Environmental Science and Ecotechnology · 2024 · 19 citations · 58 references
ComputingComputer ScienceEnvironmental EngineeringEnvironmental ModelingMachine LearningWastewater TreatmentNeural NetworksRepresentation LearningWastewater CharacterizationWastewater ChemistryBackpropagationData-driven Corrosion PredictionHybrid Model-data ApproachesMachine Learning For Environmental DataModel Performance AnalysisSewage ContaminantsSewage PollutionSewage Systems
Physical, chemical, and biological processes within sewers significantly alter sewage composition during conveyance. This leads to the formation of sulfide and methane—compounds that contribute to sewer corrosion and greenhouse gas emissions. Reliable modeling of these compounds is essential for effective sewer management, but the development of machine learning (ML) models is hindered by differences in data accessibility and sampling frequencies of water quality variables. Here we present a mechanistically enhanced hybrid (ME-Hybrid) model that combines mechanistic modeling with data-driven approaches. This model harmonizes datasets with varying sampling frequencies and generates synthetic samples for ML training, thereby enhancing the monitoring of methane and sulfide in sewers. The optimal ME-Hybrid model integrates the backpropagation neural network with mechanistic frequency harmonization. We demonstrate that the ME-Hybrid model outperforms pure ML and linear interpolation in capturing fluctuating trends and extremes of sulfide concentrations, achieving a coefficient of determination ( R 2 ) of 0.94. Synthetic samples generated through mechanistic augmentation closely approximate real samples in modeling performance, statistical distribution, and data structure. This enables the model to maintain high predictive accuracy ( R 2 > 0.76) for sulfide even when trained on only 50% of the dataset. Additionally, the ME-Hybrid model successfully assesses sewer methane concentrations with an R 2 of 0.94, validating its applicability and generalization ability. Our results provide a reliable methodological framework for modeling and prediction under data scarcity. By facilitating better monitoring and management of sewer systems, the ME-Hybrid model aids in the development of strategies that minimize environmental impacts, enhance urban resilience, and ultimately lead to sustainable urban water systems. • We develop a hybrid model that integrates mechanistic modeling with machine learning for water quality evaluation. • The model harmonizes datasets with varying sampling frequencies to improve predictive accuracy. • Mechanistic augmentation generates samples that closely match real data in data structure and statistical distribution. • Incorporating synthetic samples reduces the reliance on real samples, enhancing model performance with limited data.
58
Methane formation in sewer systems
Albert Guisasola, David de Haas, Jürg Keller et al. · Water Research · 2007 · 307 citations
Engineering, Environmental Engineering, Environmental Sciences +13
Reducing sewer corrosion through integrated urban water management
Ilje Pikaar, Keshab Sharma, Shihu Hu et al. · Science · 2014 · 262 citations
Natural Sciences, Environmental Engineering, Environmental Sciences +17