IDEAS home Printed from https://ideas.repec.org/a/gam/jsusta/v17y2025i11p5115-d1670584.html
   My bibliography  Save this article

Forecasting Air Pollutant Emissions Using Deep Sparse Transformer Networks: A Case Study of the Ekibastuz Coal-Fired Power Plant

Author

Listed:
  • Yurii Andrashko

    (Department of System Analysis and Optimization Theory, Uzhhorod National University, 88000 Uzhhorod, Ukraine)

  • Oleksandr Kuchanskyi

    (Department of Computational and Data Science, Astana IT University, Astana 010000, Kazakhstan
    Department of Information Control Systems and Technologies, Uzhhorod National University, 88000 Uzhhorod, Ukraine
    Department of Biomedical Cybernetics, National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”, 03056 Kyiv, Ukraine)

  • Andrii Biloshchytskyi

    (Department of Administration, Astana IT University, Astana 010000, Kazakhstan
    Department of Information Technology, Kyiv National University of Construction and Architecture, 03037 Kyiv, Ukraine)

  • Alexandr Neftissov

    (Research and Innovation Center “Industry 4.0”, Astana IT University, Astana 010000, Kazakhstan)

  • Svitlana Biloshchytska

    (Department of Computational and Data Science, Astana IT University, Astana 010000, Kazakhstan
    Department of Information Technology, Kyiv National University of Construction and Architecture, 03037 Kyiv, Ukraine)

Abstract

It is important to predict air pollutant emissions from coal-fired power plants using real-time technological parameters to improve environmental efficiency. Since the relationship between emissions and parameters is nonlinear, machine learning models are needed to forecast emissions under various boiler operating modes. This study develops and tests Deep Sparse Transformer Networks for predicting pollutant time series, accounting for long-term dependencies. Data were collected from a 4000 MW coal-fired power plant in Ekibastuz, Kazakhstan, covering 67,527 records for 14 indicators at 10 min intervals. Fractal R/S analysis confirmed long-term memory in SO 2 , PM 2.5 , and NO x series, guiding window length selection. The results show that the model achieves slightly better accuracy for SO 2 (R 2 0.95–0.38), while NO x and PM 2.5 have similar dynamics (R 2 0.93–0.26). However, accuracy drops notably after 12 points, making the model best suited for short-term forecasts. These findings support environmental monitoring services and help optimize plant parameters, contributing to lower emissions and advancing carbon neutrality goals.

Suggested Citation

  • Yurii Andrashko & Oleksandr Kuchanskyi & Andrii Biloshchytskyi & Alexandr Neftissov & Svitlana Biloshchytska, 2025. "Forecasting Air Pollutant Emissions Using Deep Sparse Transformer Networks: A Case Study of the Ekibastuz Coal-Fired Power Plant," Sustainability, MDPI, vol. 17(11), pages 1-17, June.
  • Handle: RePEc:gam:jsusta:v:17:y:2025:i:11:p:5115-:d:1670584
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2071-1050/17/11/5115/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/2071-1050/17/11/5115/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Kantelhardt, Jan W. & Zschiegner, Stephan A. & Koscielny-Bunde, Eva & Havlin, Shlomo & Bunde, Armin & Stanley, H.Eugene, 2002. "Multifractal detrended fluctuation analysis of nonstationary time series," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 316(1), pages 87-114.
    2. Thompson, James R. & Wilson, James R., 2016. "Multifractal detrended fluctuation analysis: Practical applications to financial time series," Mathematics and Computers in Simulation (MATCOM), Elsevier, vol. 126(C), pages 63-88.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Abdullah, Mohammad & Chowdhury, Mohammad Ashraful Ferdous & Wali Ullah, G.M., 2025. "Asymmetric tail risk dynamics, efficiency and risk spillover among FinTech stocks, cryptocurrencies and traditional assets," Global Finance Journal, Elsevier, vol. 64(C).
    2. Kakinaka, Shinji & Umeno, Ken, 2021. "Exploring asymmetric multifractal cross-correlations of price–volatility and asymmetric volatility dynamics in cryptocurrency markets," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 581(C).
    3. Méndez-Gordillo, Alma Rosa & Cadenas, Erasmo, 2021. "Wind speed forecasting by the extraction of the multifractal patterns of time series through the multiplicative cascade technique," Chaos, Solitons & Fractals, Elsevier, vol. 143(C).
    4. Mendonça, Suzielli M. & Cabella, Brenno C.T. & Martinez, Alexandre S., 2024. "A Multifractal Detrended Fluctuation Analysis approach using generalized functions," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 637(C).
    5. Ghosh, Bikramaditya & Bouri, Elie & Wee, Jung Bum & Zulfiqar, Noshaba, 2023. "Return and volatility properties: Stylized facts from the universe of cryptocurrencies and NFTs," Research in International Business and Finance, Elsevier, vol. 65(C).
    6. Chowdhury, Mohammad Ashraful Ferdous & Abdullah, Mohammad & Alam, Masud & Abedin, Mohammad Zoynul & Shi, Baofeng, 2023. "NFTs, DeFi, and other assets efficiency and volatility dynamics: An asymmetric multifractality analysis," International Review of Financial Analysis, Elsevier, vol. 87(C).
    7. Pawe{l} O'swik{e}cimka & Stanis{l}aw Dro.zd.z & Mattia Frasca & Robert Gk{e}barowski & Natsue Yoshimura & Luciano Zunino & Ludovico Minati, 2020. "Wavelet-based discrimination of isolated singularities masquerading as multifractals in detrended fluctuation analyses," Papers 2004.03319, arXiv.org.
    8. Wang, Hong-Yong & Wang, Tong-Tong, 2018. "Multifractal analysis of the Chinese stock, bond and fund markets," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 512(C), pages 280-292.
    9. Olivares, Felipe & Zanin, Massimiliano, 2022. "Corrupted bifractal features in finite uncorrelated power-law distributed data," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 603(C).
    10. Fousekis, Panos & Tzaferi, Dimitra, 2022. "Price multifractality and informational efficiency in the futures markets of the US soybean complex," Applied Econometrics, Russian Presidential Academy of National Economy and Public Administration (RANEPA), vol. 66, pages 68-84.
    11. Ghazani, Majid Mirzaee & Khosravi, Reza, 2020. "Multifractal detrended cross-correlation analysis on benchmark cryptocurrencies and crude oil prices," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 560(C).
    12. Tao Yin & Yiming Wang, 2021. "Market Efficiency and Nonlinear Analysis of Soybean Futures," Sustainability, MDPI, vol. 13(2), pages 1-10, January.
    13. Emrah Oral & Gazanfer Unal, 2019. "Modeling and forecasting time series of precious metals: a new approach to multifractal data," Financial Innovation, Springer;Southwestern University of Finance and Economics, vol. 5(1), pages 1-28, December.
    14. Abdullah, Mohammad & Chowdhury, Mohammad Ashraful Ferdous & Sulong, Zunaidah, 2023. "Asymmetric efficiency and connectedness among green stocks, halal tourism stocks, cryptocurrencies, and commodities: Portfolio hedging implications," Resources Policy, Elsevier, vol. 81(C).
    15. Sahoo, Sushanta Kumar & Katlamudi, Madhusudhanarao & Pedapudi, Chandra Sekhar, 2024. "Multifractal detrended fluctuation analysis of soil radon in the Kachchh Region of Gujarat, India: A case study of earthquake precursors," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 637(C).
    16. İşcanoğlu-Çekiç, Ayşegül & Gülteki̇n, Havva, 2019. "Are cross-correlations between Turkish Stock Exchange and three major country indices multifractal or monofractal?," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 525(C), pages 978-990.
    17. Lavička, Hynek & Kracík, Jiří, 2020. "Fluctuation analysis of electric power loads in Europe: Correlation multifractality vs. Distribution function multifractality," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 545(C).
    18. L. Telesca & T. Matcharashvili & T. Chelidze & N. Zhukova & Z. Javakhishvili, 2015. "Investigating the dynamical features of the time distribution of the reservoir-induced seismicity in Enguri area (Georgia)," Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards, Springer;International Society for the Prevention and Mitigation of Natural Hazards, vol. 77(1), pages 117-125, May.
    19. Longfeng Zhao & Wei Li & Andrea Fenu & Boris Podobnik & Yougui Wang & H. Eugene Stanley, 2017. "The q-dependent detrended cross-correlation analysis of stock market," Papers 1705.01406, arXiv.org, revised Jun 2017.
    20. Vitanov, Nikolay K. & Sakai, Kenshi & Dimitrova, Zlatinka I., 2008. "SSA, PCA, TDPSC, ACFA: Useful combination of methods for analysis of short and nonstationary time series," Chaos, Solitons & Fractals, Elsevier, vol. 37(1), pages 187-202.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jsusta:v:17:y:2025:i:11:p:5115-:d:1670584. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.