Integrating machine learning algorithm with sewer process model to realize swift prediction and real-time control of HS pollution in sewer systems.

The frequent occurrence of safety incidents in sewer systems due to the emergency toxicity of hydrogen sulfide (HS) necessitate timely and efficient prediction, early warning and real-time control. However, various factors influencing HS generation and emission leads to a substantial computational burden for the existing dynamic sewer process models and fails to timely control the HS exposure risk. The present study proposed a swift prediction model (SPM) that combined the validated dynamic sewer process model (the biofilm-initiated sewer process model, BISM) with a high-speed machine learning algorithm (MLA), achieving accurately and swiftly predict the dissolved sulfide (DS) concentration and HS concentration in a specific sewer network. Based on Gradient Boosting Decision Tree-based SPM, the simulated concentrations of DS and HS are 1.95 mg S/L and 214 ppm, respectively, which are closely to the field-measured values of 1.82 mg S/L and 219 ppm. Notably, SPM achieved a computation time of less than 0.3 s, and a significant improvement over BISM (> 5000 s) for the same task. Moreover, the real-time and dynamic dosing scheme facilitated by SPM outperformed the conventional constant dosing scheme provided by dynamic sewer process model, which significantly improved the HS control completion rate from 69 % to 100 %, and achieved a significant reduction in chemical dosage. In conclusion, the integration of dynamic sewer process models with MLA addresses the inadequacy of monitoring data for MLA training, and thus pursues swift prediction of HS generation and emission, and achieving real-time, effective, and economic control of HS in complex sewer networks.