Predicting microbial water quality in on-site water reuse systems with online sensors

Artificial Intelligence in Aquatic Biodiversity Research: A PRISMA-Based Systematic Review

Freshwater ecosystems are increasingly threatened by climate change and anthropogenic activities, necessitating innovative and scalable monitoring solutions. Artificial intelligence (AI) has emerged as a transformative tool in aquatic biodiversity research, enabling automated species identification, predictive habitat modeling, and conservation planning. This systematic review follows the PRISMA framework to analyze AI applications in freshwater biodiversity studies. Using a structured literature search across Scopus, Web of Science, and Google Scholar, we identified 312 relevant studies published between 2010 and 2024. This review categorizes AI applications into species identification, habitat assessment, ecological risk evaluation, and conservation strategies. A risk of bias assessment was conducted using QUADAS-2 and RoB 2 frameworks, highlighting methodological challenges, such as measurement bias and inconsistencies in the model validation. The citation trends demonstrate exponential growth in AI-driven biodiversity research, with leading contributions from China, the United States, and India. Despite the growing use of AI in this field, this review also reveals several persistent challenges, including limited data availability, regional imbalances, and concerns related to model generalizability and transparency. Our findings underscore AI's potential in revolutionizing biodiversity monitoring but also emphasize the need for standardized methodologies, improved data integration, and interdisciplinary collaboration to enhance ecological insights and conservation efforts.

Automation of on-site microbial water quality monitoring from source to tap: Challenges and perspectives

Ensuring the provision of safe drinking water necessitates thorough monitoring of microbial water quality. While traditional culture-based enumeration of bacterial indicators has served as the gold standard in compliance monitoring since the late 19th century, recent advancements in microbial sensor technology, driven by automation and digitalization, are revolutionizing on-site monitoring capabilities. These innovations offer unparalleled potential for automated, high temporal frequency monitoring with remote, real-time data transmission. With regulatory frameworks increasingly favouring risk-based approaches to microbial risk management throughout the drinking water supply chain, we are witnessing a paradigm shift towards the adoption of microbial sensors. This review offers a comprehensive examination of the latest developments and accomplishments in automated on-site monitoring of microbial water quality. Beginning with an elucidation of key terminology and an overview of available sensor technologies, we explore how these cutting-edge tools can enhance our understanding of microbial dynamics in the sourcing, treatment, and distribution of drinking water, and how this knowledge can be translated into operational management. Despite the promise of microbial sensors, significant challenges remain. Drawing from insights gathered from an international online survey targeting drinking water utilities, we discuss the analytical, economic, and legal barriers that must be overcome for the implementation of automated on-site monitoring of microbial water quality. This review serves as a vital resource for researchers, utilities, and policymakers operating in water microbiology and sensor technology. While it is addressing drinking water more specifically, the presented concepts and tools can be extrapolated to recreational waters or wastewater management, with the shared goal to ensure sustainable management of water resources and protection of public health.

Machine learning algorithms for predicting membrane bioreactors performance: A review

Membrane bioreactors (MBR) are recognized as a sustainable technology for treating polluted effluents. Machine learning (ML) algorithms have emerged as a modeling option to predict pollutant removal and operational variables such as membrane fouling, permeability, and energy consumption, which are significant challenges for MBR application. This review examines the use of ML algorithms in MBR-based wastewater treatment, focusing on the prediction of nitrogen and organic matter removal, and operational parameters related to membrane fouling. It presents the structures and fit quality of each model, noting that artificial neural networks (ANNs) are the most commonly used algorithm, appearing in 88 % of the 57 analyzed articles. Additionally, the review identified studies using random forests, support vector machines, k-nearest neighbors and boosting techniques, among other ML algorithms, although these were less frequently encountered. The review suggests potential in exploring less-utilized models for MBR data and identifies a gap in predicting membrane lifespan and replacement with ML models. This study aims to guide the development of new models for optimizing MBR performance by highlighting effective variables and algorithms, enhancing process control, real-time data analysis, parameter adjustment, and operational efficiency.

Reinforcing Feedbacks for Sustainable Implementation of Rural Drinking-Water Treatment Technology

Progress toward universal access to safe drinking water depends on rural water service delivery models that incorporate water safety management. Water supplies of all types have high rates of fecal contamination unless water safety risks are actively managed through water source protection, treatment, distribution, and storage. Recognizing the role of treatment within this broader risk-based framework, this study focuses on the implementation of passive chlorination and ultraviolet (UV) disinfection technologies in rural settings. These technologies can reduce the health risk from microbiological contaminants in drinking water; however, technology-focused treatment interventions have had limited sustainability in rural settings. This study examines the requirements for sustainable implementation of rural water treatment through qualitative content analysis of 26 key informant interviews, representing passive chlorination and UV disinfection projects in rural areas in South America, Africa, and Asia. The analysis is aligned with the RE-AIM framework and delivers insight into 18 principal enablers and barriers to rural water treatment sustainability. Analysis of the interrelationships among these factors identifies leverage points and encourages fit-for-purpose intervention design reinforced by collaboration between facilitating actors through hybrid service delivery models. Further work should prioritize health impact evidence, water quality reporting guidance, and technological capabilities that optimize trade-offs in fit-for-purpose treatment design.

Ensuring microbial water quality for on-site water reuse: Importance of online sensors for reliable operation

A growing number of cities and regions are promoting or mandating on-site treatment and reuse of wastewater, which has resulted in the implementation of several thousand on-site water reuse systems on a global scale. However, there is only limited information on the (microbial) water quality from implemented systems. The focus of this study was on two best-in-class on-site water reuse systems in Bengaluru, India, which typically met the local water quality requirements during monthly compliance testing. This study aimed to (i) assess the microbial quality of the reclaimed water at a high temporal resolution (daily or every 15 min), and (ii) explore whether measurements from commercially available sensors can be used to improve the operation of such systems. The monitoring campaign revealed high variations in microbial water quality, even in these best-in-class systems, rendering the water inadequate for the intended reuse applications (toilet flushing and landscape irrigation). These variations were attributed to two key factors: (1) the low frequency of chlorination, and (2) fluctuations of the chlorine demand of the water, in particular of ammonium concentrations. Such fluctuations are likely inherent to on-site systems, which rely on a low level of process control. The monitoring campaign showed that the microbial water quality was most closely related to oxidation-reduction potential (ORP) and free chlorine sensors. Due to its relatively low cost and low need for maintenance, the ORP emerges as a compelling candidate for automating the chlorination to effectively manage variations in chlorine demand and ensure safe water reuse. Overall, this study underscores the necessity of integrating treatment trains, operation, and monitoring for safe on-site water reuse.