DEVELOPING A HYBRID METHODOLOGICAL APPROACH TO FORECASTING A COUNTRY’S DECARBONIZATION POTENTIAL
DOI:
https://doi.org/10.35774/jee2026.03.468Keywords:
CO 2 emissions, data science, green transformation, Kohonen map, neural networks, nonlinear modeling.Abstract
The high variability of data on decarbonization potential and the poor formalization of these processes require modern hybrid analysis methods. The study proposes an approach that combines Kohonen self-organizing maps (SOM) to identify patterns between countries, as well as linear regression (LR) and a multilayer perceptron (MLP) neural network to forecast the average CO2 emission within clusters. The analysis covers 45 countries over a ten-year period and is based on 12 explanatory indicators. Thus, the scientific methodology based on the integration of clustering and neural network forecasting to model different national decarbonization trajectories. Kohonen maps allowed authors to identify seven groups of countries, which confirms the heterogeneity of the impact of factors and patterns of decarbonization across countries. The research results showed that linear models have limited explanatory power (R² of 0.30 on test data before clustering and 0.61 in average after clustering), while the optimized neural network provides higher forecast accuracy (average R² for all clusters of 0.75 on test data) supporting clusterbased modeling and ability of neural networks to capture nonlinear relationships. The outcomes of the research can be used by policymakers to design and tailor national climate policy and plan energy transitions.
JEL: Q50, C12, C38, C53, C55.
References
Agrafiotis, D. K., & Xu, H. (2002). A self-organizing principle for learning nonlinear manifolds. Proceedings of the National Academy of Sciences, 99(25), 15869–15872. https://doi.org/10.1073/pnas.242424399
Banna, H., Alam, A., Chen, X. H., & Alam, A. W. (2023). Energy security and economic stability: The role of inflation and war. Energy Economics, 126, Article 106949. https://doi.org/10.1016/j.eneco.2023.106949
Belsley, D. A., Kuh, E., & Welsch, R. E. (1980). Regression diagnostics: Identifying influential data and sources of collinearity. Wiley. https://doi.org/10.1002/0471725153
Bielinskyi, A., Soloviev, V., Matviychuk, A., & Bezkorovainyi, V. (2026). Stock market movement forecasting using machine learning and complex network measures. Artificial Intelligence and Applications. https://doi.org/10.47852/bonviewAIA62027537
Breiman, L. (2001). Random forests. Machine learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
Caldara, D., & Iacoviello, M. (2022). Measuring geopolitical risk. American Economic Review, 112(4), 1194–1225. https://doi.org/10.1257/aer.20191823
Cordova, C. H., Portocarrero, M. N. L., Salas, R., Torres, R., Rodrigues, P. C., & LópezGonzales, J. L. (2021). Air quality assessment and pollution forecasting using artificial neural networks in Metropolitan Lima–Peru. Scientific Reports, 11, Article 24232. https://doi.org/10.1038/s41598-021-03650-9
Ding, C., Wang, G., Zhang, X., Liu, Q., & Liu, X. (2021). A hybrid CNN-LSTM model for predicting PM2.5 in Beijing based on spatiotemporal correlation. Environmental and Ecological Statistics, 28, 503–522. https://doi.org/10.1007/s10651-021-00501-8
Encalada-Malca, A. A., Cochachi-Bustamante, J. D., Rodrigues, P. C., Salas, R., & López-Gonzales, J. L. (2021). A spatio-temporal visualization approach of PM 10 concentration data in Metropolitan Lima. Atmosphere, 12(5), Article609. https://doi.org/10.3390/atmos12050609
EnerData. (2026). Total energy consumption. World Energy & Climate Statistics – Yearbook 2026 [Data set]. https://yearbook.enerdata.net/total-energy/worldconsumption-statistics.html
Feng, X., Li, Q., Zhu, Y., Hou, J., Jin, L., & Wang, J. (2015). Artificial neural networks forecasting of PM2.5 pollution using air mass trajectory based geographic model and wavelet transformation. Atmospheric Environment, 107, 118–128. https://doi.org/10.1016/j.atmosenv.2015.02.030
Fu, M., Wang, W., Le, Z., & Khorram, M. S. (2015). Prediction of particular matter concentrations by developed feed-forward neural network with rolling mechanism and gray model. Neural Computing and Applications, 26, 1789–1797. https://doi.org/10.1007/s00521-015-1853-8
Fuinhas, J. A., Belucio, M., Santiago, R., & Betencourt, M. (2025). Are the structure dynamics of capital stock impacting carbon intensity from energy consumption? European insights. Energy, Ecology and Environment, 10, 555–574. https://doi.org/10.1007/s40974-025-00370-y
Geopolitical Risk Index. (n.d.). Final Geopolitical Risk Index [Data set]. https://www.geopriskindex.com/results-final-risk-index/
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, 15(18), Article 13934. https://doi.org/10.3390/su151813934
Hasnain, A., Sheng, Y., Hashmi, M. Z., Bhatti, U. A., Hussain, A., Hameed, M., Marjan, S., Bazai, S. U., Hossain, M. A., Sahabuddin, M., Wagan, R. A., & Zha, Y. (2022). Time series analysis and forecasting of air pollutants based on Prophet forecasting model in Jiangsu Province, China. Frontiers in Environmental Science, 10, Article 945628. https://doi.org/10.3389/fenvs.2022.945628
Haykin, S. S. (2009). Neural Networks and Learning Machines (3rd ed.). Pearson.
Kourentzes, N., Barrow, D. K., & Crone, S. F. (2014). Neural network ensemble operators for time series forecasting. Expert Systems with Applications, 41(9), 4235–4244. https://doi.org/10.1016/j.eswa.2013.12.011
Kumari, S., & Singh, S. K. (2023). Machine learning–based time series models for effective CO 2 emission prediction in India. Environmental Science and Pollution Research, 30(55), 116601–116616. https://doi.org/10.1007/s11356-022-21723-8
Li, S., Xie, G., Ren, J., Guo, L., Yang, Y., & Xu, X. (2020). Urban PM2.5 concentration prediction via attention-based CNN–LSTM. Applied Sciences, 10(6), Article 1953. https://doi.org/10.3390/app10061953
Milone, D. H., Stegmayer, G., Kamenetzky, L., López, P., & Carrari, F. (2013). Clustering biological data with SOMs: On topology preservation in non-linear dimensional reduction. Expert Systems with Applications, 40(9), 3841–3845. https://doi.org/10.1016/j.eswa.2012.12.074
Mussa, A. A. Y., & Khalifa, W. M. S. (2025). MLP enhanced CO2 emission prediction model with LWSSA nature inspired optimization. Scientific Reports, 15, Article 1891. https://doi.org/10.1038/s41598-025-85709-5
Paliwal, M., & Kumar, U. A. (2009). Neural networks and statistical techniques: A review of applications. Expert Systems with Applications, 36(1), 2–17. https://doi.org/10.1016/j.eswa.2007.10.005
Peeters, L., & Dassargues, A. (2006). Comparison of Kohonen’s self-organizing map algorithm and principal component analysis in the exploratory data analysis of a groundwater quality dataset. University of Liège. https://orbi.uliege.be/bitstream/2268/3388/1/publi144-2007.pdf
Singh, S., Kumar, M., Verma, B. K., & Kumar, S. (2026). Optimizing air pollution prediction with random forest algorithm. Aerosol Science and Engineering, 10, 208–221. https://doi.org/10.1007/s41810-025-00292-6
Solci, C. C., Reisen, V. A., & Rodrigues, P. C. (2023). Robust local bootstrap for weakly stationary time series in the presence of additive outliers. Stochastic Environmental Research and Risk Assessment, 37, 2977–2992. https://doi.org/10.1007/s00477-023-02430-3
Taylor, S. J., & Letham, B. (2017). Forecasting at scale. PeerJ Preprints, 5, Article e3190v2. https://doi.org/10.7287/peerj.preprints.3190v2
Wen, T., Liu, Y., Bai, Y. H., & Liu, H. (2023). Modeling and forecasting CO2 emissions in China and its regions using a novel ARIMALSTM model. Heliyon, 9(11), Article e21241. https://www.sciencedirect.com/science/article/pii/S2405844023084499
World Bank. (n.d.). World Development Indicators [Data set]. https://datacatalog.worldbank.org/search/dataset/0037712
Wu, S., Feng, Q., Du, Y., & Li, X. (2011). Artificial neural network models for daily PM 10 air pollution index prediction in the urban area of Wuhan, China. Environmental Engineering Science, 28(5), 357–363. https://doi.org/10.1089/ees.2010.0219
Zhang, G. P. (2003). Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 50, 159–175. https://doi.org/10.1016/S0925-2312(01)00702-0
Zhang, Y., Wang, J., Chen, R., Zhang, S., Liao, X., & Xie, J. (2024). Complementary ARIMA and XGBoost carbon emission timing forecasting methods for different terminal energy consumption industries. In Fifth International Conference on Green Energy, Environment, and Sustainable Development (GEESD 2024) (Vol. 13279, Article 1327946). SPIE Digital Library. https://doi.org/10.1117/12.3044690
Zheng, Y., Liu, F., & Hsieh, H. P. (2013). U-Air: When urban air quality inference meets big data. In R. Ghani, T. E. Senator, P. Bradley, R. Parekh, & J. He, (Eds.), Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 1436–1444). Association for Computing Machinery. https://doi.org/10.1145/2487575.2488188
Zhu, S., Lian, X., Wei, L., Che, J., Shen, X., Yang, L., Qiu, X., Liu, X., Gao, W., Ren, X., & Li, J. (2018). PM2.5 forecasting using SVR with PSOGSA algorithm based on CEEMD, GRNN and GCA considering meteorological factors. Atmospheric Environment, 183, 20–32. https://doi.org/10.1016/j.atmosenv.2018.04.004
Zhytkevych, O., & Brochado, A. (2022). Modeling national decarbonization capabilities using Kohonen maps. Neuro-Fuzzy Modeling Techniques in Economics, 11, 3–24. http://doi.org/10.33111/nfmte.2022.003
Zhytkevych, O., Matviychuk, A., & Kmytiuk, T. (2023). Modeling Nations’ Decarbonisation Potential. In F. Ortiz-Rodríguez, S. Tiwari, P. Usoro Usip, & R. Palma (Eds.), Electronic Governance with Emerging Technologies.EGETC 2023. Communications in Computer and Information Science (Vol. 1888, pp. 60–77). Springer, Cham. https://doi.org/10.1007/978-3-031-43940-7_6
Received: April 5, 2026.
Reviewed: August 6, 2026.
Accepted: September 16, 2026.
Downloads
Published
How to Cite
Issue
Section
License
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
