Predictive modeling of pharmaceutical product removal by a managed aquifer recharge system: Comparison and optimization of models using ensemble learners

A machine learning framework to predict PPCP removal through various wastewater and water reuse treatment trains

The persistence of pharmaceuticals and personal care products (PPCPs) through wastewater treatment and resulting contamination of aquatic environments and drinking water is a pervasive concern, necessitating means of identifying effective treatment strategies for PPCP removal. In this study, we employed machine learning (ML) models to classify 149 PPCPs based on their chemical properties and predict their removal via wastewater and water reuse treatment trains. We evaluated two distinct clustering approaches: C1 (clustering based on the most efficient individual treatment process) and C2 (clustering based on the removal pattern of PPCPs across treatments). For this, we grouped PPCPs based on their relative abundances by comparing peak areas measured via non-target profiling using ultra-performance liquid chromatography-tandem mass spectrometry through two field-scale treatment trains. The resulting clusters were then classified using Abraham descriptors and log K ow as input to the three ML models: support vector machines (SVM), logistic regression, and random forest (RF). SVM achieved the highest accuracy, 79.1%, in predicting PPCP removal. Notably, a 58-75% overlap was observed between the ML clusters of PPCPs and the Abraham descriptor and log K ow clusters of PPCPs, indicating the potential of using Abraham descriptors and log K ow to predict the fate of PPCPs through various treatment trains. Given the myriad of PPCPs of concern, this approach can supplement information gathered from experimental testing to help optimize the design of wastewater and water reuse treatment trains for PPCP removal.

Machine learning-based monitoring and design of managed aquifer rechargers for sustainable groundwater management: scope and challenges

Managed aquifer recharge (MAR) replenishes groundwater by artificially entering water into subsurface aquifers. This technology improves water storage, reduces over-extraction, and ensures water security in water-scarce or variable environments. MAR systems are complex, encompassing various components such as water storage, soil, meteorological factors, groundwater management (GWM), and receiving bodies. Over the past decade, the utilization of machine learning (ML) methodologies for MAR modeling and prediction has increased significantly. This review evaluates all supervised, semi-supervised, unsupervised, and ensemble ML models employed to predict MAR factors and parameters, rendering it the most comprehensive contemporary review on this subject. This study presents a concise and integrated overview of MAR's most effective ML approaches, focusing on design, suitability for water quality (WQ) applications, and GWM. The paper examines performance measures, input specifications, and the variety of ML functions employed in GWM, and highlights prospects. It also offers suggestions for utilizing ML in MAR, addressing issues related to physical aspects, technical advancements, and case studies. Additionally, previous research on ML-based data-driven and soft sensing techniques for MAR is critically evaluated. The study concludes that integrating ML into MAR systems holds significant promise for optimizing WQ management and enhancing the efficiency of groundwater replenishment strategies.

Ensemble water quality forecasting based on decomposition, sub-model selection, and adaptive interval

The prediction of effluent quality for wastewater treatment plants (WWTPs) has caused widespread concern due to its essential role in ensuring water quality standards and reducing energy consumption. However, the complex nonlinearity of WWTPs leads to difficulties in forecasting and less attention to forecast uncertainty. A novel ensemble water quality forecasting (EWQF) system is proposed that incorporates data preprocessing, point prediction and interval prediction. The system provides an accurate prediction of effluent quality and analyses this uncertainty, for enabling feed-forward control of WWTPs. Specifically, the original water quality data is decomposed into subsequences containing more information and less noise based on improved variational modal decomposition (IVMD). The optimal sub-model for each sub-series is selected from six prediction models based on the sub-model selection strategy, and the point prediction results for water quality are obtained by combining the prediction results of the sub-models. Robust and reliable prediction interval construction based on adaptive kernel density estimation. The results demonstrate that the EWQF achieves optimal point prediction results (R2 = 0.955). The EWQF interval prediction achieves the optimal coverage width criterion (CWC) for different confidence intervals and decision objectives. These results demonstrate that EWQF systems can perform excellent point and interval prediction.

Assessing groundwater recharge rates, water quality changes, and agricultural impacts of large-scale water recycling

The over-exploitation and insufficient replenishment of groundwater (GW) have resulted in a pressing need to conserve freshwater and reuse of treated wastewater. To address this issue, the Government of Karnataka launched a large-scale recycling (440 million liters/day) scheme to indirectly recharge GW using secondary treated municipal wastewater (STW) in drought-prone areas of Kolar district in southern India. This recycling employs soil aquifer treatment (SAT) technology, which involves filling surface run-off tanks with STW that intentionally infiltrate and recharge aquifers. This study quantifies the impact of STW recycling on GW recharge rates, levels, and quality in the crystalline aquifers of peninsular India. The study area is characterized by hard rock aquifers with fractured gneiss, granites, schists, and highly fractured weathered rocks. The agricultural impacts of the improved GW table are also quantified by comparing areas receiving STW to those not receiving it, and changes before and after STW recycling were measured. The AMBHAS_1D model was used to estimate the recharge rates and showed a tenfold increase in daily recharge rates, resulting in a significant increase in the GW levels. The results indicate that the surface water in the rejuvenated tanks meets the country's stringent water discharge standards for STW. The GW levels of the studied boreholes increased by 58-73 %, and the GW quality improved significantly, turning hard water into soft water. Land use land cover studies confirmed an increase in the number of water bodies, trees, and cultivated land. The availability of GW significantly improved agricultural productivity (11-42 %), milk productivity (33 %), and fish productivity (341 %). The study's outcomes are expected to serve as a role model for the rest of Indian metro cities and demonstrate the potential of reusing STW to achieve a circular economy and a water-resilient system.

Assessing the algal population dynamics using multiple machine learning approaches: Application to Macao reservoirs

The quality of reservoir water is important to the health and wellbeing of human and animals. Eutrophication is one of the most serious problems threatening the safety of reservoir water resource. Machine learning (ML) approaches are effective tools to understand and evaluate various environmental processes of concern, such as eutrophication. However, limited studies have compared the performances of different ML models to reveal algal dynamics using time-series data of redundant variables. In this study, the water quality data from two reservoirs in Macao were analyzed by adopting various ML approaches, including stepwise multiple linear regression (LR), principal component (PC)-LR, PC-artificial neuron network (ANN) and genetic algorithm (GA)-ANN-connective weight (CW) models. The influence of water quality parameters on algal growth and proliferation in two reservoirs was systematically investigated. The GA-ANN-CW model demonstrated the best performance in reducing the size of data and interpreting the algal population dynamics data, which displayed higher R-squared, lower mean absolute percentage error and lower root mean squared error values. Moreover, the variable contribution based on ML approaches suggest that water quality parameters, such as silica, phosphorus, nitrogen, and suspended solid have a direct impact on algal metabolisms in two reservoirs' water systems. This study can expand our capacity in adopting ML models in predicting algal population dynamics based on time-series data of redundant variables.