Soft sensor predictor of E. coli concentration based on conventional monitoring parameters for wastewater disinfection control

Internet of Things and citizen science as alternative water quality monitoring approaches and the importance of effective water quality communication

The increasing demand for water and worsening climate change place significant pressure on this vital resource, making its preservation a global priority. Water quality monitoring programs are essential for effectively managing this resource. Current programs rely on traditional monitoring approaches, leading to limitations such as low spatiotemporal resolution and high operational costs. Despite the adoption of novel monitoring approaches that enable better data resolution, the public's comprehension of water quality matters remains low, primarily due to communication process deficiencies. This study explores the advantages and challenges of using Internet of Things (IoT) and citizen science as alternative monitoring approaches, emphasizing the need for enhancing public communication of water quality data. Through a systematic review of studies implemented on-field, we identify and propose strategies to address five key challenges that IoT and citizen science monitoring approaches must overcome to mature into robust sources of water quality information. Additionally, we highlight three fundamental problems affecting the water quality communication process and outline strategies to convey this topic effectively to the public.

Development of a Soft Sensor Using Machine Learning Algorithms for Predicting the Water Quality of an Onsite Wastewater Treatment System

Developing advanced onsite wastewater treatment systems (OWTS) requires accurate and consistent water quality monitoring to evaluate treatment efficiency and ensure regulatory compliance. However, off-line parameters such as chemical oxygen demand (COD), total suspended solids (TSS), and Escherichia coli (E. coli) require sample collection and time-consuming laboratory analyses that do not provide real-time information of system performance or component failure. While real-time COD analyzers have emerged in recent years, they are not economically viable for onsite systems due to cost and chemical consumables. This study aimed to design and implement a real-time remote monitoring system for OWTS by developing several multi-input and single-output soft sensors. The soft sensor integrates data that can be obtained from well-established in-line sensors to accurately predict key water quality parameters, including COD, TSS, and E. coli concentrations. The temporal and spatial water quality data of an existing field-tested OWTS operated for almost two years (n = 56 data points) were used to evaluate the prediction performance of four machine learning algorithms. These algorithms, namely, partial least square regression (PLS), support vector regression (SVR), cubist regression (CUB), and quantile regression neural network (QRNN), were chosen as candidate algorithms for their prior application and effectiveness in wastewater treatment predictions. Water quality parameters that can be measured in-line, including turbidity, color, pH, NH4+, NO3-, and electrical conductivity, were selected as model inputs for predicting COD, TSS, and E. coli. The results revealed that the trained SVR model provided a statistically significant prediction for COD with a mean absolute percentage error (MAPE) of 14.5% and R2 of 0.96. The CUB model provided the optimal predictive performance for TSS, with a MAPE of 24.8% and R2 of 0.99. None of the models were able to achieve optimal prediction results for E. coli; however, the CUB model performed the best with a MAPE of 71.4% and R2 of 0.22. Given the large fluctuation in the concentrations of COD, TSS, and E. coli within the OWTS wastewater dataset, the proposed soft sensor models adequately predicted COD and TSS, while E. coli prediction was comparatively less accurate and requires further improvement. These results indicate that although water quality datasets for the OWTS are relatively small, machine learning-based soft sensors can provide useful predictive estimates of off-line parameters and provide real-time monitoring capabilities that can be used to make adjustments to OWTS operations.

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

Widespread implementation of on-site water reuse is hindered by the limited availability of monitoring approaches that ensure microbial quality during operation. In this study, we developed a methodology for monitoring microbial water quality in on-site water reuse systems using inexpensive and commercially available online sensors. An extensive dataset containing sensor and microbial water quality data for six of the most critical types of disruptions in membrane bioreactors with chlorination was collected. We then tested the ability of three typological machine learning algorithms - logistic regression, support-vector machine, and random forest - to predict the microbial water quality as "safe" or "unsafe" for reuse. The main criteria for model optimization was to ensure a low false positive rate (FPR) - the percentage of safe predictions when the actual condition is unsafe - which is essential to protect users health. This resulted in enforcing a fixed FPR ≤ 2%. Maximizing the true positive rate (TPR) - the percentage of safe predictions when the actual condition is safe - was given second priority. Our results show that logistic-regression-based models using only two out of the six sensors (free chlorine and oxidation-reduction potential) achieved the highest TPR. Including sensor slopes as engineered features allowed to reach similar TPRs using only one sensor instead of two. Analysis of the occurrence of false predictions showed that these were mostly early alarms, a characteristic that could be regarded as an asset in alarm management. In conclusion, the simplest algorithm in combination with only one or two sensors performed best at predicting the microbial water quality. This result provides useful insights for water quality modeling or for applications where small datasets are a common challenge and a general advantage might be gained by using simpler models that reduce the risk of overfitting, allow better interpretability, and require less computational power.

Reduction of pathogens in greywater with biological and sustainable treatments selected through a multicriteria approach

Non-potable reuse of greywater (GW) can represent a valid alternative to freshwater consumption, satisfying the Sustainable Development Goals promoted by United Nations. The Multi-Criteria Analysis (MCA) was applied to select the most suitable processes for the reduction of microbiological contamination in GW. A pilot plant, including horizontal flow constructed wetland (CW) and anaerobic filtration (AF) in parallel, best treatment options according to MCA results, was built to treat GW collected from a Venezuelan family. (i) The removal efficiency of microbiological parameters, and (ii) the turbidity as possible microbiological contamination indicator and possible influence factor of disinfection treatment, were investigated. Except for Escherichia coli (4.1 ± 0.9 log reduction with AF), CW achieved the best reductions yields for total coliforms, faecal coliforms, and Salmonella, respectively equal to 3.1 ± 0.5 log, 4.3 ± 0.5 log, and 2.9 ± 0.4 log. In accordance with Venezuelan legislation and WHO guidelines, GW treated with CW was found to be suitable for irrigation reuse for non-edible crops. However, the reduction of pathogens by CW should be considered as a preliminary and not complete disinfection treatment. To reuse GW, especially in the irrigation of edible crops, stronger disinfection treatment should be considered as a complement to the preliminary disinfection performed by CW, to avoid any kind of risk. No significant correlation was found for turbidity either as a possible predictor of microbiological contamination or as an influence on biological disinfection.

Contactless Sensing of Water Properties for Smart Monitoring of Pipelines

A key milestone for the pervasive diffusion of wireless sensing nodes for smart monitoring of water quality and quantity in distribution networks is the simplification of the installation of sensors. To address this aspect, we demonstrate how two basic contactless sensors, such as piezoelectric transducers and strip electrodes (in a longitudinal interdigitated configuration to sense impedance inside and outside of the pipe with potential for impedimetric leak detection), can be easily clamped on plastic pipes to enable the measurement of multiple parameters without contact with the fluid and, thus, preserving the integrity of the pipe. Here we report the measurement of water flow rate (up to 24 m³/s) and temperature with ultrasounds and of the pipe filling fraction (capacitance at 1 MHz with ~cm³ resolution) and ionic conductivity (resistance at 20 MHz from 700 to 1400 μS/cm) by means of impedance. The equivalent impedance model of the sensor is discussed in detail. Numerical finite-element simulations, carried out to optimize the sensing parameters such as the sensing frequency, confirm the lumped models and are matched by experimental results. In fact, a 6 m long, 30 L demonstration hydraulic loop was built to validate the sensors in realistic conditions (water speed of 1 m/s) monitoring a pipe segment of 0.45 m length and 90 mm diameter (one of the largest ever reported in the literature). Tradeoffs in sensors accuracy, deployment, and fabrication, for instance, adopting single-sided flexible PCBs as electrodes protected by Kapton on the external side and experimentally validated, are discussed as well.

Data Augmentation for a Virtual-Sensor-Based Nitrogen and Phosphorus Monitoring

To better control eutrophication, reliable and accurate information on phosphorus and nitrogen loading is desired. However, the high-frequency monitoring of these variables is economically impractical. This necessitates using virtual sensing to predict them by utilizing easily measurable variables as inputs. While the predictive performance of these data-driven, virtual-sensor models depends on the use of adequate training samples (in quality and quantity), the procurement and operational cost of nitrogen and phosphorus sensors make it impractical to acquire sufficient samples. For this reason, the variational autoencoder, which is one of the most prominent methods in generative models, was utilized in the present work for generating synthetic data. The generation capacity of the model was verified using water-quality data from two tributaries of the River Thames in the United Kingdom. Compared to the current state of the art, our novel data augmentation-including proper experimental settings or hyperparameter optimization-improved the root mean squared errors by 23-63%, with the most significant improvements observed when up to three predictors were used. In comparing the predictive algorithms' performances (in terms of the predictive accuracy and computational cost), k-nearest neighbors and extremely randomized trees were the best-performing algorithms on average.

Assessment of phytotoxic potential and pathogenic bacteria removal from secondary effluents during ozonation and UV/H2O2

Wastewater reuse is an important strategy for water resource management. For this reason, the disinfection process must be appropriated, eliminating pathogenic microorganisms. Ozonation (O₃) and UV/H₂O₂ treatments can be used for effluent disinfection, but few studies just address the Escherichia coli quantification. In this study, secondary effluents from two wastewater treatment plants with different characteristics were exposed to O₃ (5 and 10 mg L^-1) or UV/H₂O₂ (H₂O₂: 90 mg L^-1) treatments and evaluated by BD Phoenix ™ 100 (Becton Dickinson, USA) and MALDI-TOF for the characterization of the indigenous microorganisms in the effluents, before and after treatments. Additionally, all the samples were tested for phytotoxicity by Lactuca sativa bioassay. The results showed that the highest ozone dose and the UV/H₂O₂ treatment were effective in removing E. coli. UV/H₂O₂ was more efficient as it eliminated most of the microorganisms. Acinetobacter sp., Aeromonas and Pseudomonas were still found after O₃ treatment. Bacillus sp. was found after O₃ and UV/H₂O₂ treatments. The results with L. sativa showed inhibition of root growth for all dry period (low rainfall) samples of one of the WWTP, due to the high concentration of the phytotoxicity compounds. For environmental and human health safety, treated effluents should be evaluated for their toxic and pathogenic potential before being released into the environment. Pathogens evaluation on treated effluents should cover a wider range of pathogenic microorganisms than those routinely required by legislation.

Virtual Sensors for Smart Data Generation and Processing in AI-Driven Industrial Applications

The current digitalisation revolution demonstrates the high importance and possibilities of quality data in industrial applications. Data represent the foundation of any analytical process, establishing the fundamentals of the modern Industry 4.0 era. Data-driven processes boosted by novel Artificial Intelligence (AI) provide powerful solutions for industrial applications in anomaly detection, predictive maintenance, optimal process control and digital twins, among many others. Virtual Sensors offer a digital definition of a real Internet of Things (IoT) sensor device, providing a smart tool capable to face key issues on the critical data generation side: i) Scalability of expensive measurement devices, ii) Robustness and resilience through real-time data validation and real-time sensor replacement for continuous service, or iii) Provision of key parameters’ estimation on difficult to measure situations. This chapter presents a profound introduction to Virtual Sensors, including the explanation of the methodology used in industrial data-driven projects, novel AI techniques for their implementation and real use cases in the Industry 4.0 context.

Chlorophyll soft-sensor based on machine learning models for algal bloom predictions

Harmful algal blooms (HABs) are a growing concern to public health and aquatic ecosystems. Long-term water monitoring conducted by hand poses several limitations to the proper implementation of water safety plans. This work combines automatic high-frequency monitoring (AFHM) systems with machine learning (ML) techniques to build a data-driven chlorophyll-a (Chl-a) soft-sensor. Massive data for water temperature, pH, electrical conductivity (EC) and system battery were taken for three years at intervals of 15 min from two different areas of As Conchas freshwater reservoir (NW Spain). We designed a set of soft-sensors based on compact and energy efficient ML algorithms to infer Chl-a fluorescence by using low-cost input variables and to be deployed on buoys with limited battery and hardware resources. Input and output aggregations were applied in ML models to increase their inference performance. A component capable of triggering a 10 [Formula: see text]g/L Chl-a alert was also developed. The results showed that Chl-a soft-sensors could be a rapid and inexpensive tool to support manual sampling in water bodies at risk.

A review of the application of machine learning in water quality evaluation

With the rapid increase in the volume of data on the aquatic environment, machine learning has become an important tool for data analysis, classification, and prediction. Unlike traditional models used in water-related research, data-driven models based on machine learning can efficiently solve more complex nonlinear problems. In water environment research, models and conclusions derived from machine learning have been applied to the construction, monitoring, simulation, evaluation, and optimization of various water treatment and management systems. Additionally, machine learning can provide solutions for water pollution control, water quality improvement, and watershed ecosystem security management. In this review, we describe the cases in which machine learning algorithms have been applied to evaluate the water quality in different water environments, such as surface water, groundwater, drinking water, sewage, and seawater. Furthermore, we propose possible future applications of machine learning approaches to water environments.

The status of potable water reuse implementation

A review of the current status of direct and indirect potable water reuse (DPR/IPR) implementation has been conducted, focusing on the regulatory and practical aspects and with reference to the most recent published literature. The review encompasses (a) the principal contaminant types, their required removal and the methods by which their concentration is monitored, (b) regulatory approaches and stipulations in assessing/ratifying treatment schemes and maintaining treated water quality, and (c) existing full-scale installations. Analytical methods discussed include established in-line monitoring tools, such as turbidity measurement, to more recent polymerase chain reaction (PCR)-based assay methods for microbial detection. The key risk assessment tools of quantitative microbial risk assessment (QMRA) and water safety plans (WSPs) are considered in relation to their use in selecting/ratifying treatment schemes, and the components of the treatment schemes from 40 existing IPR/DPR installations summarised. Five specific schemes are considered in more detail. The review reveals:Whilst there are a number of ongoing projects where RO is not used because of the challenge imposed by disposal of RO concentrate, the prevalence of the sequential RO-UV combination implies the importance of quantifying the impact of process upsets on these unit operations.

Identification of surrogates for rapid monitoring of microbial inactivation by ozone for water reuse: A pilot-scale study

The complex contaminants in reclaimed water sources and delayed feedback of microbial detection have brought tremendous challenges to disinfection process control. The identification of sensitive and online surrogates for indicating microbial inactivation efficacy is vital to evaluate and optimize the disinfection technologies and processes. This study analyzes the inactivation of microbial indicators during ozone disinfection at a pilot-scale study over 5 months. It is identified that total fluorescence (TF) intensity, ultraviolet absorbance at 254 nm (UV₂₅₄) and intracellular adenosine triphosphate (cATP) concentration can act as surrogates in predicting microbial inactivation by ozone. Particularly, the empirical linear correlations for log removal values (LRV) of TF, UV₂₅₄ and cATP concentration are developed for the inactivation of four widely applied microbial indicators, namely the total coliforms, fecal coliforms, Escherichia coli (E. coli) and heterotrophic plate count (HPC) (R² = 0.86-0.96). Validation analyses are further conducted to verify the robustness and effectiveness of empirical models. Notably, TF is considered as the most efficient surrogate due to its high sensitivity, accuracy and reliability, whereas cATP concentration is an efficient supplement to directly reflect total microbial counts. The study is important to provide a rapid and reliable approach for ozone disinfection efficiency evaluation and prediction.

Digital E. coli Counter: A Microfluidics and Computer Vision-Based DNAzyme Method for the Isolation and Specific Detection of E. coli from Water Samples

Biological water contamination detection-based assays are essential to test water quality; however, these assays are prone to false-positive results and inaccuracies, are time-consuming, and use complicated procedures to test large water samples. Herein, we show a simple detection and counting method for E. coli in the water samples involving a combination of DNAzyme sensor, microfluidics, and computer vision strategies. We first isolated E. coli into individual droplets containing a DNAzyme mixture using droplet microfluidics. Upon bacterial cell lysis by heating, the DNAzyme mixture reacted with a particular substrate present in the crude intracellular material (CIM) of E. coli. This event triggers the dissociation of the fluorophore-quencher pair present in the DNAzyme mixture leading to a fluorescence signal, indicating the presence of E. coli in the droplets. We developed an algorithm using computer vision to analyze the fluorescent droplets containing E. coli in the presence of non-fluorescent droplets. The algorithm can detect and count fluorescent droplets representing the number of E. coli present in the sample. Finally, we show that the developed method is highly specific to detect and count E. coli in the presence of other bacteria present in the water sample.

Artificial neural network modeling of full-scale UV disinfection for process control aimed at wastewater reuse

Accurate modeling of wastewater ultraviolet disinfection is fundamental as support for process optimization and control. Detailed modeling of hydrodynamics and fluence rate via computational fluid dynamics, coupled to laboratory studies of inactivation kinetics, are usually the preferred approach for UV disinfection modeling. Despite this approach often provides accurate predictive performance, it requires significantly high computational time, making it unfeasible for real-time process control. In this study, to enable an effective process control, black-box regression models were assessed as a modeling alternative for UV disinfection, synthesizing hydrodynamics, fluence rate and inactivation kinetics. UV disinfection of a full-scale wastewater treatment plant in Italy was monitored for 10 months, measuring influent and effluent E. coli concentration, turbidity, absorbance at 254 nm, temperature and flow rate at different UV doses. Considering the usually observed distribution of effluent E. coli concentration and the zero inflation of the collected dataset, Poisson, zero-inflated Poisson and Hurdle generalized linear models were tested, as well as two-part models coupling a classifier describing the E. coli zero-count events and a regressor estimating the magnitude of E. coli concentrations in positive-count events. The two-part artificial neural network model showed the best predictive performance, being able of both describing nonlinearities and handling the high proportion of null values in the dataset. The deployment of this model to control ultraviolet disinfection was simulated, estimating a plausible 63% energy saving.

From Fully Physical to Virtual Sensing for Water Quality Assessment: A Comprehensive Review of the Relevant State-of-the-Art

Rapid urbanization, industrial development, and climate change have resulted in water pollution and in the quality deterioration of surface and groundwater at an alarming rate, deeming its quick, accurate, and inexpensive detection imperative. Despite the latest developments in sensor technologies, real-time determination of certain parameters is not easy or uneconomical. In such cases, the use of data-derived virtual sensors can be an effective alternative. In this paper, the feasibility of virtual sensing for water quality assessment is reviewed. The review focuses on the overview of key water quality parameters for a particular use case and the development of the corresponding cost estimates for their monitoring. The review further evaluates the current state-of-the-art in terms of the modeling approaches used, parameters studied, and whether the inputs were pre-processed by interrogating relevant literature published between 2001 and 2021. The review identified artificial neural networks, random forest, and multiple linear regression as dominant machine learning techniques used for developing inferential models. The survey also highlights the need for a comprehensive virtual sensing system in an internet of things environment. Thus, the review formulates the specification book for the advanced water quality assessment process (that involves a virtual sensing module) that can enable near real-time monitoring of water quality.

Modern Analytical Techniques for Detection of Bacteria in Surface and Wastewaters

Contamination of surface waters with pathogens as well as all diseases associated with such events are a significant concern worldwide. In recent decades, there has been a growing interest in developing analytical methods with good performance for the detection of this category of contaminants. The most important analytical methods applied for the determination of bacteria in waters are traditional ones (such as bacterial culturing methods, enzyme-linked immunoassay, polymerase chain reaction, and loop-mediated isothermal amplification) and advanced alternative methods (such as spectrometry, chromatography, capillary electrophoresis, surface-enhanced Raman scattering, and magnetic field-assisted and hyphenated techniques). In addition, optical and electrochemical sensors have gained much attention as essential alternatives for the conventional detection of bacteria. The large number of available methods have been materialized by many publications in this field aimed to ensure the control of water quality in water resources. This study represents a critical synthesis of the literature regarding the latest analytical methods covering comparative aspects of pathogen contamination of water resources. All these aspects are presented as representative examples, focusing on two important bacteria with essential implications on the health of the population, namely Pseudomonas aeruginosa and Escherichia coli.

Influence of Anthropogenic Loads on Surface Water Status: A Case Study in Lithuania

Twenty-six water bodies and 10 ponds were selected for this research. Anthropogenic loads were assessed according to pollution sources in individual water catchment basins. It was determined that 50% of the tested water bodies had Ntotal values that did not correspond to the good and very good ecological status classes, and 20% of the tested water bodies had Ptotal values that did not correspond to the good and very good ecological status classes. The lake basins and ponds received the largest amounts of pollution from agricultural sources with total nitrogen at 1554.13 t/year and phosphorus at 1.94 t/year, and from meadows and pastures with total nitrogen at 9.50 t/year and phosphorus at 0.20 t/year. The highest annual load of total nitrogen for lake basins on average per year was from agricultural pollution from arable land (98.85%), and the highest total phosphorus load was also from agricultural pollution from arable land (60%).