CO2 emission estimation in Central Asian countries by use of artificial intelligent methods

Balzhan Azibek ^a, Andrii Biloshchytskyi ^a, Mohammad Alhuyi Nazari ^b,

Nurkhat Zhakiyev ^a*

---

^a Astana IT University, Mangilik El avenue, 55/11, Business center EXPO, block C1, Astana, 010000, Kazakhstan
^b University of Tehran, Enghelab Sq., 16th Azar St., Tehran, 1417935840, Iran

Email: nzhakiyev@gmail.com

Balzhan Azibek: balzhan.azibek@astanait.edu.kz; Andrii Biloshchytskyi: a.b@astanait.edu.kz; Mohammad Alhuyi Nazari: nazari.mohammad.a@ut.ac.ir

https://doi.org/10.29258/CAJSCR/2024-R1.v3-2/1-23.eng

September 30, 2024

Abstract

Energy consumption and shares of different types of energy sources in the total energy supply play a critical role in CO2 emissions in various countries. Aside from the energy-related factors, economic indicators such as Gross Domestic Product (GDP) can also influence emissions. In the present study, shares of different energy sources in total energy supply and GDP were utilized as inputs to propose a model for estimating CO2 emissions in three Central Asian states, namely Kazakhstan, Uzbekistan, and Turkmenistan. In addition to the modelling outputs, the article likewise describes important characteristics of energy systems in target countries. Based on the comparison of CO2 emissions per GDP unit, the study allowed identifying that this index in the target countries exceeds the global average, which necessitates urgent actions to reduce emissions. The input data for the research were obtained from the International Energy Agency (IEA) and World Bank. The study applied the Group Method of Data Handling (GMDH) and the Multilayer Perceptron (MLP) method. Both models showed significant performance in emissions estimation; however, according to the calculated values for the applied criteria, it was concluded that the GMDH led to better exactness compared to the MLP. The mean absolute relative deviations of the GMDH and MLP modes were approximately 3.69% and 4.28%, respectively. The R2 value of the mentioned models were 0.9936 and 0.9929, respectively. In the majority of the cases for both models, relative deviations between the predicted and actual CO2 emission were in the range of ±5%.

Download the Paper

Available in English

For citation: Azibek, B., Biloshchytskyi, A., Nazari, M., Zhakiyev, M. (2024). CO2 emission estimation in Central Asian countries by use of artificial intelligent methods. Central Asian Journal of Sustainability and Climate Research. https://doi.org/10.29258/CAJSCR/2024-R1.v3-2/1-23.eng

Rerefences

Ahmadi, M. H., Dehghani Madvar, M., Sadeghzadeh, M., Rezaei, M. H., Herrera, M., & Shamshirband, S. (2019). Current Status Investigation and Predicting Carbon Dioxide Emission in Latin American Countries by Connectionist Models. Energies, 12(10), 1916. https://doi.org/10.3390/en12101916

Ahmadi, M. H., Jashnani, H., Chau, K. W., Kumar, R., & Rosen, M. A. (2019). Carbon dioxide emissions prediction of five Middle Eastern countries using artificial neural networks. Energy Sources, Part A: Recovery, Utilization and Environmental Effects. https://doi.org/10.1080/15567036.2019.167 9914

Alhuyi Nazari, M., Mukhtar, A., Yasir, A. S. H. M., Rashidi, M. M., Ahmadi, M. H., Blazek, V., Prokop, L., & Misak, S. (2023). Applications of intelligent methods in solar heaters: an updated review. In Engineering Applications of Computational Fluid Mechanics (Vol. 17, Issue 1). Taylor and Francis Ltd. https://doi.org/10.1080/19942060.2023.2229882

Alhuyi Nazari, M., Salem, M., Mahariq, I., Younes, K., & Maqableh, B. B. (2021). Utilization of Data- Driven Methods in Solar Desalination Systems: A Comprehensive Review. Frontiers in Energy Research, 0, 541. https://doi.org/10.3389/FENRG.2021.742615

Altikat, S. (2021). Prediction of CO2 emission from greenhouse to atmosphere with artificial neural networks and deep learning neural networks. International Journal of Environmental Science and Technology, 18(10), 3169–3178. https://doi.org/10.1007/s13762-020-03079-z

Betting Big on Renewables. (n.d.). USAID. https://www.usaid.gov/stories/betting-big-on-renewables#:~:text=From 2018 to 2020%2C USAID,the road for a year.

Carbon Capture, Utilisation and Storage. (n.d.). IEA. https://www.iea.org/energy-system/carbon-capture-utilisation-and-storage

CO2 Emissions in 2023 A new record high, but is there light at the end of the tunnel? (2024).

Decree of the President of the Republic of Uzbekistan “On measures to radically improve the management system of the fuel and energy industry of the Republic of Uzbekistan” dated 01.02.2019 №UP- 5646. (2022). IEA. https://www.iea.org/policies/13314-decree-of-the-president-of-the-republic-of-uzbekistan-on-measures-to-radically-improve-the-management-system-of-the-fuel-and-energ­y-industry-of-the-republic-of-uzbekistan-dated-01022019-up-5646

Dossumbekov, Y. K., Zhakiyev, N., Nazari, M. A., Salem, M., & Abdikadyr, B. (2024). Sensitivity analysis and performance prediction of a micro plate heat exchanger by use of intelligent approaches. International Journal of Thermofluids, 22(February), 100601. https://doi.org/10.1016/j. ijft.2024.100601

Elbaz, K., Shen, S., Zhou, A., Yin, Z., & Lyu, H. (2021). Prediction of Disc Cutter Life During Shield Tunneling with AI via the Incorporation of a Genetic Algorithm into a GMDH-Type Neural Network. Engineering, 7(2), 238–251. https://doi.org/10.1016/j.eng.2020.02.016

Electric Vehicles. (2023). IEA. https://www.iea.org/energy-system/transport/electric-vehicles

Energy. (2023). CAREC. https://www.carecprogram.org/?page_id=16#:~:text=Key Projects,support growth in ongoing trade.

Energy efficiency classes of buildings. (2022). IEA. https://www.iea.org/policies/7040-energy-efficiency-classes-of-buildings

Energy Statistics Data Browser. (n.d.-a). IEA. https://www.iea.org/data-and-statistics/data-tools/ energy-statistics-data-browser?country=KAZ

Energy Statistics Data Browser. (n.d.-b). IEA. https://www.iea.org/data-and-statistics/data-tools/ energy-statistics-data-browser?country=UZB

Energy Statistics Data Browser. (n.d.-c). IEA. https://www.iea.org/data-and-statistics/data-tools/ energy-statistics-data-browser?country=TKM

Executive summary. (n.d.). IEA. https://www.iea.org/reports/kazakhstan-2022/executive-summary

Farlow, S. J. (2020). Self-Organizing Methods in Modeling: GMDH Type Algorithms. CRC Press, Boca Raton.

Filik, Ü. B., & Filik, T. (2017). Wind Speed Prediction Using Artificial Neural Networks Based on Multiple Local Measurements in Eskisehir. Energy Procedia, 107, 264–269. https://doi.org/10.1016/J. EGYPRO.2016.12.147

Filipović, S., Orlov, A., & Panić, A. A. (2024). Key forecasts and prospects for green transition in the region of Central Asia beyond 2022. Energy, Sustainability and Society, 14(1), 25. https://doi. org/10.1186/s13705-024-00457-0

García, S., Luengo, J., & Herrera, F. (2015). Data Preprocessing in Data Mining (Vol. 72). Springer International Publishing. https://doi.org/10.1007/978-3-319-10247-4

García, S., Ramírez-Gallego, S., Luengo, J., Benítez, J. M., & Herrera, F. (2016). Big data preprocessing: methods and prospects. Big Data Analytics, 1(1), 9. https://doi.org/10.1186/s41044-016-0014-0

GDP (current US$) – Kazakhstan. (n.d.). WorldBank. https://data.worldbank.org/indicator/NY.GDP. MKTP.CD?locations=KZ

GDP (current US$) – Turkmenistan. (n.d.). WorldBank. https://data.worldbank.org/indicator/NY.GDP. MKTP.CD?locations=TM

GDP (current US$) – Uzbekistan. (n.d.). WorldBank. https://data.worldbank.org/indicator/NY.GDP. MKTP.CD?locations=uz

Ghalandari, M., Forootan Fard, H., Komeili Birjandi, A., & Mahariq, I. (2020). Energy-related carbon dioxide emission forecasting of four European countries by employing data-driven methods. Journal of Thermal Analysis and Calorimetry, 1–10. https://doi.org/10.1007/s10973-020-10400-y

Heat Pumps. (n.d.). IEA. https://www.iea.org/energy-system/buildings/heat-pumps

KAZAKHSTAN: Law No. 541-IV of 2012 on Energy Saving and Energy Efficiency (2019 Ed.). (2019). Asia- Pacific Energy. https://policy.asiapacificenergy.org/node/135

Kim, M., & Okuyucu, O. (2022). Prediction of Undrained Shear Strength by the GMDH-Type Neural Network Using SPT-Value and Soil Physical Properties. Materials, 15, 6385. https://doi.org/ https://doi.org/10.3390/ ma15186385

Komeili Birjandi, A., Fahim Alavi, M., Salem, M., Assad, M. E. H., & Prabaharan, N. (2022a). Modeling carbon dioxide emission of countries in southeast of Asia by applying artificial neural network. International Journal of Low-Carbon Technologies, 17, 321–326. https://doi.org/10.1093/ijlct/ ctac002

Komeili Birjandi, A., Fahim Alavi, M., Salem, M., Assad, M. E. H., & Prabaharan, N. (2022b). Modeling carbon dioxide emission of countries in southeast of Asia by applying artificial neural network. International Journal of Low-Carbon Technologies, 17, 321–326. https://doi.org/10.1093/ijlct/ ctac002

Kuziboev, B., Saidmamatov, O., Khodjaniyazov, E., Ibragimov, J., Marty, P., Ruzmetov, D., Matyakubov, U., Lyulina, E., & Ibadullaev, D. (2024). CO2 Emissions, Remittances, Energy Intensity and Economic Development: The Evidence from Central Asia. Economies, 12(4), 95. https://doi.org/10.3390/ economies12040095

Law of the Republic of Uzbekistan “On the use of renewable energy sources” dated May 21, 2019 No. ZRU-539. (2022). IEA. https://www.iea.org/policies/13310-law-of-the-republic-of-uzbekistan-on-the-use-of-renewable-energy-sources-dated-may-21-2019-no-zru-539

Luo, X. J., Oyedele, L. O., Ajayi, A. O., Akinade, O. O., Owolabi, H. A., & Ahmed, A. (2020). Feature extraction and genetic algorithm enhanced adaptive deep neural network for energy consumption prediction in buildings. Renewable and Sustainable Energy Reviews, 131, 109980. https://doi. org/10.1016/J.RSER.2020.109980

M. K., A. N., & V., M. A. (2020). Role of energy use in the prediction of CO2 emissions and economic growth in India: evidence from artificial neural networks (ANN). Environmental Science and Pollution Research, 27(19), 23631–23642. https://doi.org/10.1007/s11356-020-08675-7

Nationally Determined Contribution (NDC) to the Paris Agreement (2022 Update): Turkmenistan. (n.d.). IEA. https://www.iea.org/policies/17050-nationally-determined-contribution-ndc-to-the-paris-agreement-2022-update-turkmenistan

Navarro, R. I. (2013). Study of a neural network-based system for stability augmentation of an airplane Annex 1 Introduction to Neural Networks and Adaptive Neuro-Fuzzy Inference Systems (ANFIS).

Oh, S., & Pedrycz, W. (2002). The design of self-organizing Polynomial Neural Networks. 141, 237–258.

On protection of the atmospheric air. (2022). IEA. https://www.iea.org/policies/11440-on-protection-of-the-atmospheric-air

Pindoriya, N. M., Singh, S. N., & Singh, S. K. (2008). An adaptive wavelet neural network-based energy price forecasting in electricity markets. IEEE Transactions on Power Systems, 23(3), 1423–1432. https://doi.org/10.1109/TPWRS.2008.922251

Population, total – Kazakhstan. (n.d.). WorldBank. https://data.worldbank.org/indicator/SP.POP. TOTL?locations=KZ

Population, total – Turkmenistan. (n.d.). WorldBank. https://data.worldbank.org/indicator/SP.POP. TOTL?locations=TM

Population, total – Uzbekistan. (n.d.). WorldBank. https://data.worldbank.org/indicator/SP.POP. TOTL?locations=UZ

Radovanović, M., Filipović, S., & Andrejević Panić, A. (2021). Sustainable energy transition in Central Asia: status and challenges. Energy, Sustainability and Society, 11(1), 49. https://doi.org/10.1186/ s13705-021-00324-2

Renewables. (n.d.). IEA. https://www.iea.org/energy-system/renewables

Rezaei, M. H., Sadeghzadeh, M., Alhuyi Nazari, M., Ahmadi, M. H., & Astaraei, F. R. (2018a). Applying GMDH artificial neural network in modeling CO2 emissions in four nordic countries. International Journal of Low-Carbon Technologies, 13(3), 266–271. https://doi.org/10.1093/ijlct/cty026

Rezaei, M. H., Sadeghzadeh, M., Alhuyi Nazari, M., Ahmadi, M. H., & Astaraei, F. R. (2018b). Applying GMDH artificial neural network in modeling CO2 emissions in four nordic countries. International Journal of Low-Carbon Technologies, 13(3), 266–271. https://doi.org/10.1093/ijlct/cty026

Şahin, M., & Erol, R. (2017). A Comparative Study of Neural Networks and ANFIS for Forecasting Attendance Rate of Soccer Games. Mathematical and Computational Applications 2017, Vol. 22, Page 43, 22(4), 43. https://doi.org/10.3390/MCA22040043

The Law About Support the Use of Renewable Energy Sources (amended). (2022). IEA. https://www. iea.org/policies/5407-the-law-about-support-the-use-of-renewable-energy-sources-amended

The Outlook for the Development of Renewable Energy in Uzbekistan. (2014).

Transition to renewable energy sources: economic benefits for entrepreneurs in Kazakhstan. (2024). UNDP. https://www.undp.org/kazakhstan/stories/transition-renewable-energy-sources-economic-benefits-entrepreneurs-kazakhstan

Turkmenistan. (n.d.). IEA. https://www.iea.org/countries/turkmenistan

Turmunkh, B.-E. (2021). Renewable and Non-Renewable Energy Consumption, Carbon Dioxide Emissions, and Economic Growth: Empirical Evidence from Central Asian Countries. Journal of Economics and Development Studies, 9(1). https://doi.org/10.15640/jeds.v9n1a7

UNDP continues to support Turkmenistan in improving energy efficiency and developing renewable energy sources. (n.d.). IEA. https://www.undp.org/turkmenistan/press-releases/undp-continues-support-turkmenistan-improving-energy-efficiency-and-developing-renewable-energy-sources

USAID Energizes Uzbekistan’s First Green Hydrogen Hub. (n.d.). USAID. https://uz.usembassy.gov/ usaid-energizes-uzbekistans-first-green-hydrogen-hub/

USAID Power Central Asia. (n.d.). IEA. https://www.usaid.gov/central-asia-regional/fact-sheets/ usaid-power-central-asia

Uzbekistan. (n.d.). IEA. https://www.iea.org/countries/uzbekistan

Uzbekistan (12/08). (n.d.). U.S. Department of State. https://2009-2017.state.gov/outofdate/bgn/ uzbekistan/113251.htm

Xiu, Z. Wei. (2022). Environmental implications of economic transition in Central Asia: A study of energy consumption and carbon emissions. Top Academic Journal of Economics and Statistics, 7(3), 19–39.

Yuldoshboy, S., Karimov, M., & Kuralbaev, J. (2022). The association between CO2 and economic growth in Central Asian countries: Panel data approach. Journal of Positive School Psychology, 5587–5601.

Zhakiyev, N., Khamzina, A., Zhakiyeva, S., De Miglio, R., Bakdolotov, A., & Cosmi, C. (2023). Optimization Modelling of the Decarbonization Scenario of the Total Energy System of Kazakhstan until 2060. Energies, 16(13), 5142. https://doi.org/10.3390/en16135142