RESUMEN
The denitrifying sulfur (S) conversion-associated enhanced biological phosphorus removal (DS-EBPR) process for treating saline wastewater is characterized by its unique microbial ecology that integrates carbon (C), nitrogen (N), phosphorus (P), and S biotransformation. However, operational instability arises due to the numerous parameters and intricates bacterial interactions. This study introduces a two-stage interpretable machine learning approach to predict S conversion-driven P removal efficiency and optimize DS-EBPR process. Stage one utilized the XGBoost regression model, achieving an R2 value of 0.948 for predicting sulfate reduction (SR) intensity from anaerobic parameters with feature engineering. Stage two involved the CatBoost classification and regression model integrating anoxic parameters with the predicted SR values for predicting P removal, reaching an accuracy of 94% and an R2 value of 0.93, respectively. This study identified key environmental factors, including SR intensity (20-45 mg S/L), influent P concentration (<9.0 mg P/L), mixed liquor volatile suspended solids (MLVSS)/mixed liquor suspended solids (MLSS) ratio (0.55-0.72), influent C/S ratio (0.5-1.0), anoxic reaction time (5-6 h), and MLSS concentration (>6.50 g/L). A user-friendly graphic interface was developed to facilitate easier optimization and control. This approach streamlines the determination of optimal conditions for enhancing P removal in the DS-EBPR process.
Asunto(s)
Carbono , Aprendizaje Automático , Nitrógeno , Fósforo , Azufre , Aguas Residuales , Fósforo/metabolismo , Nitrógeno/metabolismo , Azufre/metabolismo , Aguas Residuales/química , Carbono/metabolismo , Biotransformación , Ecosistema , Eliminación de Residuos Líquidos/métodos , DesnitrificaciónRESUMEN
Anaerobic fermentation (AF) has been identified as a promising method of transforming waste activated sludge (WAS) into high-value products (e.g., short-chain fatty acids (SCFAs)). This study developed thiosulfate/FeCl3 pre-treatment and investigated the effects of different thiosulfate/FeCl3 ratios (S:Fe = 3:1, 3:2, 1:1, 3:4 and 3:5) on SCFA production and sulfur transformation during the AF of WAS. At a S:Fe ratio of 1:1, the maximal SCFA yield (933.3 mg COD/L) and efficient H2S removal (96.5 %) were obtained. S:Fe ratios ≤ 1:1 not only benefited hydrolysis and acidification but largely mitigated H2S generation. These results were supported by the enriched acidogens and reduced sulfur-reducing bacteria (SRB). Molecular ecological network analysis further revealed that the keystone taxon (g_Saccharimonadales) was found in S:Fe = 1:1, together with reductions in associations among methanogens, acidogens and SRB. This work provides a strategy for enhancing high-value product recovery from WAS and minimising H2S emissions.