IDEAS home Printed from https://ideas.repec.org/a/eee/appene/v378y2025ipas0306261924022347.html
   My bibliography  Save this article

Sequential gated recurrent and self attention explainable deep learning model for predicting hydrogen production: Implications and applicability

Author

Listed:
  • Ukwuoma, Chiagoziem C.
  • Cai, Dongsheng
  • Ukwuoma, Chibueze D.
  • Chukwuemeka, Mmesoma P.
  • Ayeni, Blessing O.
  • Ukwuoma, Chidera O.
  • Adeyi, Odeh Victor
  • Huang, Qi

Abstract

To meet the difficulties of the current energy environment, hydrogen has enormous potential as a clean and sustainable energy source. Utilizing hydrogen's potential requires accurate hydrogen production prediction. Due to its capacity to identify intricate patterns in data, Machine learning alongside deep learning models has attracted considerable interest from a variety of industries, including the energy industry. Although these models yield an acceptable performance, there is still a need to improve their prediction results. Also, they are inherently black boxes, which makes it difficult to comprehend and interpret their predictions, particularly in important sectors like hydrogen generation. Sequel to the above, a sequential gated recurrent and self-attention network is proposed in this study to enhance hydrogen production prediction. The framework captures both sequential dependencies and contextual information enabling the model to effectively learn and represent temporal patterns in hydrogen production prediction. The biomass gasification dataset is used for the experiment including the Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Coefficient of Determination (R2), Mean Squared Logarithmic Error (MSLE) and Root Mean Squared Logarithmic Error (RMSLE) evaluation metrics. The proposed model recorded an optimal performance with an MAE of 0.102, MSE of 0.027, RMSE of 0.160, R2 of 0.999, MSLE of 0.001, and RMSLE of 0.030 based on K-cross validation. Among the input features, the percentage of plastics in the mixture(wt%) and RSS Particle Size(mm) are identified to be the most influential features in the proposed model prediction as identified by Shapley Additive Explanation (SHAP), Local Interpretable Model-Agnostic Explanations (LIME) and Feature importance plot. With 99.99 % of the data points for H2 production found within the range of reliability, the model demonstrates robust predictive capability with the majority of observations exerting minimal leverage (0 ≤ u ≤ [leverage threshold]) and limited influence (0 ≤ H ≤ [cooks' threshold]) on the predictive outcome using the modified William plot. Furthermore, various visualization approaches like Matthews correlation coefficient and Tarloy charts were adapted for the result explanations. The proposed model results were compared with state-of-the-art models exploring the significance of the proposed model in providing insights into the underlying mechanisms and factors influencing hydrogen production processes hence improving human understanding of the relationships between input factors and hydrogen production outputs as well as bridging the gap between predicted accuracy and interpretability.

Suggested Citation

  • Ukwuoma, Chiagoziem C. & Cai, Dongsheng & Ukwuoma, Chibueze D. & Chukwuemeka, Mmesoma P. & Ayeni, Blessing O. & Ukwuoma, Chidera O. & Adeyi, Odeh Victor & Huang, Qi, 2025. "Sequential gated recurrent and self attention explainable deep learning model for predicting hydrogen production: Implications and applicability," Applied Energy, Elsevier, vol. 378(PA).
  • Handle: RePEc:eee:appene:v:378:y:2025:i:pa:s0306261924022347
    DOI: 10.1016/j.apenergy.2024.124851
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0306261924022347
    Download Restriction: Full text for ScienceDirect subscribers only

    File URL: https://libkey.io/10.1016/j.apenergy.2024.124851?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Khosravi, A. & Machado, L. & Nunes, R.O., 2018. "Time-series prediction of wind speed using machine learning algorithms: A case study Osorio wind farm, Brazil," Applied Energy, Elsevier, vol. 224(C), pages 550-566.
    2. Bai, Zhang & Liu, Qibin & Gong, Liang & Lei, Jing, 2019. "Investigation of a solar-biomass gasification system with the production of methanol and electricity: Thermodynamic, economic and off-design operation," Applied Energy, Elsevier, vol. 243(C), pages 91-101.
    3. Yang, Ren-Xuan & Wu, Shan-Luo & Chuang, Kui-Hao & Wey, Ming-Yen, 2020. "Co-production of carbon nanotubes and hydrogen from waste plastic gasification in a two-stage fluidized catalytic bed," Renewable Energy, Elsevier, vol. 159(C), pages 10-22.
    4. Lou, Siwei & Li, Danny H.W. & Lam, Joseph C. & Chan, Wilco W.H., 2016. "Prediction of diffuse solar irradiance using machine learning and multivariable regression," Applied Energy, Elsevier, vol. 181(C), pages 367-374.
    5. Chen, Hao & Zhang, Chao & Yu, Haizeng & Wang, Zhilin & Duncan, Ian & Zhou, Xianmin & Liu, Xiliang & Wang, Yu & Yang, Shenglai, 2022. "Application of machine learning to evaluating and remediating models for energy and environmental engineering," Applied Energy, Elsevier, vol. 320(C).
    6. Kargbo, Hannah & Harris, Jonathan Stuart & Phan, Anh N., 2021. "“Drop-in” fuel production from biomass: Critical review on techno-economic feasibility and sustainability," Renewable and Sustainable Energy Reviews, Elsevier, vol. 135(C).
    7. Hussain, Sajid & AlAlili, Ali, 2017. "A hybrid solar radiation modeling approach using wavelet multiresolution analysis and artificial neural networks," Applied Energy, Elsevier, vol. 208(C), pages 540-550.
    8. Ma, Zherui & Wang, Jiangjiang & Feng, Yingsong & Wang, Ruikun & Zhao, Zhenghui & Chen, Hongwei, 2023. "Hydrogen yield prediction for supercritical water gasification based on generative adversarial network data augmentation," Applied Energy, Elsevier, vol. 336(C).
    9. Solarte-Toro, Juan Camilo & González-Aguirre, Jose Andrés & Poveda Giraldo, Jhonny Alejandro & Cardona Alzate, Carlos A., 2021. "Thermochemical processing of woody biomass: A review focused on energy-driven applications and catalytic upgrading," Renewable and Sustainable Energy Reviews, Elsevier, vol. 136(C).
    10. Reza Derakhshani & Leszek Lankof & Amin GhasemiNejad & Alireza Zarasvandi & Mohammad Mahdi Amani Zarin & Mojtaba Zaresefat, 2024. "A Novel Sustainable Approach for Site Selection of Underground Hydrogen Storage in Poland Using Deep Learning," Energies, MDPI, vol. 17(15), pages 1-13, July.
    11. Collard, François-Xavier & Blin, Joël, 2014. "A review on pyrolysis of biomass constituents: Mechanisms and composition of the products obtained from the conversion of cellulose, hemicelluloses and lignin," Renewable and Sustainable Energy Reviews, Elsevier, vol. 38(C), pages 594-608.
    12. Gassar, Abdo Abdullah Ahmed & Cha, Seung Hyun, 2021. "Review of geographic information systems-based rooftop solar photovoltaic potential estimation approaches at urban scales," Applied Energy, Elsevier, vol. 291(C).
    13. Wang, Zhangyuan & Zhao, Xudong & Han, Zhonghe & Luo, Liang & Xiang, Jinwei & Zheng, Senglin & Liu, Guangming & Yu, Min & Cui, Yu & Shittu, Samson & Hu, Menglong, 2021. "Advanced big-data/machine-learning techniques for optimization and performance enhancement of the heat pipe technology – A review and prospective study," Applied Energy, Elsevier, vol. 294(C).
    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. Chen, Hao & Zhang, Chao & Yu, Haizeng & Wang, Zhilin & Duncan, Ian & Zhou, Xianmin & Liu, Xiliang & Wang, Yu & Yang, Shenglai, 2022. "Application of machine learning to evaluating and remediating models for energy and environmental engineering," Applied Energy, Elsevier, vol. 320(C).
    2. Devasahayam, Sheila & Albijanic, Boris, 2024. "Predicting hydrogen production from co-gasification of biomass and plastics using tree based machine learning algorithms," Renewable Energy, Elsevier, vol. 222(C).
    3. Mariyam, Sabah & Shahbaz, Muhammad & Al-Ansari, Tareq & Mackey, Hamish. R & McKay, Gordon, 2022. "A critical review on co-gasification and co-pyrolysis for gas production," Renewable and Sustainable Energy Reviews, Elsevier, vol. 161(C).
    4. Zhao, Haitao & Ezeh, Collins I. & Ren, Weijia & Li, Wentao & Pang, Cheng Heng & Zheng, Chenghang & Gao, Xiang & Wu, Tao, 2019. "Integration of machine learning approaches for accelerated discovery of transition-metal dichalcogenides as Hg0 sensing materials," Applied Energy, Elsevier, vol. 254(C).
    5. Zang, Haixiang & Cheng, Lilin & Ding, Tao & Cheung, Kwok W. & Wang, Miaomiao & Wei, Zhinong & Sun, Guoqiang, 2019. "Estimation and validation of daily global solar radiation by day of the year-based models for different climates in China," Renewable Energy, Elsevier, vol. 135(C), pages 984-1003.
    6. Liu, Xiaolei & Lin, Zi & Feng, Ziming, 2021. "Short-term offshore wind speed forecast by seasonal ARIMA - A comparison against GRU and LSTM," Energy, Elsevier, vol. 227(C).
    7. Chen, Wei-Hsin & Lin, Bo-Jhih, 2016. "Characteristics of products from the pyrolysis of oil palm fiber and its pellets in nitrogen and carbon dioxide atmospheres," Energy, Elsevier, vol. 94(C), pages 569-578.
    8. Yang, Yuhan & Wang, Tiancheng & Hu, Hongyun & Yao, Dingding & Zou, Chan & Xu, Kai & Li, Xian & Yao, Hong, 2021. "Influence of partial components removal on pyrolysis behavior of lignocellulosic biowaste in molten salts," Renewable Energy, Elsevier, vol. 180(C), pages 616-625.
    9. Jun Sheng Teh & Yew Heng Teoh & Heoy Geok How & Thanh Danh Le & Yeoh Jun Jie Jason & Huu Tho Nguyen & Dong Lin Loo, 2021. "The Potential of Sustainable Biomass Producer Gas as a Waste-to-Energy Alternative in Malaysia," Sustainability, MDPI, vol. 13(7), pages 1-31, April.
    10. Primaz, Carmem T. & Ribes-Greus, Amparo & Jacques, Rosângela A., 2021. "Valorization of cotton residues for production of bio-oil and engineered biochar," Energy, Elsevier, vol. 235(C).
    11. Kluska, Jacek & Turzyński, Tomasz & Ochnio, Mateusz & Kardaś, Dariusz, 2020. "Characteristics of ash formation in the process of combustion of pelletised leather tannery waste and hardwood pellets," Renewable Energy, Elsevier, vol. 149(C), pages 1246-1253.
    12. Qin, Fanzhi & Zhang, Chen & Zeng, Guangming & Huang, Danlian & Tan, Xiaofei & Duan, Abing, 2022. "Lignocellulosic biomass carbonization for biochar production and characterization of biochar reactivity," Renewable and Sustainable Energy Reviews, Elsevier, vol. 157(C).
    13. Jamil, Basharat & Akhtar, Naiem, 2017. "Comparison of empirical models to estimate monthly mean diffuse solar radiation from measured data: Case study for humid-subtropical climatic region of India," Renewable and Sustainable Energy Reviews, Elsevier, vol. 77(C), pages 1326-1342.
    14. Dong, Zhen & Li, Zhongguo & Liang, Zhongchao & Xu, Yiqiao & Ding, Zhengtao, 2021. "Distributed neural network enhanced power generation strategy of large-scale wind power plant for power expansion," Applied Energy, Elsevier, vol. 303(C).
    15. Lou, Siwei & Li, Danny H.W. & Lam, Joseph C., 2017. "CIE Standard Sky classification by accessible climatic indices," Renewable Energy, Elsevier, vol. 113(C), pages 347-356.
    16. Sitek, Tomáš & Pospíšil, Jiří & Poláčik, Ján & Špiláček, Michal & Varbanov, Petar, 2019. "Fine combustion particles released during combustion of unit mass of beechwood," Renewable Energy, Elsevier, vol. 140(C), pages 390-396.
    17. Jiang, Hou & Zhang, Xiaotong & Yao, Ling & Lu, Ning & Qin, Jun & Liu, Tang & Zhou, Chenghu, 2023. "High-resolution analysis of rooftop photovoltaic potential based on hourly generation simulations and load profiles," Applied Energy, Elsevier, vol. 348(C).
    18. Costa, Marcelo Azevedo & Ruiz-Cárdenas, Ramiro & Mineti, Leandro Brioschi & Prates, Marcos Oliveira, 2021. "Dynamic time scan forecasting for multi-step wind speed prediction," Renewable Energy, Elsevier, vol. 177(C), pages 584-595.
    19. Alam, Mahboob & Bhavanam, Anjireddy & Jana, Ashirbad & Viroja, Jaimin kumar S. & Peela, Nageswara Rao, 2020. "Co-pyrolysis of bamboo sawdust and plastic: Synergistic effects and kinetics," Renewable Energy, Elsevier, vol. 149(C), pages 1133-1145.
    20. Kawale, Harshal D. & Kishore, Nanda, 2019. "Production of hydrocarbons from a green algae (Oscillatoria) with exploration of its fuel characteristics over different reaction atmospheres," Energy, Elsevier, vol. 178(C), pages 344-355.

    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:eee:appene:v:378:y:2025:i:pa:s0306261924022347. 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: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/description#description .

    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.