Search Results (10)

The increasing cost of energy and the need for low-carbon solutions have strengthened interest in wastewater as a stable and underutilized source of recoverable heat. This study assesses the technical feasibility, economic viability, and environmental benefits of a wastewater heat recovery system based on a case study of the Gorzyce municipal wastewater treatment plant in Poland. Water-to-water heat pump configurations and application scenarios are analyzed together with data-driven forecasting of wastewater outflow using artificial neural networks (MLP and RBF). Operational data from 2025 were used to estimate thermal potential and support system sizing. RBF networks provided more accurate flow forecasts than MLP models, improving reliability of energy recovery planning. Results show that even with a 1 K cooling depth, the annual heat recovery potential reaches about 1.16 GWh. The proposed heat pump system achieved the COP values of 3.0–3.4 and seasonal COP around 3.2, confirming high technical performance supported by stable wastewater temperatures. The recovered heat can fully cover the facility’s heating demand, demonstrating clear technical feasibility. The economic analysis indicates annual savings of about EUR 2310 compared to gas heating, with a simple payback period of roughly 13 years, reduced to 7–8 years when combined with on-site photovoltaics. Environmental benefits include CO₂ emission reductions of about 5.5 tones per year. Overall, wastewater heat recovery supported by predictive modeling and renewable electricity is a practical, cost-effective, and environmentally friendly solution for municipal infrastructure. Full article

Forecasting influent flow in Wastewater Treatment Plants (WWTPs) is critical for managing operational risks during flash floods, especially in Spain’s Mediterranean coastal regions. These facilities, essential for public health and environmental protection, are vulnerable to abrupt inflow surges caused by heavy rainfall. This study proposes a data-driven approach combining historical flow and rainfall data to predict short-term inflow dynamics. Several models were evaluated, including Random Forest, XGBoost, CatBoost, and LSTM, using metrics such as Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R-squared (R²). XGBoost outperformed the others, particularly under severe class imbalance, with only 1% of the data representing rainfall events. Hyperparameter tuning and input window size analysis revealed that accurate predictions are achievable with just 14 days of training data from a 10-year (2012–2022) dataset sourced from a single WWTP and on-site weather station. The proposed framework supports proactive WWTP management during extreme weather events. Full article

This study investigates the capability of Gaussian process regression (GPR) models in the probabilistic forecasting of water flow and depth in a combined sewer system. Traditionally, deterministic methods have been implemented in sewer flow forecasting and anomaly detection, two crucial techniques for a good wastewater network and treatment plant management. However, with the uncertain nature of the factors impacting on sewer flow and depth, a probabilistic approach which takes uncertainties into account is preferred. This research introduces a novel use of GPR in sewer systems for real-time control and forecasting. To this end, a composite kernel is designed to capture flow and depth patterns in dry- and wet-weather periods by considering the underlying physical characteristics of the system. The multi-input, single-output GPR model is evaluated using root mean square error (RMSE), coverage, and differential entropy. The model demonstrates high predictive accuracy for both treatment plant inflow and manhole water levels across various training durations, with coverage values ranging from 87.5% to 99.4%. Finally, the model is used for anomaly detection by identifying deviations from expected ranges, enabling the estimation of surcharge and overflow probabilities under various conditions. Full article

Wastewater treatment plants (WWTPs) connected to combined sewer systems must cope with high flows during wet-weather conditions, often leading to bypass and thus pollution of water bodies. Radar rainfall forecasts coupled with a rainfall-runoff model provides flow and volume forecasts that can be used for deciding when to switch from normal to wet-weather operation, which temporarily allows for higher inflow. However, forecasts are by definition uncertain and may lead to potential mismanagement, e.g., false alarms and misses. Our study focused on two years of operational data from the Damhuså sewer catchment and WWTP. We used the Relative Economic Value (REV) framework to optimize the control parameters of a baseline control strategy (thresholds on flow measurements and radar flow prognosis) and to test new control strategies based on volume instead of flow thresholds. We investigated two situations with different objective functions, considering higher negative impact from misses than false alarms and vice versa, and obtained in both cases a reduction of the rate of false alarms, higher flow thresholds and lower bypass compared to the baseline control. We also assess a new control strategy that employs thresholds of predicted accumulated volume instead of predicted flow and achieved even better results. Full article

In recent years, wastewater reuse has become crucial for addressing global freshwater scarcity and promoting sustainable water resource development. Accurate inflow volume predictions are essential for enhancing operational efficiency in water treatment facilities and effective wastewater utilization. Traditional and decomposition integration models often struggle with non-stationary time series, particularly in peak and anomaly sensitivity. To address this challenge, a differential decomposition integration model based on real-time rolling forecasts has been developed. This model uses an initial prediction with a machine learning (ML) model, followed by differential decomposition using Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN). A Time-Aware Outlier-Sensitive Transformer (TS-Transformer) is then applied for integrated predictions. The ML-CEEMDAN-TSTF model demonstrated superior accuracy compared to basic ML models, decomposition integration models, and other Transformer-based models. This hybrid model explicitly incorporates time-scale differentiated information as a feature, improving the model’s adaptability to complex environmental data and predictive performance. The TS-Transformer was designed to make the model more sensitive to anomalies and peaks in time series, addressing issues such as anomalous data, uncertainty in water volume data, and suboptimal forecasting accuracy. The results indicated that: (1) the introduction of time-scale differentiated information significantly enhanced model accuracy; (2) ML-CEEMDAN-TSTF demonstrated higher accuracy compared to ML-CEEMDAN-Transformer; (3) the TS-Transformer-based decomposition integration model consistently outperformed those based on LSTM and eXtreme Gradient Boosting (XGBoost). Consequently, this research provides a precise and robust method for predicting reclaimed water volumes, which holds significant implications for research on clean water and water environment management. Full article

The ongoing digitalization of critical infrastructures enables more efficient processes, but also comes with new challenges related to potential cyber-physical attacks or incidents. To manage their associated risk, a precise and systematic framework should be adopted. This paper describes a general methodology that is consistent with the Risk Management ISO (31000-2018) and builds on specific tools developed within the H2020 digital-water.city (DWC) project. The approach has been demonstrated for a digital solution of the DWC project that allows to visualize inflow predictions for the Wastewater Treatment Plant (WWTP) in the city of Copenhagen. Specifically, the risk assessment and risk treatment steps are demonstrated in the case of the spoofing of the web interface where misleading forecast data may turn into fallacious maintenance schedules for the operators. The adopted methodology applied to the selected use case led to the identification of convenient measures for risk mitigation. Full article

Due to the high underground water level, frequent rainfall, and large amounts of infiltration and inflow (I/I) into the sewage system, a city in the plain river network region had to face a series of problems caused by the high water-level operation of the drainage system. Suzhou, a city in the Yangtze River Delta region of China, can be a representative of cities in plain river networks, where this research was carried out. The amount of I/I into the sewage system was evaluated, and the storm water management model (SWMM) was used to further calculate the sewer water storage capacity under dry and wet weather with multi-year average rainfall. Based on the offline model calculation and artificial experiences, the rule-based online regulation and storage real-time control strategy (RTC) is verified, and the online regulation and storage intelligent scheduling demonstration is carried out in the central-city district of Suzhou. The results showed that the infiltration in dry weather accounted for about 20–25% of the total collected wastewater; in wet weather (36 mm precipitation), the extraneous water induced by I/I peaked at 73.64%. The collaborative control of regional multi-stage pumping stations through RTC of the sewage system can effectively avoid the high water-level operation caused by peak sewage flows on dry days. In combination with rainfall forecasting, the coordinated control of plants and pumping stations to pre-empty the sewer pipelines prior to rainfall can, to some extent (up to 35 mm of rainfall in this study), cope with the increase in I/I induced by rainfall. Full article

Control of wastewater treatment plants (WWTPs) is challenging not only because of their high nonlinearity but also because of important external perturbations. One the most relevant of these perturbations is weather. In fact, different weather conditions imply different inflow rates and substance (e.g., N-ammonia, which is among the most important) concentrations. Therefore, weather has traditionally been an important signal that operators take into account to tune WWTP control systems. This signal cannot be directly measured with traditional physical sensors. Nevertheless, machine learning-based soft-sensors can be used to predict non-observable measures by means of available data. In this paper, we present novel research about a new soft-sensor that predicts the current weather signal. This weather prediction differs from traditional weather forecasting since this soft-sensor predicts the weather conditions as an operator does when controling the WWTP. This prediction uses a model based on past WWTP influent states measured by only a few physical and widely applied sensors. The results are encouraging, as we obtained a good accuracy level for a relevant and very useful signal when applied to advanced WWTP control systems. Full article

Autoregressive Integrated Moving Average (ARIMA) is a time series analysis model that can be dated back to 1955. It has been used in many different fields of study to analyze time series and forecast future data points; however, it has not been widely used to forecast daily wastewater influent flow. The objective of this study is to explore the possibility for wastewater treatment plants (WWTPs) to utilize ARIMA for daily influent flow forecasting. To pursue the objective confidently, five stations across North America are used to validate ARIMA’s performance. These stations include Woodward, Niagara, North Davis, and two confidential plants. The results demonstrate that ARIMA models can produce satisfactory daily influent flow forecasts. Considering the results of this study, ARIMA models could provide the operating engineers at both municipal and rural WWTPs with sufficient information to run the stations efficiently and thus, support wastewater management and planning at various levels within a watershed. Full article

Forecasting long-term power production of small hydropower (SHP) plants is of great significance for coordinating with large-medium hydropower (LHP) plants. Accurate forecasting can solve the problems of waste-water and abandoned electricity and ensure the safe operation of the power system. However, it faces a series of challenges, such as lack of sufficient data, uncertainty of power generation, no regularity of a single station and poor forecasting models. It is difficult to establish a forecasting model based on classical and mature prediction models. Therefore, this paper introduces a correlation analysis method for forecasting power production of SHP plants. By analyzing the correlation between SHP and LHP plants, a safe conclusion can be drawn that the power production of SHP plants show similar interval inflow to LHP plants in the same region. So a regression model is developed to forecast power production of SHP plants by using the forecasting inflow values of LHP plants. Taking the SHP plants in Yunnan province as an example, the correlation between SHP and LHP plants in a district or county are analyzed respectively. The results show that this correlation method is feasible. The proposed forecasting method has been successfully applied to forecast long-term power production of SHP plants in the 13 districts of the Yunnan Power Grid. From the results, the rationality, accuracy and generality of this method have been verified. Full article