Neural network prediction model : applied to U.S. industrial greenhouse gas emissions

• Autorzy: Tseng Shih-Hsien , Wang Chia-Hsuan , Duong Thi Ha Trang

Identyfikatory

DOI

10.24425/aep.2025.153754

• Języki publikacji: EN

Abstrakty

EN

This study explores the use of deep learning neural network models for predicting greenhouse gas emissions, focusing on small-sample time-series data sets, an area with limited prior research. It utilizes Recurrent Neural Networks (RNNs), Long Short-Term Memory Networks (LSTMs), Gated Recurrent Units (GRUs), and Transformers combined with Genetic Algorithms to forecast CO₂ emissions from industrial sources in Texas, a major contributor to U.S. greenhouse gas emissions. The analysis is based on the Environmental Protection Agency's (EPA) "Inventory of U.S. Greenhouse Gas Emissions and Sinks" dataset, spanning 1990 to 2020. The results indicate that LSTM and Transformer models are particularly effective, with LSTM outperforming Transformers in computational efficiency by 6.97 times. These findings highlight the potential of LSTM and Transformer models as accurate and stable tools for predicting CO₂ emissions in small-sample time-series data, offering valuable insights for future research and policy development in environmental management.

Słowa kluczowe

EN

deep learning; greenhouse gas emission; GRU; RNN; transformer; time series prediction model

• Wydawca: Institute of Environmental Engineering, Polish Academy of Sciences
• Czasopismo: Archives of Environmental Protection
• Rocznik: 2025
• Tom: Vol. 51, no. 1
• Strony: 103--115
• Opis fizyczny: Bibliogr. 18 poz., tab., wykr.

Twórcy

autor

Tseng Shih-Hsien

• National Taiwan University of Science and Technology, Taiwan

autor

Wang Chia-Hsuan

• National Taiwan University of Science and Technology, Taiwan

autor

Duong Thi Ha Trang

• National Taiwan University of Science and Technology, Taiwan

Bibliografia

• 1. Alibrahim, H. & Ludwig, S. A. (2021, 28 June-1 July 2021). Hyperparameter Optimization: Comparing Genetic Algorithm against Grid Search and Bayesian Optimization. 2021 IEEE Congress on Evolutionary Computation (CEC),
• 2. AlKheder, S. & Almusalam, A. (2022). Forecasting of carbon dioxide emissions from power plants in Kuwait using United States Environmental Protection Agency, Intergovernmental panel on climate change, and machine learning methods. Renewable Energy, 191, pp. 819-827.
• 3. EIA. (2022). Texas State Energy Profile. U.S. Energy Information Administration Retrieved from https://www.eia.gov/state/print.php?sid=TX
• 4. Fang, Z., Yang, H., Li, C., Cheng, L., Zhao, M. & Xie, C. (2021). Prediction of PM2. 5 hourly concentrations in Beijing based on machine learning algorithm and ground-based LiDAR. Archives of Environmental Protection, 47(3).
• 5. Hochreiter, S. & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), pp. 1735-1780.
• 6. Hsu, A., Wang, X., Tan, J., Toh, W. & Goyal, N. (2022). Predicting European cities’ climate mitigation performance using machine learning. Nature Communications, 13(1), 7487. DOI:10.1038/s41467-022-35108-5
• 7. Hyndman, R. J. & Athanasopoulos, G. (2018). Forecasting: principles and practice. OTexts.
• 8. Mitchell, M. (1998). An introduction to genetic algorithms. MIT press.
• 9. Potvin, J.-Y. (1996). Genetic algorithms for the traveling salesman problem. Annals of Operations Research, 63, pp. 337-370.
• 10. Riekstin, A. C., Langevin, A., Dandres, T., Gagnon, G. & Cheriet, M. (2020). Time Series-Based GHG Emissions Prediction for Smart Homes. IEEE Transactions on Sustainable Computing, 5(1), pp. 134-146. DOI:10.1109/TSUSC.2018.2886164
• 11. Rumelhart, D. E., Hinton, G. E. & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323(6088), pp. 533-536.
• 12. Şahin, U. (2019). Forecasting of Turkey's greenhouse gas emissions using linear and nonlinear rolling metabolic grey model based on optimization. Journal of Cleaner Production, 239, 118079.
• 13. Sen, P., Roy, M. & Pal, P. (2016). Application of ARIMA for forecasting energy consumption and GHG emission: A case study of an Indian pig iron manufacturing organization. Energy, 116, pp. 1031-1038.
• 14. Sonata, I. & Heryadi, Y. (2024, 17-18 July 2024). Comparison of LSTM and Transformer for Time Series Data Forecasting. 2024 7th International Conference on Informatics and Computational Sciences (ICICoS),
• 15. Sun, W. & Liu, M. (2016). Prediction and analysis of the three major industries and residential consumption CO2 emissions based on least squares support vector machine in China. Journal of Cleaner Production, 122, pp. 144-153.
• 16. Szeląg, B., Bartkiewicz, L., Studziński, J. & Barbusinski, K. (2017). Evaluation of the impact of explanatory variables on the accuracy of prediction of daily inflow to the sewage treatment plant by selected models nonlinear. Archives of Environmental Protection, 43. DOI:10.1515/aep-2017-0030
• 17. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł. & Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems, 30.
• 18. Yin, L., Sharifi, A., Liqiao, H. & Jinyu, C. (2022). Urban carbon accounting: An overview. Urban Climate, 44, 101195.DOI:10.1016/j.uclim.2022.101195

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).