Microbial-Guided prediction of methane and sulfide production in Sewers: Integrating mechanistic models with Machine learning

Abstract

Accurate modeling of methane (CH₄) and sulfide (H₂S) production in sewer systems was constrained by insufficient consideration of microbial processes under dynamic environmental conditions. This study introduces a microbial-guided machine learning (ML) framework (Micro-ML), which integrates microbial process representations from mechanistic models (microbial information) with ML models. Results indicate that Micro-ML model enhanced predictions of CH₄ and H₂S production, where microbial information provides more information for model optimization. The feature importance of microbial information performed comparable weightings for 58.12 % and 55.16 %, respectively, but their relative significance in influencing Micro-ML model performance varies considerably. The application of Micro-ML performed great potential in reducing CH₄ and H₂S production (decreased ∼ 80 % and 90 %). The integrated model not only improves the accuracy of CH₄ and H₂S predictions but also offers a valuable tool for effective management strategies for sewer systems.

Keywords: Data Driven; Microbial Information; Sewers; machine learning; wastewater management.