Multi-Country GHG Emissions Forecasting by Sector Using a GCN-LSTM Model
Downloads
This study developed a novel hybrid Graph Convolutional Network–Long Short-Term Memory (GCN–LSTM) model to forecast greenhouse gas (GHG) emissions across multiple country sectors, aiming to enhance climate policy. We analyzed 52 years (1970–2022) of GHG emissions data (CO₂, CH₄, N₂O, F-Gases) from 163 countries and eight sectors (Agriculture, Buildings, Fuel Exploitation, Industrial Combustion, Power Industry, Processes, Transport, Waste), sourced from the EDGAR v8 database. The GCN adjacency matrix captures spatial relationships on a weighted sum of Haversine distance and cosine similarity, while the LSTM models temporal dynamics. Data preprocessing includes min-max scaling and outlier handling with Interquartile Range capping. The model was trained on 70% of the data, validated on 15%, and tested on 15%, using Mean Squared Error (MSE) loss and the Adam optimizer. The performance was evaluated with Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Coefficient of Determination (R²). The GCN–LSTM model outperformed baseline models (ARIMA, Simple LSTM, Stacked LSTM), achieving the lowest MAE (0.0207 in Waste) and highest R² (0.9756 in Waste). Model interpretability highlighted strong regional connections, such as Thailand–Cambodia in the Waste sector, suggesting that spatial and temporal dependencies offer superior forecasting accuracy, informing targeted climate action.
Downloads
[1] Friedlingstein, P., Jones, M. W., O’Sullivan, M., Andrew, R. M., Bakker, D. C. E., Hauck, J., Le Quéré, C., Peters, G. P., Peters, W., Pongratz, J., Sitch, S., Canadell, J. G., Ciais, P., Jackson, R. B., Alin, S. R., Anthoni, P., Bates, N. R., Becker, M., Bellouin, N., … Zeng, J. (2022). Global Carbon Budget 2021. Earth System Science Data, 14(4), 1917–2005. doi:10.5194/essd-14-1917-2022.
[2] Andrew, R. M. (2018). Global CO2 emissions from cement production. Earth System Science Data, 10(1), 195–217. doi:10.5194/essd-10-195-2018.
[3] Luo, R., Wang, J., & Gates, I. (2024). Forecasting Methane Data Using Multivariate Long Short-Term Memory Neural Networks. Environmental Modeling and Assessment, 29(3), 441–454. doi:10.1007/s10666-024-09957-x.
[4] Saunois, M., R. Stavert, A., Poulter, B., Bousquet, P., G. Canadell, J., B. Jackson, R., A. Raymond, P., J. Dlugokencky, E., Houweling, S., K. Patra, P., Ciais, P., K. Arora, V., Bastviken, D., Bergamaschi, P., R. Blake, D., Brailsford, G., Bruhwiler, L., M. Carlson, K., Carrol, M., … Zhuang, Q. (2020). The global methane budget 2000-2017. Earth System Science Data, 12(3), 1561–1623. doi:10.5194/essd-12-1561-2020.
[5] Tian, H., Xu, R., Canadell, J. G., Thompson, R. L., Winiwarter, W., Suntharalingam, P., Davidson, E. A., Ciais, P., Jackson, R. B., Janssens-Maenhout, G., Prather, M. J., Regnier, P., Pan, N., Pan, S., Peters, G. P., Shi, H., Tubiello, F. N., Zaehle, S., Zhou, F., … Yao, Y. (2020). A comprehensive quantification of global nitrous oxide sources and sinks. Nature, 586(7828), 248–256. doi:10.1038/s41586-020-2780-0.
[6] Purohit, P., Höglund-Isaksson, L., Dulac, J., Shah, N., Wei, M., Rafaj, P., & Schöpp, W. (2020). Electricity savings and greenhouse gas emission reductions from global phase-down of hydrofluorocarbons. Atmospheric Chemistry and Physics, 20(19), 11305–11327. doi:10.5194/acp-20-11305-2020.
[7] Shao, Z., Gao, S., Zhou, K., & Yang, S. (2024). A new multiregional carbon emissions forecasting model based on a multivariable information fusion mechanism and hybrid spatiotemporal graph convolution network. Journal of Environmental Management, 352, 119976. doi:10.1016/j.jenvman.2023.119976.
[8] Osobajo, O. A., Otitoju, A., Otitoju, M. A., & Oke, A. (2020). The impact of energy consumption and economic growth on carbon dioxide emissions. Sustainability (Switzerland), 12(19), 7965. doi:10.3390/SU12197965.
[9] Wei, S., Wang, T., & Li, Y. (2017). Influencing factors and prediction of carbon dioxide emissions using factor analysis and optimized least squares support vector machine. Environmental Engineering Research, 22(2), 175–185. doi:10.4491/eer.2016.125.
[10] Chukwunonso, B. P., AL-Wesabi, I., Shixiang, L., AlSharabi, K., Al-Shamma’a, A. A., Farh, H. M. H., Saeed, F., Kandil, T., & Al-Shaalan, A. M. (2024). Predicting carbon dioxide emissions in the United States of America using machine learning algorithms. Environmental Science and Pollution Research, 31(23), 33685–33707. doi:10.1007/s11356-024-33460-1.
[11] Yao, X., Zhang, H., Wang, X., Jiang, Y., Zhang, Y., & Na, X. (2024). Which model is more efficient in carbon emission prediction research? A comparative study of deep learning models, machine learning models, and econometric models. Environmental Science and Pollution Research, 31(13), 19500–19515. doi:10.1007/s11356-024-32083-w.
[12] Agarwal, H., Mahajan, G., Shrotriya, A., & Shekhawat, D. (2024). Predictive Data Analysis: Leveraging RNN and LSTM Techniques for Time Series Dataset. Procedia Computer Science, 235, 979–989. doi:10.1016/j.procs.2024.04.093.
[13] Crespo-Otero, A., Esteve, P., & Zanin, M. (2024). Deep Learning models for the analysis of time series: A practical introduction for the statistical physics practitioner. Chaos, Solitons and Fractals, 187, 115359. doi:10.1016/j.chaos.2024.115359.
[14] Roy, D. S. (2020). Forecasting the Air Temperature at a Weather Station Using Deep Neural Networks. Procedia Computer Science, 178, 38–46. doi:10.1016/j.procs.2020.11.005.
[15] Boubaker, S., Benghanem, M., Mellit, A., Lefza, A., Kahouli, O., & Kolsi, L. (2021). Deep Neural Networks for Predicting Solar Radiation at Hail Region, Saudi Arabia. IEEE Access, 9, 36719–36729. doi:10.1109/ACCESS.2021.3062205.
[16] Hamdan, A., Al-Salaymeh, A., AlHamad, I. M., Ikemba, S., & Ewim, D. R. E. (2023). Predicting future global temperature and greenhouse gas emissions via LSTM model. Sustainable Energy Research, 10(1), 21. doi:10.1186/s40807-023-00092-x.
[17] Sha, M., Emmanuel, S., Bindhu, A., & Mustaq, M. (2024). Intensified greenhouse gas prediction: Configuring Gate with Fine-Tuning Shifts with Bi-LSTM and GRU System. Frontiers in Climate, 6, 1457441. doi:10.3389/fclim.2024.1457441.
[18] García-Duarte, L., Cifuentes, J., & Marulanda, G. (2023). Short-term spatio-temporal forecasting of air temperatures using deep graph convolutional neural networks. Stochastic Environmental Research and Risk Assessment, 37(5), 1649–1667. doi:10.1007/s00477-022-02358-0.
[19] Waqas, M., & Humphries, U. W. (2024). A critical review of RNN and LSTM variants in hydrological time series predictions. MethodsX, 13, 102946. doi:10.1016/j.mex.2024.102946.
[20] Han, Z., Cui, B., Xu, L., Wang, J., & Guo, Z. (2023). Coupling LSTM and CNN Neural Networks for Accurate Carbon Emission Prediction in 30 Chinese Provinces. Sustainability (Switzerland), 15(18), 13934. doi:10.3390/su151813934.
[21] Azzam, A., Sanami, S., & Aghdam, A. G. (2024). Load Forecasting using GNN-LSTM Attention Mechanism with Low-Frequency Data. Proceedings of SysCon 2024 - 18th Annual IEEE International Systems Conference, 1–6. doi:10.1109/SysCon61195.2024.10553600.
[22] Zhang, X., & Wang, D. (2023). A GNN-based Day Ahead Carbon Intensity Forecasting Model for Cross-Border Power Grids. E-Energy 2023 - Proceedings of the 2023 14th ACM International Conference on Future Energy Systems, 361–373. doi:10.1145/3575813.3597346.
[23] Liao, W., Yang, D., Wang, Y., & Ren, X. (2021). Fault diagnosis of power transformers using graph convolutional network. CSEE Journal of Power and Energy Systems, 7(2), 241–249. doi:10.17775/CSEEJPES.2020.04120.
[24] Huang, D., Liu, H., Bi, T., & Yang, Q. (2022). GCN-LSTM spatiotemporal-network-based method for post-disturbance frequency prediction of power systems. Global Energy Interconnection, 5(1), 96–107. doi:10.1016/j.gloei.2022.04.008.
[25] Chen, H., Zhu, M., Hu, X., Wang, J., Sun, Y., Yang, J., Li, B., & Meng, X. (2023). Multifeature Short-Term Power Load Forecasting Based on GCN-LSTM. International Transactions on Electrical Energy Systems, 2023, 8846554. doi:10.1155/2023/8846554.
[26] Azati, Y., Wang, X., Quddus, M., & Zhang, X. (2025). Graph convolutional LSTM algorithm for real-time crash prediction on mountainous freeways. International Journal of Transportation Science and Technology, 18(3), 272–284. doi:10.1016/j.ijtst.2024.07.002.
[27] Li, P., Zhang, T., & Jin, Y. (2023). A Spatio-Temporal Graph Convolutional Network for Air Quality Prediction. Sustainability (Switzerland), 15(9), 7624. doi:10.3390/su15097624.
[28] Friedlingstein, P., O’Sullivan, M., Jones, M. W., Andrew, R. M., Bakker, D. C. E., Hauck, J., Landschützer, P., Le Quéré, C., Luijkx, I. T., Peters, G. P., Peters, W., Pongratz, J., Schwingshackl, C., Sitch, S., Canadell, J. G., Ciais, P., Jackson, R. B., Alin, S. R., Anthoni, P., … Zheng, B. (2023). Global Carbon Budget 2023. Earth System Science Data, 15(12), 5301–5369. doi:10.5194/essd-15-5301-2023.
[29] Chen, C., Guo, J., Zhang, L., Wu, X., & Yang, Z. (2024). Robust multi-scale time series prediction for building carbon emissions with explainable deep learning. Energy and Buildings, 312, 114159. doi:10.1016/j.enbuild.2024.114159.
[30] Pfenning-Butterworth, A., Buckley, L. B., Drake, J. M., Farner, J. E., Farrell, M. J., Gehman, A. L. M., Mordecai, E. A., Stephens, P. R., Gittleman, J. L., & Davies, T. J. (2024). Interconnecting global threats: climate change, biodiversity loss, and infectious diseases. The Lancet Planetary Health, 8(4), e270–e283. doi:10.1016/S2542-5196(24)00021-4.
[31] Stefănescu, C. A., Dobrea, R. C., & Loghin, M. (2022). A Comparative Analysis of Waste Management Systems Used for Environmental Protection: Norway (Oslo) – Zanzibar (Zanzibar). Proceedings of the International Management Conference, 15(1), 195–205. doi:10.24818/Imc/2021/01.19.
[32] Dash, C. S. K., Behera, A. K., Dehuri, S., & Ghosh, A. (2023). An outliers detection and elimination framework in classification task of data mining. Decision Analytics Journal, 6, 100164. doi:10.1016/j.dajour.2023.100164.
[33] Pan, F., Yang, Y., Ji, Y., Li, J., Zhang, J., & Zhong, L. (2024). Application of improved graph convolutional networks in daily-ahead carbon emission prediction. Frontiers in Energy Research, 12, 1371507. doi:10.3389/fenrg.2024.1371507.
[34] Jelti, F., Allouhi, A., & Tabet Aoul, K. A. (2023). Transition Paths towards a Sustainable Transportation System: A Literature Review. Sustainability (Switzerland), 15(21), 15457. doi:10.3390/su152115457.
[35] Yuan, Y., Wang, Y., Chi, Y., & Jin, F. (2020). Identification of key carbon emission sectors and analysis of emission effects in China. Sustainability (Switzerland), 12(20), 1–19. doi:10.3390/su12208673.
[36] Mishra, T., & Nair, P. S. (2024). Advancing Agriculture Predictive Models for Farming Suitability Using Machine Learning. International Journal of Intelligent Systems and Applications in Engineering, 12(5s), 494–502.
[37] Do, T. N., & Burke, P. J. (2023). Is ASEAN ready to move to multilateral cross-border electricity trade? Asia Pacific Viewpoint, 64(1), 110–125. doi:10.1111/apv.12343.
[38] Mele, M., Magazzino, C., Schneider, N., & Nicolai, F. (2021). Revisiting the dynamic interactions between economic growth and environmental pollution in Italy: evidence from a gradient descent algorithm. Environmental Science and Pollution Research, 28(37), 52188–52201. doi:10.1007/s11356-021-14264-z.
[39] Wen, T., Liu, Y., Bai, Y. he, & Liu, H. (2023). Modeling and forecasting CO2 emissions in China and its regions using a novel ARIMA-LSTM model. Heliyon, 9(11), 21241. doi:10.1016/j.heliyon.2023.e21241.
[40] Crippa, M., Guizzardi, D., Muntean, M., Schaaf, E., Dentener, F., Van Aardenne, J. A., Monni, S., Doering, U., Olivier, J. G. J., Pagliari, V., & Janssens-Maenhout, G. (2018). Gridded emissions of air pollutants for the period 1970-2012 within EDGAR v4.3.2. Earth System Science Data, 10(4), 1987–2013. doi:10.5194/essd-10-1987-2018.
[41] Kumari, S., & Singh, S. K. (2023). Machine learning-based time series models for effective CO2 emission prediction in India. Environmental Science and Pollution Research, 30(55), 116601–116616. doi:10.1007/s11356-022-21723-8.
[42] ADBI. (2014). Assessing the costs and benefits of economic integration in Southeast Asia. Asian Development Bank Institute, ADBI Working Paper Series, 483. Available online: https://www.adb.org/sites/default/files/publication/156338/adbi-wp483.pdf (accessed on January 2026).
[43] ADB. (2018). Agricultural cooperation in Southeast Asia: Opportunities and challenges. Asian Development Bank, ADB Briefs, 106. doi:10.22617/TCS189598-2.
- This work (including HTML and PDF Files) is licensed under a Creative Commons Attribution 4.0 International License.
