Real-time control of urban drainage systems using neuro-evolution.

With climate change and urbanization, existing urban drainage systems are being stressed beyond their design capacity in many parts of the world. Real-time control (RTC) can improve the performance of these systems and reduce the need for system upgrades. However, developing optimal control policies for RTC is a challenging research area due to computational demands, high uncertainties and system dynamics. This study presents a new RTC method using neuro-evolution for controlling combined sewer overflow (CSO) in urban drainage systems. Neuro-evolution is an approach to neural network research by evolutionary algorithms. Neuro-evolution realizes RTC by training the control policy in advance, thus avoiding the online optimization process in the application period. The simulation results of the benchmark Astlingen network indicate that the trained control policy outperforms the equal filling degree strategy in terms of CSO volume reduction and robustness in the face of tank level uncertainty. The performance analysis of the typical CSO events shows that the control policy mainly makes positive contributions during 'small' CSO events rather than 'large' ones. In particular, the effectiveness of the control policy in 'small' CSO events is more prominent in the initial phase of the events compared with the final phase. This work stands to support a foundation for future studies in the control of urban water systems based on neuro-evolution.

Gated graph neural networks for identifying contamination sources in water distribution systems.

Contamination events in water distribution networks (WDN) pose significant threats to water supply and public health. Rapid and accurate contamination source identification (CSI) can facilitate the development of remedial measures to reduce impacts. Though many machine learning (ML) methods have been proposed for fast detection, there is a critical need for approaches capturing complex spatial dynamics in WDNs to enhance prediction accuracy. This study proposes a gated graph neural network (GGNN) for CSI in the WDN, incorporating both spatiotemporal water quality data and flow directionality between network nodes. Evaluated across various contamination scenarios, the GGNN demonstrates high prediction accuracy even with limited sensor coverage. Notably, directional connections significantly enhance the GGNN CSI accuracy, underscoring the importance of network topology and flow dynamics in ML-based WDN CSI approaches. Specifically, the method achieves a 92.27% accuracy in narrowing the contamination source to 5 points using just 2 h of sensor data. The GGNN showcases resilience under model and measurement uncertainties, reaffirming its potential for real-time implementation in practice. Moreover, our findings highlight the impact of sensor sampling frequency and measurement accuracy on CSI accuracy, offering practical insights for ML methods in water network applications.

The effect of green infrastructure on resilience performance in combined sewer systems under climate change.

Climate change is currently reshaping precipitation patterns, intensifying extremes, and altering runoff dynamics. Particularly susceptible to these impacts are combined sewer systems (CSS), which convey both stormwater and wastewater and can lead to combined sewer overflow (CSO) discharges during heavy rainfall. Green infrastructure (GI) can help mitigate these discharges and enhance system resilience under historical conditions; however, the quantification of its effect on resilience in a future climate remains unknown in the literature. This study employs a modified Global Resilience Analysis (GRA) framework for continuous simulation to quantify the impact of climate change on CSS resilience, particularly CSOs. The study assesses the efficacy of GI interventions (green roofs, permeable pavements, and bioretention cells) under diverse future rainfall scenarios based on EURO-CORDEX regional climate models (2085-2099) and three Representative Concentration Pathways (2.6, 4.5, 8.5 W/m2). The findings underscore a general decline in resilience indices across the future rainfall scenarios considered. Notably, the total yearly CSO discharge volume increases by a range of 145 % to 256 % in response to different rainfall scenarios. While GI proves effective in increasing resilience, it falls short of offsetting the impacts of climate change. Among the GI options assessed, green roofs routed to pervious areas exhibit the highest adaptive capacity, ranging from 9 % to 22 % at a system level, followed by permeable pavements with an adaptation capacity between 7 and 13 %. By linking the effects of future rainfall scenarios on CSO performance, this study contributes to understanding GI's potential as a strategic tool for enhancing urban resilience.

Enhanced Stability of Dimethyl Ether Carbonylation through Pyrazole Tartrate on Tartaric Acid-Complexed Cobalt-Iron-Modified Hydrogen-Type Mordenite.

In this study, pyrazole tartrate (Pya·DL) and tartaric acid (DL) complexed with cobalt-iron bimetallic modified hydrogen-type mordenite (HMOR) were prepared using the ion exchange method. The results demonstrate that the stability of the dimethyl ether (DME) carbonylation reaction to methyl acetate (MA) was significantly improved after the introduction of Pya·DL to HMOR. The Co∙Fe∙DL-Pya·DL-HMOR (0.8) sample exhibited sustainable stability within 400 h DME carbonylation, exhibiting a DME conversion rate of about 70% and MA selectivity of above 99%. Through modification with the DL-complexed cobalt-iron bimetal, the dispersion of cobalt-iron was greatly enhanced, leading to the formation of new metal Lewis acidic sites (LAS) and thus a significant improvement in catalysis activity. Pya·DL effectively eliminated non-framework aluminum in HMOR, enlarged its pore size, and created channels for carbon deposition diffusion, thereby preventing carbon accumulation and pore blockage. Additionally, Pya·DL shielded the Bronsted acid sites (BAS) in the 12 MR channel, effectively suppressing the side reactions of carbon deposition and reducing the formation of hard carbon deposits. These improvements collectively contribute to the enhanced stability of the DME carbonylation reaction.

Global resilience analysis of combined sewer systems under continuous hydrologic simulation.

Managing and reducing combined sewer overflow (CSO) discharges is crucial for enhancing the resilience of combined sewer systems (CSS). However, the absence of a standardised resilience analysis approach poses challenges in developing effective discharge reduction strategies. To address this, our study presents a top-down method that expands the existing Global Resilience Analysis to quantify resilience performance in CSS. This approach establishes a link between threats (e.g., rainfall) and impacts (e.g., CSOs) through continuous and long-term simulation, accommodating various rainfall patterns, including extreme events. We assess CSO discharge impacts from a resilience perspective by introducing eight new metrics. We conducted a case study in Fehraltorf, Switzerland, analysing the performance of three green infrastructure (GI) types (bioretention cells, green roofs, and permeable pavements) over 38 years. The results demonstrated that GI enhanced all resilience indices, with variations observed in individual CSO performance metrics and their system locations. Notably, in Fehraltorf, green roofs emerged as the most effective GI type for improving resilience, while the downstream outfall displayed the highest resilience enhancement. Overall, our proposed method enables a shift from event-based to continuous simulation analysis, providing a standardised approach for resilience assessment. This approach informs the development of strategies for CSO discharge reduction and the enhancement of CSS resilience.

The structure design of integrated urban drainage systems: A view of robust optimization.

Rapid urbanization puts a lot of pressure on urban water pollution from point and non-point sources, calling for the practical, specific, and integrated management of urban drainage systems (UDS). The structural design of an integrated UDS is essential for highly complex and uncertain urban water management. In this study, we developed a multi-objective robust optimization model to explore the optimal structures of UDS considering system uncertainty. We applied this model to City B, northern China, to illustrate its effectiveness. The results show that the model can produce optimal designs with a more robust performance in terms of structural uncertainty. When the uncertainty degree ranges from 5% to 20%, a considerable extra cost (increased by 1.10-2.68 times) is required to improve the robustness of UDS. With the increase in structural uncertainty, the fraction of the cost invested in the stormwater subsystem increased from 10.2% to 27.2%. The findings showed that stormwater management is efficient in coping with system uncertainty. The research results promote an understanding of robust urban drainage systems.

Regulatory Implications of Integrated Real-Time Control Technology under Environmental Uncertainty.

Integrated real-time control (RTC) of urban wastewater systems, which can automatically adjust system operation to environmental changes, has been found in previous studies to be a cost-effective strategy to strike a balance between good surface water quality and low greenhouse gas emissions. However, its regulatory implications have not been examined. To investigate the effective regulation of wastewater systems with this technology, two permitting approaches are developed and assessed in this work: upstream-based permitting (i.e., environmental outcomes as a function of upstream conditions) and means-based permitting (i.e., prescription of an optimal RTC strategy). An analytical framework is proposed for permit development and assessment using a diverse set of high performing integrated RTC strategies and environmental scenarios (rainfall, river flow rate, and water quality). Results from a case study show that by applying means-based permitting, the best achievable, locally suitable environmental outcomes (subject to 10% deviation) are obtained in over 80% of testing scenarios (or all testing scenarios if 19% of performance deviation is allowed) regardless of the uncertain upstream conditions. Upstream-based permitting is less effective as it is difficult to set reasonable performance targets for a highly complex and stochastic environment.

Alterations of kinematics in knees after single versus multiple radius femoral prostheses total knee arthroplasty: a retrospective study.

BACKGROUND: Design modifications in prostheses may cause alterations in gait kinematics, thus influencing functional restoration of knees after total knee arthroplasty (TKA). The aim of the study was to investigate the differences in gait kinematics and clinical outcomes after single radius (SR) versus multiple radius (MR) TKA. METHOD: The present retrospective study included 38 unilateral TKA involving 20 knees using MR design implant and 18 knees using SR design implant. Thirty-six healthy volunteers were also recruited. The mean follow-up time was 16 ± 3 months. At the end of follow-up, the 6 degrees of freedom (DOF) kinematics of knees and range of motion (ROM) were measured with a portable optical tracking system. Knee society score (KSS) and knee injury, and osteoarthritis outcome score (KOOS) were also collected. RESULTS: Patients in the SR group had significantly higher scores in activities of daily living (84.7 ± 15.9) and sports and recreation (67.5 ± 25.2) KOOS sub-score than MR group (69.9 ± 17.6, P = 0.012; 50.0 ± 20.8, P = 0.027, respectively). Significant differences were detected between MR knees and SR knees (1.82° ± 3.11° vs 4.93° ± 3.58°, P = 0.009), and MR knees and healthy knees (1.82° ± 3.11° vs 3.62° ± 3.52°, P = 0.032) in adduction/abduction ROM. The proximal/distal translation was significantly smaller in MR knees (0.58 ± 0.54 cm) compared with SR knees (1.03 ± 0.53 cm, P = 0.003) or healthy knees (0.84 ± 0.45 cm, P = 0.039). SR knees (0.24 ± 0.40 cm) had smaller translation compared with the MR group (0.54 ± 0.33 cm, P = 0.017) and control group (0.67 ± 0.36 cm, P = 0.028). No significant difference was detected in the other DOFs during the gait cycle. Significant difference was detected in extension/flexion, internal/external rotation, adduction/abduction, proximal/distal and medial/lateral among MR, SR and healthy knees. CONCLUSION: After TKA, patients have altered gait kinematics compared with the control group. MR and SR design showed varied characteristics in 6 DOF gait kinematics, which could be the cause of the difference in functional outcome.

Performance evaluation of time-sharing utilization of multi-function sponge space to reduce waterlogging in a highly urbanizing area.

Urban waterlogging is a dilemma faced by many highly urbanizing areas. To solve the contradiction between the space requirement for waterlogging control and the scarcity of urban space, time-sharing utilization of the multi-function sponge space (MFSS) is promoted in some urbanizing areas. The MFSS is designed to have certain social or economic functions during dry or light rain events and detains stormwater on heavy rain events. However, there is lack of understanding on how to achieve the maximum benefit of multi-function. In this study, three time-sharing utilization modes are proposed to use MFSS to detain runoff: when the rain event begins (Mode A), when cumulative rainfall is greater than a specific threshold (Mode B), or when rainfall intensity is higher than a specific threshold (Mode C). A methodological framework based on the Storm Water Management Model (SWMM) is proposed to evaluate the waterlogging reduction performance of the three modes under different rainfall conditions and thresholds for enabling MFSS in an urbanizing catchment in Shenzhen, China. The performance is measured by comparing the total volume of overflow from manholes of the drainage system with and without MFSS during a storm event. The results indicate that: (1) Under Mode A, the performance is more effective under a light storm event with an early peak; (2) Under Mode B, as the cumulative rainfall threshold for enabling MFSS increases, the overflow first decreases and then increases. Different threshold values have to be set for different types of rainfall events to achieve the best performance; (3) Under Mode C, as the rainfall intensity threshold for enabling MFSS increases, the overflow also first decreases and then rapidly increases at a high threshold value. The mode has an identical range of optimal thresholds under different types of rainfall events. Furthermore, Mode C has higher efficiency in overflow reduction than the other two modes, no matter whether under design storms or historical storms. Therefore, Mode C is recommended as an efficient and stable utilization mode for MFSS.

Spatial variations of pollutants from sewer interception system overflow.

Sewer interception systems have been built along rivers in rapidly urbanizing areas to collect unregulated sewage discharges due to misconnections between storm sewers and sanitary sewers. During storm events, combined sewage might overflow from these systems into rivers through orifices and deteriorate water quality in rivers. Interception system overflows (ISOs) from different orifices in a sewer interception system might interact with each other, therefore pollutants from ISOs show a spatial variation. This paper aims to understand the spatial variation of pollutants from ISOs for informed decision making. In this study, an urbanized catchment in China is chosen as the study area, and the Storm Water Management Model (SWMM) is used to examine the spatial variation of pollutants from ISOs and to analyze the effect of sewer separation on ISOs. The results obtained from the case study indicate that: (1) Critical rainfall amounts which trigger overflows decrease downstream in an interception system while annual ISO volumes and pollutant loads from ISOs increase downstream; additionally, these variations are influenced by sizes and slopes of interceptors; (2) Runoff is the main source of COD from ISOs while sewage is the main source of NH3-N, and ratios of pollutants from sewage to ISOs increase downstream; (3) Sewer separation can significantly reduce pollutant loads from sewage to ISOs, but it cannot significantly reduce pollutant loads from runoff. In order to mitigate ISO pollution, it is suggested to increase conveyance capacities of interceptors in the downstream, separate sewage from runoff, and promote source control for urban runoff in highly urbanized areas.

Reliable, Resilient and Sustainable Urban Drainage Systems: An Analysis of Robustness under Deep Uncertainty.

Reliability, resilience and sustainability are key goals of any urban drainage system. However, only a few studies have recently focused on measuring, operationalizing and comparing such concepts in a world of deep uncertainty. In this study, these key concepts are defined and quantified for a number of gray, green and hybrid strategies, aimed at improving the capacity issues of an existing integrated urban wastewater system. These interventions are investigated by means of a regret-based approach, which evaluates the robustness (that is the ability to perform well under deep uncertainty conditions) of each strategy in terms of the three qualities through integration of multiple objectives (i.e., sewer flooding, river water quality, combined sewer overflows, river flooding, greenhouse gas emissions, cost and acceptability) across four different future scenarios. The results indicate that strategies found to be robust in terms of sustainability were typically also robust for resilience and reliability across future scenarios. However, strategies found to be robust in terms of their resilience and, in particular, for reliability did not guarantee robustness for sustainability. Conventional gray infrastructure strategies were found to lack robustness in terms of sustainability due to their unbalanced economic, environmental and social performance. Such limitations were overcome, however, by implementing hybrid solutions that combine green retrofits and gray rehabilitation solutions.

Antiresorptive Agents are More Effective in Preventing Titanium Particle-Induced Calvarial Osteolysis in Ovariectomized Mice Than Anabolic Agents in Short-Term Administration.

Aseptic loosening due to wear particle-induced osteolysis is the main cause of arthroplasty failure and the influence of postmenopausal osteoporosis and anti-osteoporosis treatment on Titanium (Ti) particle-induced osteolysis remains unclear. 66 C57BL/6J female mice were used in this study. Ovariectomy (OVX) was performed to induce osteopenia mice and confirmed by micro-CT. The Ti particle-induced mouse calvaria osteolysis model was established subsequently and both OVX and Sham-OVX mice were divided into four groups, respectively: Ti (-) group, Ti group, Ti + zoledronic acid (ZOL) group (50ug/kg, local administration, single dose) and Ti + teriparatide (TPTD) group (40ug/kg/d, subcutaneous injection*14d). Mice calvarias were collected for micro-CT and histomorphometric analysis 2 weeks after particle induction. 8 weeks after bilateral OVX, significantly reduced BMD and microstructure parameters in both proximal tibia and calvaria were observed in OVX mice when comparing with Sham-OVX mice. OVX mice in Ti group had not only markly decreased BMD and BV/TV, but also significantly increased total porosity, eroded surface area and osteoclast numbers when comparing with Sham-OVX mice. Shown by Two-way ANOVA analysis, the interaction terms between OVX and Ti implantation on micro-CT and histomorphometry parameters didn't reach significant difference. As illustrated by micro-CT and histological analysis, ZOL treatment markedly inhibited Ti particle-induced osteolysis in OVX mice and Sham-OVX mice, and there were significant differences when comparing to both Ti and Ti+TPTD group. The combination of osteoporosis and Ti particle implantation result in aggravated bone resorption, accompanied with increased osteoclasts and excessive inflammation response. ZOL was more effective in preventing Ti particle-induced osteolysis in both OVX mice and Sham-OVX mice than TPTD in short-term administration. ZOL exert the protective effects on Ti particle-induced bone loss via the suppression of osteoclasts.

Rapid surface water intervention performance comparison for urban planning.

Surface water flooding can be a significant source of damage and disruption in urban areas. The complexity of urban surfaces, the need for spatially disaggregated approaches and the multiplicity of interventions makes management challenging from a number of perspectives. This research responds to the challenge of selecting appropriate surface water management interventions by applying a fast assessment framework to generate evidence for comparing strategies at low resource cost during initial design. This is demonstrated by simulating flood dynamics and comparing damage costs in 144 flood scenarios. The main finding of this work is that a high-level quantitative assessment of large numbers of scenarios is capable of providing evidence to identify performance trends and consider resilience to extreme events at an early stage of planning.

Attribute-based intervention development for increasing resilience of urban drainage systems.

Resilience building commonly focuses on attributes such as redundancy. Whilst this may be effective in some cases, provision of specific attributes does not guarantee resilient performance and research is required to determine the suitability of such approaches. This study uses 250 combined sewer system virtual case studies to explore the effects of two attribute-based interventions (increasing distributed storage and reducing imperviousness) on performance-based resilience measures. These are found to provide improvement in performance under system failure in the majority of case studies, but it is also shown that attribute-based intervention development can result in reduced resilience.

Cost-Effective River Water Quality Management using Integrated Real-Time Control Technology.

Integrated real-time control (RTC) of urban wastewater systems is increasingly presented as a promising and emerging strategy to deliver improved surface water quality by responsive operation according to real-time data collected from the sewer system, treatment plant, and the receiving water. However, the detailed benefits and costs associated with integrated RTC have yet to be comprehensively evaluated. Built on state-of-the-art modeling and analytical tools, a three-step framework is proposed to develop integrated RTC strategies which cost-effectively maximize environmental outcomes. Results from a case study show integrated RTC can improve river quality by over 20% to meet the "good status" requirements of the EU Water Framework Directive with a 15% reduced cost, due to responsive aeration with changing environmental assimilation capacity. The cost-effectiveness of integrated RTC strategies is further demonstrated against tightening environmental standards (to the strictest levels) and against two commonly used compliance strategies. Compared to current practices (seasonal/monthly based operation), integrated RTC strategies can reduce costs while improving resilience of the system to disturbances and reducing environmental risk.

A framework to support decision making in the selection of sustainable drainage system design alternatives.

This paper presents a new framework for decision making in sustainable drainage system (SuDS) scheme design. It integrates resilience, hydraulic performance, pollution control, rainwater usage, energy analysis, greenhouse gas (GHG) emissions and costs, and has 12 indicators. The multi-criteria analysis methods of entropy weight and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) were selected to support SuDS scheme selection. The effectiveness of the framework is demonstrated with a SuDS case in China. Indicators used include flood volume, flood duration, a hydraulic performance indicator, cost and resilience. Resilience is an important design consideration, and it supports scheme selection in the case study. The proposed framework will help a decision maker to choose an appropriate design scheme for implementation without subjectivity.

An Integrated Environmental Assessment of Green and Gray Infrastructure Strategies for Robust Decision Making.

The robustness of a range of watershed-scale "green" and "gray" drainage strategies in the future is explored through comprehensive modeling of a fully integrated urban wastewater system case. Four socio-economic future scenarios, defined by parameters affecting the environmental performance of the system, are proposed to account for the uncertain variability of conditions in the year 2050. A regret-based approach is applied to assess the relative performance of strategies in multiple impact categories (environmental, economic, and social) as well as to evaluate their robustness across future scenarios. The concept of regret proves useful in identifying performance trade-offs and recognizing states of the world most critical to decisions. The study highlights the robustness of green strategies (particularly rain gardens, resulting in half the regret of most options) over end-of-pipe gray alternatives (surface water separation or sewer and storage rehabilitation), which may be costly (on average, 25% of the total regret of these options) and tend to focus on sewer flooding and CSO alleviation while compromising on downstream system performance (this accounts for around 50% of their total regret). Trade-offs and scenario regrets observed in the analysis suggest that the combination of green and gray strategies may still offer further potential for robustness.

Making Waves: Towards data-centric water engineering.

Artificial intelligence (AI) is expected to transform many scientific disciplines, with the potential to significantly accelerate scientific discovery. This perspective calls for the development of data-centric water engineering to tackle water challenges in a changing world. Building on the historical evolution of water engineering from empirical and theoretical paradigms to the current computational paradigm, we argue that a fourth paradigm, i.e., data-centric water engineering, is emerging driven by recent AI advances. Here we define a new framework for data-centric water engineering in which data are transformed into knowledge and insight through a data pipeline powered by AI technologies. It is proposed that data-centric water engineering embraces three principles - data-first, integration and decision making. We envision that the development of data-centric water engineering needs an interdisciplinary research community, a shift in mindset and culture in the academia and water industry, and an ethical and risk framework to guide the development and application of AI. We hope this paper could inspire research and development that will accelerate the paradigm shift towards data-centric water engineering in the water sector and fundamentally transform the planning and management of water infrastructure.

Real-time water quality prediction in water distribution networks using graph neural networks with sparse monitoring data.

Ensuring the safety and reliability of drinking water supply requires accurate prediction of water quality in water distribution networks (WDNs). However, existing hydraulic model-based approaches for system state prediction face challenges in model calibration with limited sensor data and intensive computing requirements, while current machine learning models are lack of capacity to predict the system states at sites that are not monitored or included in model training. To address these gaps, this study proposes a novel gated graph neural network (GGNN) model for real-time water quality prediction in WDNs. The GGNN model integrates hydraulic flow directions and water quality data to represent the topology and system dynamics, and employs a masking operation for training to enhance prediction accuracy. Evaluation results from a real-world WDN demonstrate that the GGNN model is capable to achieve accurate water quality prediction across the entire WDN. Despite being trained with water quality data from a limited number of sensor sites, the model can achieve high predictive accuracies (Mean Absolute Error = 0.07 mg L-1 and Mean Absolute Percentage Error = 10.0 %) across the entire network including those unmonitored sites. Furthermore, water quality-based sensor placement significantly improves predictive accuracy, emphasizing the importance of careful sensor location selection. This research advances water quality prediction in WDNs by offering a practical and effective machine learning solution to address challenges related to limited sensor data and network complexity. This study provides a first step towards developing machine learning models to replace hydraulic models in WDN modelling.

Improving the interpretability of deep reinforcement learning in urban drainage system operation.

Deep reinforcement learning (DRL) has been increasingly used as an adaptive and efficient solution for real-time control (RTC) of the urban drainage system (UDS). Despite the promising potential of DRL, it is a black-box model whose control logic and control consequences are difficult to be understood and evaluated. This leads to issues of interpretability and poses risks in practical applications. This study develops an evaluation framework to analyze and improve the interpretability of DRL-based UDS operation. The framework includes three analysis methods: Sobol sensitivity analysis, tree-based surrogate modelling, and conditional probability analysis. It is validated using two different DRL approaches, i.e., deep Q-learning network (DQN) and proximal policy optimization (PPO), which are trained to reduce combined sewer overflow (CSO) discharges and flooding in a real-world UDS. According to the results, the two DRLs have been shown to perform better than a rule-based control system that is currently being used. Sobol sensitivity analysis indicates that DQN is particularly sensitive to the flow of links and rainfall, while PPO is sensitive to all the states. Tree-based surrogate models effectively reveal the control logic behind the DRLs and indicate that PPO is more comprehensible but DQN is more forward-looking. Conditional probability analysis demonstrates the potential control consequences of the DRLs and identifies three situations where the DRLs are ineffective: a) the storage of UDS is fully utilized; b) peak flows have already passed through actuators; c) a substantial amount of water enters one location simultaneously. The proposed evaluation framework enhances the interpretability of DRL in UDS operations, fostering trust and confidence from operators, stakeholders, and regulators.