Enumerating virus particles (VPs) at different stages of the wastewater treatment process or along the distribution network is essential for ensuring high performance and reducing public health risks. Herein, we aimed to (i) optimize the flow virometry (FVM) protocol for use in wastewater matrices, (ii) correlate FVM data with specific virus genera of interest, and (iii) develop machine learning (ML) models for determining total VP concentration. We identified and tested a comprehensive set of parameters to determine the optimal conditions for wastewater FVM. Specifically, we tested various sample preprocessing steps to enhance FVM detection sensitivity, including the use of different nucleic acid staining dyes, surfactant addition and concentration optimization, glutaraldehyde fixation, and the effect of sample freezing before FVM analysis. Spearman's rank correlation of FVM data with virus genera concentration using a conventional qPCR-based method in 206 samples showed a positive correlation for all five virus genera, ranging from 0.21 to 0.44 (p < 0.01). The extreme gradient-boosting (XGB) model using easily accessible physiochemical water parameters (such as turbidity, electroconductivity, total dissolved solids, total suspended solids, pH, chemical oxygen demand, and concentrations of nitrate nitrogen, nitrite nitrogen, and ammonium nitrogen) as input data outperformed the random forest (RF) model and can be used to estimate total virus count across all types of wastewater matrices as output data. Furthermore, XGB achieved a better root mean square error in the four treatment processes (influent, aerobic, sand, and MBR) by a mean of 23 % than RF in model development. This study demonstrates that FVM, combined with ML, can significantly enhance monitoring capabilities by accurately estimating VP concentrations across diverse wastewater matrices.

Reduced bacteria concentrations in wastewater is a key indicator of the efficacy of water resource recovery facilities (WRRFs). However, monitoring the presence of bacterial concentrations in real time at each stage of the WRRF is challenging as it requires taking and processing water samples offline. Although few studies have been proposed to predict bacterial concentrations using data-driven models, generalizing these models to unseen data from different WRRFs remains challenging. This paper proposes a calibration approach based on neural networks to adapt the optimal models across various WRRFs in Saudi Arabia for bacterial estimation at the influent and effluent stages. The calibration relies on the out-of-distribution (OOD) framework of the physiochemical water parameters (e.g., pH, COD, TDS, turbidity, conductivity) with a design threshold chosen based on the data distribution of the received unseen samples. We propose a calibration framework that continues updating the trained neural network model for accurate bacterial concentration estimation upon receiving new samples. We tested the effectiveness of the proposed calibration scheme on four WRRF datasets in Saudi Arabia, comparing the results with before and after calibration without the OOD. Before calibration model was based on a traditional and optimal neural network approach, typically considered the conventional method for building neural networks. After calibration without OOD, the model continued retraining without explicitly checking for OOD condition. The results showed that the proposed calibration framework of the selected baseline WRRF with the OOD scheme improved \(99.68\%\) and \(56.00\%\) of the worst-case influent bacteria concentration before calibration and after calibration without OOD, respectively. Similarly, the worst-case effluent bacteria concentration estimation was enhanced by \(99.37\%\) before calibration and \(33.98\%\) after calibration without the OOD. Our findings highlight the importance of integrating the calibration framework with neural network approaches to achieve model generalization.

Aquaculture systems can benefit from the recent development of advanced control strategies to reduce operating costs and fish loss and increase growth production efficiency, resulting in fish welfare and health. Monitoring the water quality and controlling feeding are fundamental elements of balancing fish productivity and shaping the fish growth process. Currently, most fish-feeding processes are conducted manually in different phases and rely on time-consuming and challenging artificial discrimination. The feeding control approach influences fish growth and breeding through the feed conversion rate; hence, controlling these feeding parameters is crucial for enhancing fish welfare and minimizing general fishery costs. The high concentration of environmental factors, such as a high ammonia concentration and pH, affect the water quality and fish survival. Therefore, there is a critical need to develop control strategies to determine optimal, efficient, and reliable feeding processes and monitor water quality. This paper reviews the main control design techniques for fish growth in aquaculture systems, namely algorithms that optimize the feeding and water quality of a dynamic fish growth process. Specifically, we review model-based control approaches and model-free reinforcement learning strategies to optimize the growth and survival of the fish or track a desired reference live-weight growth trajectory. The model-free framework uses an approximate fish growth dynamic model and does not satisfy constraints. We discuss how model-based approaches can support a reinforcement learning framework to efficiently handle constraint satisfaction and find better trajectories and policies from value-based reinforcement learning.