IDEAS home Printed from https://ideas.repec.org/a/eee/renene/v270y2026ics0960148126007329.html

Interpretable ANN-SHAP framework for multi-objective optimization of CH4 and H2S in full-scale anaerobic digestion

Author

Listed:
  • Shirzad Gavabari, Amirhosein
  • Zamir, Seyed Morteza
  • Nosrati, Mohsen

Abstract

Optimizing biogas energy content while limiting corrosive hydrogen sulfide (H2S) remains a key challenge in anaerobic digestion (AD). This study introduces a novel framework combining an interpretable artificial neural network (ANN), Shapley additive explanations (SHAP), and a multi-objective evolutionary algorithm (AGE-MOEA) to simultaneously predict and optimize methane (CH4) and H2S concentrations in biogas from a full-scale wastewater treatment plant (WWTP). The ANN, after hyperparameter tuning, achieved R2 = 0.78 ± 0.05 (CH4) and 0.79 ± 0.04 (H2S). SHAP identified temperature as the primary driver of CH4, while primary sludge (PS) and alkalinity dominated H2S formation. AGE-MOEA generated a Pareto front illustrating different options between CH4 maximization and H2S suppression. A balanced operating point (56.4% CH4, 4980 ppm H2S) increased CH4 by 7.6% and reduced H2S by 11.6% without exceeding the H2S concentration threshold of 5000 ppm for on-site desulfurization unit. The integrated ANN–SHAP–MOEA framework provides a transparent, data-driven tool to enhance biogas quality in data-constrained AD environments.

Suggested Citation

  • Shirzad Gavabari, Amirhosein & Zamir, Seyed Morteza & Nosrati, Mohsen, 2026. "Interpretable ANN-SHAP framework for multi-objective optimization of CH4 and H2S in full-scale anaerobic digestion," Renewable Energy, Elsevier, vol. 270(C).
    • Handle: RePEc:eee:renene:v:270:y:2026:i:c:s0960148126007329
    DOI: 10.1016/j.renene.2026.125906
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0960148126007329
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.renene.2026.125906?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

    for a different version of it.

    More about this item

    Keywords

    ;
    ;
    ;
    ;
    ;

    Statistics

    Access and download statistics

    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:renene:v:270:y:2026:i:c:s0960148126007329. 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.

    We have no bibliographic references for this item. You can help adding them by using 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.journals.elsevier.com/renewable-energy .

    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.