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

Innovative multistep and synchronous soft sensing prediction of COD and NH3 in WWTPs via multimodal data and multiple attention mechanisms

Accurate prediction of Chemical Oxygen Demand (COD) and ammonia nitrogen (NH₃) is crucial for maintaining stable and effective wastewater treatment processes. Traditional methods rely on costly, high-maintenance sensors, limiting their application in resource-limited wastewater treatment plants. Soft sensing methods provide an alternative by reducing dependence on costly sensors. However, existing approaches cannot perform multitarget and multistep predictions, limiting their practical applicability. This study introduced a novel triple attention-enhanced encoder-decoder temporal convolutional network (TAED-TCN) to address this problem. The model used multimodal inputs, including easily accessible water quality parameters and wastewater surface images, for multistep and synchronous prediction of COD and NH₃. When it was validated with real-world sequencing batch reactor wastewater data, the model demonstrated superior multistep prediction performance. Specifically, the R² for 1-h predictions of COD and NH₃ was over 26.03 % and 20.51 % higher than the baseline model, respectively. By incorporating multiple attention mechanisms (feature, temporal, and cross-attention), TAED-TCN effectively captured essential features, model nonlinear relationships, and identified long-term dependencies, thus enabled consistent multitarget prediction results even under abnormal conditions. Additionally, economic analysis revealed that TAED-TCN could reduce COD and NH₃ monitoring costs by 79 % over the equipment life cycle. This study offers a cost-effective solution for water quality prediction, enhancing the operational efficiency of wastewater management.

Predicting and investigating water quality index by robust machine learning methods

This study addresses the critical challenges of waste management and water quality in urban environments, where accelerated urbanization has exacerbated environmental degradation and public health risks. Employing advanced machine learning algorithms-Long Short-Term Memory (LSTM), Random Forest (RF), Decision Tree (DT), and Support Vector Machine (SVM)-this research predicts the Water Quality Index (WQI) to improve urban environmental management. The novelty lies in the integration of multiple algorithms within a single framework, focusing on classifying WQI labels (1-9) for "good" to "poor" water quality, a departure from traditional continuous value predictions. Among the algorithms, LSTM demonstrated the most significant advantages, achieving superior predictive accuracy and precision across training, testing, and validation datasets, with RMSE values of 0.0611, 0.0810, and 0.0754 and R2 values consistently above 0.9964. Comparative analysis revealed LSTM's capacity to capture complex temporal dependencies in data, surpassing RF, DT, and SVM in predictive performance. This approach provides actionable insights into WQI dynamics, enabling the identification of key pollution factors, optimizing waste management practices, and supporting real-time decision-making. The integration of climate indicators into the models further enhances their applicability in addressing long-term trends associated with climate change. Statistical evaluations, including AARE and SD, corroborate LSTM's robustness and reliability, making it a transformative tool for urban water quality prediction. This research pioneers a scalable, efficient, and practical solution to urban environmental challenges, contributing to sustainable resource management and improved public health outcomes.

Fit-for-purpose WWTP unmanned aerial systems: A game changer towards an integrated and sustainable management strategy

In the ongoing Anthropocene era, air quality monitoring constitutes a primary axis of European and international policies for all sectors, including Waste Water Treatment Plants (WWTPs). Unmanned Aerial Systems (UASs) with proper sensing equipment provide an edge technology for air quality and odor monitoring. In addition, Unmanned Aerial Vehicle (UAV) photogrammetry has been used in civil engineering, environmental (water) quality assessment and lately for industrial facilities monitoring. This study constitutes a systematic review of the late advances and limitations of germane equipment and implementations. Despite their unassailable flexibility and efficiency, the employment of the aforementioned technologies in WWTP remote monitoring is yet sparse, partial, and concerns only particular aspects. The main finding of the review was the lack of a tailored UAS for WWTP monitoring in the literature. Therefore, to fill in this gap, we propose a fit-for-purpose remote monitoring system consisting of a UAS with a platform that would integrate all the required sensors for air quality (i.e., emissions of H2S, NH3, NOx, SO2, CH4, CO, CO2, VOCs, and PM) and odor monitoring, multispectral and thermal cameras for photogrammetric structural health monitoring (SHM) and wastewater/effluent properties (e.g., color, temperature, etc.) of a WWTP. It constitutes a novel, supreme and integrated approach to improve the sustainable management of WWTPs. Specifically, the developments that a fit-for-purpose WWTP UAS would launch, are fostering the decision-making of managers, administrations, and policymakers, both in operational conditions and in case of failures, accidents or natural disasters. Furthermore, it would significantly reduce the operational expenditure of a WWTP, ensuring personnel and population health standards, and local area sustainability.

Predicting the Occurrence of Substituted and Unsubstituted, Polycyclic Aromatic Compounds in Coking Wastewater Treatment Plant Effluent using Machine Learning Regression

Organic contaminants such as polycyclic aromatic compounds (PACs) occurring in industrial effluents can not only persist in wastewater but transform into more toxic and mobile, substituted heterocyclic products during treatment. Thus, predicting the occurrence of PACs and their heterocyclic derivatives (HPACs) in coking wastewater is of utmost importance to reduce the environmental risks in water bodies that receive industrial effluents. Although HPACs can be monitored through sampling and analysis, the characterisation techniques used in their analyses are costly and time-consuming. In this study, we propose 3 distinct kernel-based machine learning (ML) models for predicting PACs including substituted HPACs and alkylated PACs occurring in coking wastewater. By using routinely measured wastewater quality data as input for our models, we predicted the occurrence of 14 HPACs in the final effluent of a coking wastewater treatment plant. Support Vector Machine based regression model (SVR) used for HPAC prediction showed the highest R2 of 0.83. Performance assessment of SVR model showed a mean absolute logarithmic error (MALE) of 0.46 and root mean square error (RMSE) of 0.073 ng/L. Comparatively, K-Nearest Neighbor and Random Forest models showed lower R2 of 0.75 and 0.76 respectively for HPAC prediction. Feature analysis attributed the superior predictability of SVR model likely to its higher weightage (81%) towards dissolved organic carbon and total ammonia as input variables. Both these variables could capture the underlying secondary PAC transformations likely occurring in the treatment plant. Partial dependence plots predicted that ammonia levels higher than 120 mg/L and DOC levels of 50-60 mg/L were likely linked to higher HPACs occurring in the final effluent. This work highlights the capability of kernel-based ML models in capturing nonlinear wastewater chemistry and offers a tool for monitoring trace organic contaminants released in coking effluents.

Mechanistic and data-driven modeling of carbon respiration with bio-electrochemical sensors

Bioelectrochemical sensor (BES) technologies have been developed to measure soluble carbon concentrations in wastewater. However, architectures and analytical methods developed in controlled laboratory environments fail to predict BES behavior during field deployments at water resource recovery facilities (WRRFs). Here, we examine the possibilities and obstacles associated with integrating BESs into environmental sensing networks and machine learning algorithms to monitor the biodegradable carbon dynamics and microbial metabolism at WRRFs. This approach highlights the potential of BESs to provide real-time insights into full-scale biodegradable carbon consumption across WRRFs.

Photocatalytic degradation of drugs and dyes using a maching learning approach

The waste management industry uses an increasing number of mathematical prediction models to accurately forecast the behavior of organic pollutants during catalytic degradation. With the increasing quantity of waste generated, these models are critical for reinforcing the efficiency of wastewater treatment strategies. The application of machine-learning techniques in recent years has notably improved predictive models for waste management, which are essential for mitigating the impact of toxic commercial waste on global water supply. Organic contaminants, dyes, pesticides, surfactants, petroleum by-products, and prescription drugs pose risks to human health. Because traditional techniques face challenges in ensuring water quality, modern strategies are vital. Machine learning has emerged as a valuable tool for predicting the photocatalytic degradation of medicinal drugs and dyes, providing a promising avenue for addressing urgent demands in removing organic pollutants from wastewater. This research investigates the synergistic application of photocatalysis and machine learning for pollutant degradation, showcasing a sustainable solution with promising effects on environmental remediation and computational efficiency. This study contributes to green chemistry by providing a clever framework for addressing present-day water pollution challenges and achieving era-driven answers.

Sensors for Emerging Water Contaminants: Overcoming Roadblocks to Innovation

Ensuring water quality and safety requires the effective detection of emerging contaminants, which present significant risks to both human health and the environment. Field deployable low-cost sensors provide solutions to detect contaminants at their source and enable large-scale water quality monitoring and management. Unfortunately, the availability and utilization of such sensors remain limited. This Perspective examines current sensing technologies for detecting emerging contaminants and analyzes critical barriers, such as high costs, lack of reliability, difficulties in implementation in real-world settings, and lack of stakeholder involvement in sensor design. These technical and nontechnical barriers severely hinder progression from proof-of-concepts and negatively impact user experience factors such as ease-of-use and actionability using sensing data, ultimately affecting successful translation and widespread adoption of these technologies. We provide examples of specific sensing systems and explore key strategies to address the remaining scientific challenges that must be overcome to translate these technologies into the field such as improving sensitivity, selectivity, robustness, and performance in real-world water environments. Other critical aspects such as tailoring research to meet end-users' requirements, integrating cost considerations and consumer needs into the early prototype design, establishing standardized evaluation and validation protocols, fostering academia-industry collaborations, maximizing data value by establishing data sharing initiatives, and promoting workforce development are also discussed. The Perspective describes a set of guidelines for the development, translation, and implementation of water quality sensors to swiftly and accurately detect, analyze, track, and manage contamination.

Anaerobic Digestion as a Core Technology in Addressing the Global Sanitation Crisis: Challenges and Opportunities

Successfully addressing the complex global sanitation problem is a massive undertaking. Anaerobic digestion (AD), coupled with post-treatment, has been identified as a promising technology to contribute to meeting this goal. It offers multiple benefits to the end users, such as the potential inactivation of pathogenic microorganisms in waste and the recovery of resources, including renewable energy and nutrients. This feature article provides an overview of the most frequently applied AD systems for decentralized communities and low- and lower-middle-income countries with an emphasis on sanitation, including technologies for which pathogen inactivation was considered during the design. Challenges to AD use are then identified, such as experience, economics, knowledge/training of personnel and users, and stakeholder analysis. Finally, accelerators for AD implementation are noted, such as the inclusion of field studies in academic journals, analysis of emerging contaminants, the use of sanitation toolboxes and life cycle assessment in design, incorporation of artificial intelligence in monitoring, and expansion of undergraduate and graduate curricula focused on Water, Sanitation, and Hygiene (WASH).