Automated machine learning-based models for predicting and evaluating antibiotic removal in constructed wetlands

Revealing the impacts of the built environment factors on pedestrian-weighted air pollutant concentration using automated and interpretable machine learning

Urban air pollution poses significant health risks, especially to pedestrians due to their proximity to pollutants and lack of physical protection. Understanding the influence of built environment factors is essential to mitigate this pollution and safeguard pedestrian health. However, most existing literature focus primarily on pollutant sources and dispersion dynamics, paying less attention to the factors that affect the extent of pedestrian exposure to pollutants. Additionally, while machine learning has gained traction in urban studies, challenges remain in model optimization and interpretability, leading to limited transparency and reduced clarity in environment strategy development. To address these gaps, this study proposes a methodological framework to measure pedestrian-weighted air pollutant concentrations (PWAPC) and analyze the complex effects of the built environment. The objectives include (1) integrating air pollution and pedestrian volume data to quantify PWAPC levels, and (2) employing automated machine learning (AutoML) and interpretable machine learning (IML) to model PWAPC and evaluate key built environment impacts. A case study on PM2.5 concentrations in Central London demonstrates the efficiency of AutoML in algorithm selection and hyperparameter optimization. Using IML, critical factors such as points of interest (POIs), traffic infrastructure, diversion ratios, betweenness centrality, street canyon effects, and urban greenness are identified. The analysis also reveals non-linear relationships between these factors and PWAPC. This study provides actionable insights for urban planning and environmental management.

Tracing antibiotics in sewers: Concentrations, measurement techniques, and mathematical approaches

Antibiotic contamination in sewer networks has significant environmental and health concerns worldwide, primarily due to its role in promoting bacterial resistance. In this literature review, antibiotic concentrations reported in urban sewers and hospital effluents, techniques for antimicrobial compound detection and quantification, and current modeling strategies are analyzed and discussed based on 91 papers published between 2014 and 2024. One-hundred and nine antibiotic compounds were reported across 80 studies, with sulfonamides, fluoroquinolones, and macrolides being the most frequently detected classes, while amphenicols and aminocyclitols were the least monitored. Advanced analytical techniques such as liquid chromatography and mass spectrometry are the most common approaches used for antibiotic quantification. Modeling efforts remain limited, with kinetic models, Risk Quotient (RQ) assessments, and Wastewater-Based Epidemiology (WBE) representing the main approaches identified. This review compiles 992 reports into a comprehensive dataset intended to support future research, especially for global monitoring, the development of predictive models, and the formulation of regulatory frameworks for managing antibiotic pollution in sewer systems.

Microbial-Guided prediction of methane and sulfide production in Sewers: Integrating mechanistic models with Machine learning

Accurate modeling of methane (CH4) and sulfide (H2S) production in sewer systems was constrained by insufficient consideration of microbial processes under dynamic environmental conditions. This study introduces a microbial-guided machine learning (ML) framework (Micro-ML), which integrates microbial process representations from mechanistic models (microbial information) with ML models. Results indicate that Micro-ML model enhanced predictions of CH4 and H2S production, where microbial information provides more information for model optimization. The feature importance of microbial information performed comparable weightings for 58.12 % and 55.16 %, respectively, but their relative significance in influencing Micro-ML model performance varies considerably. The application of Micro-ML performed great potential in reducing CH4 and H2S production (decreased ∼ 80 % and 90 %). The integrated model not only improves the accuracy of CH4 and H2S predictions but also offers a valuable tool for effective management strategies for sewer systems.

Interpretable causal machine learning optimization tool for improving efficiency of internal carbon source-biological denitrification

Interpretable causal machine learning (ICML) was used to predict the performance of denitrification and clarify the relationships between influencing factors and denitrification. Multiple models were examined, and XG-Boost model provided the best prediction (R2 = 0.8743). Based on the ICML framework, hydraulic retention time (HRT), mixture chemical oxygen demand/total nitrogen (COD/TN = C/N), mixture COD concentration, and pretreatment technology were identified as important features affecting the denitrification performance. Further, tapping point and partial dependence analyses provided the range of key factors that precisely regulate denitrification. In the application analysis, HRT (6-10.5 h), mixture C/N (6-12), and mixture COD concentration (300-600 mg L-1) were the appropriate operating ranges, achieving TN removal of approximately 73 %-77 %. The effluent TN and COD concentrations met the discharge standards for wastewater in China (class 1A) and EU. These findings provide support for regulating excess sludge as internal carbon source to promote denitrification.

Machine learning to guide the use of plasma technology for antibiotic degradation

Antibiotics are misused and discharged into environmental water, posing a constant potential threat to the ecosystem. Utilising plasma's physical and chemical effects to remove antibiotics has emerged as a promising wastewater treatment technology. However, the complexity and high cost of reactor configurations represent significant limitations to the practical application of this technology. Furthermore, evaluating the degradation efficiency of antibiotics necessitates using costly and sophisticated testing instruments, coupled with time-consuming and labour-intensive experiments. The present study developed a generalised model using machine learning algorithms to predict the removal efficiency of antibiotics by a plasma system. Of the eight machine learning algorithms constructed, the ensemble model XGBoost exhibited the highest prediction accuracy, as indicated by a Pearson correlation coefficient of 0.943. This correlation indicates a strong relationship between the predicted removal rates and the experimental values. Moreover, the accuracy of the prediction was enhanced through the utilisation of a multi-model stacking approach. A further quantitative assessment of the key factors affecting the efficiency of the plasma process, and their synergistic effects, is provided by the interpretable analysis of the model's behaviour. It is anticipated that the results will facilitate the design of efficient plasma systems, reduce the need for extensive experimental screening, and improve practical applications in the removal of antibiotic contamination. This provides an informative view of the applications of plasma technology, opening the way for new environmental research questions.

Automated machine learning-aided prediction and interpretation of gaseous by-products from the hydrothermal liquefaction of biomass

Hydrothermal liquefaction (HTL) is a thermochemical conversion technology that produces bio-oil from wet biomass without drying. However, by-product gases will inevitably be produced, and their formation is unclear. Therefore, an automated machine learning (AutoML) approach, automatically training without human intervention, was used to aid in predicting gaseous production and interpreting the formation mechanisms of four gases (CO2, CH4, CO, and H2). Specifically, four accurate optimal single-target models based on AutoML were developed with elemental compositions and HTL conditions as inputs for four gases. Herein, the gradient boosting machine (GBM) performed excellently with train R2 ≥ 0.99 and test R2 ≥ 0.80. Then, the screened GBM algorithm-based ML multi-target models (maximum average test R2 = 0.89 and RMSE = 0.39) were built to predict four gases simultaneously. Results indicated that biomass carbon, solid content, pressure, and biomass hydrogen were the top four factors for gas production from HTL of biomass. This study proposed an AutoML-aided prediction and interpretation framework, which could provide new insight for rapid prediction and revelation of gaseous compositions from the HTL process.

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.

Long-term performance of a deep oxidation pond with horizontal subsurface flow constructed wetland for purification of rural polluted river water

A full-scale deep oxidation pond with horizontal subsurface flow constructed wetland (DOP-HSCWs) was constructed and used to investigate the nutrient removal and establish a practical inversion prediction model. The high long-term performances of nearly 7 years were obtained with the average removal efficiencies of 76.48 ± 10.11% (chemical oxygen demand, COD), 60.61 ± 29.21% (ammonia nitrogen, NH4+-N), 54.04 ± 21.92% (total phosphorus, TP) and 88.44 ± 6.86% (suspended solids, SS), respectively. The removal efficiency actually increased after 2016 with outflow concentrations lower as compared to initial phase of operation. The effluent concentration in autumn were obviously higher than that in other seasons because of high influent loadings. The Flaml model achieved good performance demonstrating the ability to predict water quality of DOP-HSCWs without human intervention. In addition, COD, NH4+-N, TP concentration of effluent can be significantly affected by SS concentration of influent according to the generalized additive model (p < 0.001). Compared with HSCWs, the DOPs was mainly contributed to pollutant removal. In summer, Cyanobacteria, Cyanobacteria and Proteobacteria were dominated in DOPs, while Proteobacteria was dominated in winter. Although the relative abundance of Proteobacteria in anaerobic zone decreased by 14.99%, the relative abundance of Firmicutes and Chloroflexi increased by nearly 10%, which ensured decontamination effect of the DOPs. Proteobacteria was also dominated in HSCWs, but it was lower than that in DOPs. This study indicated that DOP-HSCWs can achieve a sustainably excellent purification of rural polluted river water during the long period of operation.

Impact analysis of hydraulic loading rate and antibiotics on hybrid constructed wetland systems: Insight into the response to decontamination performance and environmental-associated microbiota

Hybrid constructed wetlands (HCWs) are a promising solution for water ecology and environmental treatment, not only for conventional types of water pollution but also for antibiotics. Among the critical parameters for wetlands, the hydraulic loading rate (HLR) is especially important given the challenges of antibiotics treatment and frequent extreme rainfall. To investigate the removal performance of different HLRs on nutrients and antibiotics, as well as the response of antibiotics to nutrient removal, and the impact of HLRs on microbial communities, new HCWs with vertical flow constructed wetlands (VFCWs) and floating constructed wetlands (FCWs) in series were built. The results of the study showed that: (1) HCWs are highly effective in removing chemical oxygen demand (COD), NH4+-N, NO2--N, and total phosphorus (TP) at low HLR (L_HLR), with removal efficiencies as high as 97.8%, 99.6%, 100%, and 80.5%. However, high HLR (H_HLR) reduced their removal efficiencies; (2) The average removal efficiency of fluoroquinolones (FQs) under different HLRs was consistently high, at 99.9%, while the average removal efficiency of macrolides (MLs) was 96.3% (L_HLR) and 88.4% (H_HLR). The removal efficiency of sulfonamides (SAs) was susceptible to HLRs, and the removal of antibiotics occurred mainly in the rhizosphere zone of wetland; (3) High concentrations of antibiotics in HCWs were found to inhibit and poison plant growth and to reduce the removal efficiency of TP by 12%. However, they had a minor effect on the removal efficiency of carbon and nitrogen nutrients; (4) H_HLR altered the diversity and abundance of microbial communities in different compartments of the wetland and also reduced the relative abundance of Bacillus, Hydrogenophaga, Nakamurella, Denitratisoma and Acidovorax genera, which are involved in denitrification and phosphorus removal processes. This alteration in microbial communities was one of the main reasons for the reduced performance of nitrogen and phosphorus removal.

Evaluation of pollutant removal efficiency of urban stormwater wet ponds and the application of machine learning algorithms

Wet ponds have been extensively used for controlling stormwater pollutants, such as sediment and nutrients, in urban watersheds. The removal of pollutants relies on a combination of physical, chemical, and biological processes. It is crucial to assess the performance of wet ponds in terms of removal efficiency and develop an effective modeling scheme for removal efficiency prediction to optimize water quality management. To achieve this, a two-year field program was conducted at two wet ponds in Calgary, Alberta, Canada to evaluate the wet ponds' performance. Additionally, machine learning (ML) algorithms have been shown to provide promising predictions in datasets with intricate interactions between variables. In this study, the generalized linear model (GLM), partial least squares (PLS) regression, support vector machine (SVM), random forest (RF), and K-nearest neighbors (KNN) were applied to predict the outflow concentrations of three key pollutants: total suspended solids (TSS), total nitrogen (TN), and total phosphorus (TP). Generally, the concentrations of inflow pollutants in the two study ponds are highly variable, and a wide range of removal efficiencies are observed. The results indicate that the concentrations of TSS, TN, and TP decrease significantly from the inlet to outlet of the ponds. Meanwhile, inflow concentration, rainfall characteristics, and wind are important indicators of pond removal efficiency. In addition, ML algorithms can be an effective approach for predicting outflow water quality: PLS, GLM, and SVM have shown strong potential to capture the dynamic interactions in wet ponds and predict the outflow concentration. This study highlights the complexity of pollutant removal dynamics in wet ponds and demonstrates the potential of data-driven outflow water quality prediction.