RESUMO
Prediction of influent characteristics, before any treatment takes place, is of great importance to the operation and management of wastewater treatment plants (WWTPs). In this study, four machine-learning models, including multilayer perceptron (MLP), long short-term memory network (LSTM), K-nearest neighbour (KNN), and random forest (RF), are introduced to utilize real-time wastewater data from three WWTPs in North America (i.e., Tres Rios, Woodward, and one confidential plant) for predicting hourly influent characteristics. Input variables are selected using an autocorrelation analysis and a variable importance measure from RF. Both univariate and multivariate analyses are investigated to improve model accuracy. The performances of one- and multiple-step-ahead models are compared. With a short prediction horizon, all the models derived from both univariate and multivariate analyses show excellent performance. It was found that the performance deterioration as the prediction horizon expands could be mitigated significantly by including extra variables, such as meteorological variables. This work can provide valuable support for the high-temporal-resolution prediction of wastewater influent characteristics for WWTPs. The proposed models can also bridge the gap between data and decision-making in the wastewater sector.
Assuntos
Águas Residuárias , Purificação da Água , Monitoramento Ambiental , Aprendizado de Máquina , Redes Neurais de ComputaçãoRESUMO
Sustainable water management is essential to increasing water availability and decreasing water pollution. The wastewater sector is expanding globally and beginning to incorporate technologies that recover nutrients from wastewater. Nutrient recovery increases energy consumption but may reduce the demand for nutrients from virgin sources. We estimate the increase in annual global energy consumption (1,100 million GJ) and greenhouse gas emissions (84 million t CO2e) for wastewater treatment in the year 2030 compared to today's levels to meet sustainable development goals. To capture these trends, integrated assessment and computable general equilibrium models that address the energy-water nexus must evolve. We reviewed 16 of these models to assess how well they capture wastewater treatment plant energy consumption and GHG emissions. Only three models include biogas production from the wastewater organic content. Four explicitly represent energy demand for wastewater treatment, and eight include explicit representation of wastewater treatment plant greenhouse gas emissions. Of those eight models, six models quantify methane emissions from treatment, five include representation of emissions of nitrous oxide, and two include representation of emissions of carbon dioxide. Our review concludes with proposals to improve these models to better capture the energy-water nexus associated with the evolving wastewater treatment sector.