An ensemble model for accurate prediction of key water quality parameters in river based on deep learning methods.

Deep learning models provide a more powerful method for accurate and stable prediction of water quality in rivers, which is crucial for the intelligent management and control of the water environment. To increase the accuracy of predicting the water quality parameters and learn more about the impact of complex spatial information based on deep learning models, this study proposes two ensemble models TNX (with temporal attention) and STNX (with spatio-temporal attention) based on seasonal and trend decomposition (STL) method to predict water quality using geo-sensory time series data. Dissolved oxygen, total phosphorus, and ammonia nitrogen were predicted in short-step (1 h, and 2 h) and long-step (12 h, and 24 h) with seven water quality monitoring sites in a river. The ensemble model TNX improved the performance by 2.1%-6.1% and 4.3%-22.0% relative to the best baseline deep learning model for the short-step and long-step water quality prediction, and it can capture the variation pattern of water quality parameters by only predicting the trend component of raw data after STL decomposition. The STNX model, with spatio-temporal attention, obtained 0.5%-2.4% and 2.3%-5.7% higher performance compared to the TNX model for the short-step and long-step water quality prediction, and such improvement was more effective in mitigating the prediction shift patterns of long-step prediction. Moreover, the model interpretation results consistently demonstrated positive relationship patterns across all monitoring sites. However, the significance of seven specific monitoring sites diminished as the distance between the predicted and input monitoring sites increased. This study provides an ensemble modeling approach based on STL decomposition for improving short-step and long-step prediction of river water quality parameter, and understands the impact of complex spatial information on deep learning model.

Degradation of organic pollutants by the Cl-/PMS process.

The viewpoints on whether high concentrations of chloride ion (Cl-) promote or inhibit the oxidation activity of activated persulfates are still inconclusive. Furthermore, the degradation of organic pollutants by the persulfates in the presence of high Cl- concentrations without any activation medium has not yet been studied. In this work, the efficiency and mechanism of degradation of organic pollutants such as carbamazepine (CBZ), sulfadiazine (SDZ), and phenol (PN) by Cl--activated PMS (denoted as Cl-/PMS) were investigated. Results showed that Cl- could effectively activate PMS for the complete removal of CBZ, SDZ, and PN with reaction kinetic constants of 0.4516 min-1, 0.01753 min-1, and 0.06805 min-1, respectively. Parameters such as PMS dose, Cl- concentration, solution pH, and initial concentrations of organic pollutants that affect the degradation efficiencies of the Cl-/PMS process were optimized. Unlike conventional activated persulfates, it was confirmed that the free chlorine was the main active species in the Cl-/PMS process. Finally, the degradation by-products of CBZ and SDZ as well as their toxicity were detected, and a possible degradation pathway for CBZ and SDZ was proposed. Though higher toxic chlorinated by-products were generated, the Cl-/PMS process was still an efficient oxidation method for the removal of organic pollutants in aqueous solutions which contain high concentrations of Cl-.

Modeling of truncated normal distribution for estimating hydraulic parameters in water distribution systems: taking nodal water demand as an example.

The normal probability density function (PDF) is widely used in parameter estimation in the modeling of dynamic systems, assuming that the random variables are distributed at infinite intervals. However, in practice, these random variables are usually distributed in a finite region confined by the physical process and engineering practice. In this study, we address this issue through the application of truncated normal PDF. This method avoids a non-differentiable problem inherited in the truncated normal PDF at the truncation points, a limitation that can limit the use of analytical methods (e.g., Gaussian approximation). A data assimilation method with the derived formula is proposed to describe the probability of parameter and measurement noise in the truncated space. In application to a water distribution system (WDS), the proposed method leads to estimating nodal water demand and hydraulic pressure key to hydraulic and water quality model simulations. Application results to a hypothetical and a large field WDS clearly show the superiority of the proposed method in parameter estimation for WDS simulations. This improvement is essential for developing real-time hydraulic and water quality simulation and process control in field applications when the parameter and measurement noise are distributed in the finite region.