Analysis, 2018
- A new approach to testing forecast predictive accuracyMeteorological Applications, 2015
- Time Series Analysis2008
- Methods for imputation of missing values in air quality data setsAtmospheric Environment, 2004
- Early Stopping - But When?1998