Estimating ammonium changes in pilot and full-scale constructed wetlands using kinetic model, linear regression, and machine learning

Comparative analysis and application of soft sensor models in domestic wastewater treatment for advancing sustainability

This study focuses on the development and evaluation of soft sensor models for predicting NH3-N values in a wastewater treatment process. The study compares the performance of linear regression (LR), neural networks (NN) and random forest regression (RFR) models. The proposed methodology involves optimizing the sequencing batch reactor process using artificial intelligence and an automatic control system. Real-time NH3-N values are obtained by inputting data from electronic conductivity and temperature sensors into the prediction models. Once the predicted NH3-N value falls below the effluent standard, the cycle ends, improving energy efficiency and sustainability by cutting down the agitator and aerator. The research results demonstrate that the RNN-based NH3-N soft sensor built in this study exhibits the best performance, which is promising for wastewater treatment process optimization and evaluation. The results show that sensor model NNR[0.5Y]H exhibits exceptional performance, utilizing recurrent neural network with 5-step input delays. Sensor NNR[0.5Y]H exhibits an R2 of 0.921, an RMSE of 6.110, and an MAE of 4.558. Based on the findings, recurrent neural network (RNN) variants emerge as the most effective modeling technique due to their ability to capture temporal dependencies and handle variable-length sequences. This study provides satisfied performance results for the NNR[0.5Y]H soft sensor model in NH3-N monitoring and process optimization in wastewater treatment, highlighting the effectiveness of recurrent neural networks and their contribution to improving interpretability, accuracy, and adaptability of soft sensor models.

Simplification and simulation of evaluation process for low efficiency constructed wetlands based on principal component analysis and machine learning

The existing performance evaluation process of constructed wetlands (CWs) is complex, with shortcomings in both simplification of method and construction of simulation model, especially for low-efficiency CWs (LECWs, with an average close-degree calculated by the entropy weight method being <0.6). This study presents a case study of LECWs in the Ningxia region (comprising 13 subsurface flow constructed wetlands (SSF CWs) and 7 surface flow constructed wetlands (SF CWs)), employs the entropy weight method (EWM) to construct an evaluation of CW operational efficiency, simplifies evaluation indicators through principal component analysis (PCA), develops two random forest (RF) models to validate the rationality of the simplified indicators, and establishes simulation models by logistic regression (LR). The results demonstrate that the evaluation indicators of CWs can be simplified to chemical oxygen demand (COD) and total nitrogen (TN), with no significant difference observed between the evaluation results and the original model (P < 0.05), thereby indicating reliability. Moreover, the simulation model performs well with R2 values for fitting SSF CWs and SF CWs exceeding 0.8. According to the simulated results of the model, the operational efficiency of LECWs is more significantly affected by the COD removal rates compared to the TN removal rates. In comparison to influent with 0 < COD/TN < 3 and 5 < COD/TN < 8, the operational efficiency of SSF CWs and SF CWs is optimal when COD/TN is between 3 and 5. These research findings may provide valuable support for streamlining evaluation processes and daily management for LECWs.

Nitrate and ammonium removal in constructed wetlands: Experimental insights and zero-dimensional numerical modeling

Constructed wetlands (CWs) have emerged as effective wastewater treatment systems, mimicked natural wetland processes but engineered for enhanced pollutant removal efficiency. Ammonium (NH4+) and nitrate (NO3-) are among common pollutants in wastewater, posing significant environmental and health risks. The primary objective of this study is to compares the performance of CWs using gravel and three sizes of natural pumice, along with phragmites australis, in horizontal and horizontal-vertical CWs for nitrate and ammonium removal in the complementary treatment of domestic wastewater. Additionally, the study aims to develop and validate a numerical model using MATLAB software to predict the removal efficiency of these pollutants, thereby contributing to the optimization of CW design and operation. The model operates as a zero-dimensional model based on the law of mass conservation, treating the wetland as a completely mixed reactor, thus avoiding complexities associated with solute movement in porous media. It accurately could predict removal efficiency of chemical, biochemical, and biological indicators while considering active and passive absorption mechanisms by plant uptake. Notably, the determination of coefficients in the model equation does not rely on potentially error-prone laboratory measurements due to sampling issues. Instead, optimization techniques alongside field data robustly estimate these coefficients, ensuring reliability and practicality. Results indicate that higher pollutant concentrations increase reaction rates, particularly enhancing CW efficiency in ammonium removal. Pumice, especially in larger sizes, exhibits superior absorption due to increased porosity and surface area. Overall, the model accurately predicts nitrates concentrations, demonstrating its potential for CW performance optimization and confirming the significance of effective pollutant removal strategies in wastewater treatment.

Meta-analysis review for pilot and large-scale constructed wetlands: Design parameters, treatment performance, and influencing factors

Despite their longstanding use in environmental remediation, constructed wetlands (CWs) are still topical due to their sustainable and nature-based approach. While research and review publications have grown annually by 7.5 % and 37.6 %, respectively, from 2018 to 2022, a quantitative meta-analysis employing advanced statistics and machine learning to assess CWs has not yet been conducted. Further, traditional statistics of mean ± standard deviation could not convey the extent of confidence or uncertainty in results from CW studies. This study employed a 95 % bootstrap-based confidence interval and out-of-bag Random Forest-based driver analysis on data from 55 studies, totaling 163 cases of pilot and full-scale CWs. The study recommends, with 95 % confidence, median surface hydraulic loading rates (HLR) of 0.14 [0.11, 0.17] m/d for vertical flow-CWs (VF) and 0.13 [0.07, 0.22] m/d for horizontal flow-CWs (HF), and hydraulic retention time (HRT) of 125.14 [48.0, 189.6] h for VF, 72.00 [42.00, 86.28] h for HF, as practical for new CW design. Permutation importance results indicate influent COD impacted primarily on COD removal rate at 21.58 %, followed by HLR (16.03 %), HRT (12.12 %), and substrate height (H) (10.90 %). For TN treatment, influent TN and COD were the most significant contributors at 12.89 % and 10.01 %, respectively, while H (9.76 %), HRT (9.72 %), and HLR (5.87 %) had lower impacts. Surprisingly, while HRT and H had a limited effect on COD removal, they substantially influenced TN. This study sheds light on CWs' performance, design, and control factors, guiding their operation and optimization.