Designing coupled LID-GREI urban drainage systems: Resilience assessment and decision-making framework

Enhancing the resilience of urban drainage system using deep reinforcement learning

Real-time control (RTC) is an effective method used in urban drainage systems (UDS) for reducing flooding and combined sewer overflows. Recently, RTC based on Deep Reinforcement Learning (DRL) has been proven to have various advantages compared to traditional RTC methods. However, the existing DRL methods solely focus on reducing the total amount of CSO discharge and flooding, ignoring the UDS resilience. Here, we develop new DRL models trained by two new reward functions to enhance the resilience of UDS. These models are tested on a UDS in eastern China, and found to enhance UDS resilience and, simultaneously, reduce the total amount of flooding and CSO discharges. Their performance is influenced by the rainfalls and the DRL types. Specifically, different rainfalls lead to different resilience performance curves and DRL model generalization. The value-based DRL model trained with the duration-weighted reward achieves the best performance in the case study.

Multi-stage optimization framework for synergetic grey-green infrastructure in response to long-term climate variability based on shared socio-economic pathways

Global climate change and rapid urbanization have increasingly intensified extreme rainfall events and surface runoff, posing significant challenges to urban hydrological security. Synergetic Grey-Green Infrastructure (SGGI) has been widely applied to enhance stormwater management in urban areas. However, current research primarily focused on optimizing and evaluating either grey infrastructure (GREI) or green infrastructure (GI) under single rainfall event, neglecting the non-stationary impacts of long-term climate change on infrastructure performance. Therefore, this study introduced a multi-stage optimization framework for SGGI layouts based on shared socio-economic pathways, utilizing graph theory and genetic algorithms to identify optimal solutions through life cycle cost (LCC) and hydraulic reliability in response to varying climate change scenarios. A case study of Shenzhen, China, was conducted to validate this method. The results indicated that: (1) SSP2-4.5 and SSP5-8.5 scenarios revealed significant phase-specific variations in Shenzhen's annual precipitation series; (2) The optimized SGGI layouts yielded substantial LCC savings compared to GREI, with centralized and decentralized strategies achieving reductions of 6.6% and 4.7%, respectively. (3) The SGGI adapted to extreme rainfall conditions by shifting preference from permeable pavements to bioretention cells; (4) The Change-GREI&GI (CGG) strategy consistently outperformed the Change-only-GI (COG) strategy in LCC control and hydraulic reliability, particularly a 1.68% cost advantage under extreme scenarios. These findings highlight the critical role of multi-stage optimization in improving the cost-effectiveness and resilience of integrated grey-green infrastructure systems, providing valuable insights for designing adaptive SGGI strategies that effectively respond to long-term climate variability in urban environments.

Evaluating the effectiveness of environmental sustainability indicators in optimizing green-grey infrastructure for sustainable stormwater management

Green-grey infrastructure is recommended as an innovative stormwater management strategy in response to urban flooding and climate change. Currently, the indicators used to optimize sustainable green-grey infrastructure and evaluate its stormwater management performance have been limited and based on self-defined criteria. In this study, we developed a comprehensive environmental sustainability indicator that integrates reliability, resilience, vulnerability, and hydrological sustainability as one of the objectives for optimizing green-grey infrastructure layout. The new indicator fully considered both system-level and component-level failures. Graph-theoretic algorithm coupled with NSGA-Ⅱ was applied to support the layout design and optimization. Additionally, the hydro-hydraulic performance of representative optimized layouts under extreme storms and climate change scenarios was re-evaluated to compare the effectiveness of various self-defined environmental sustainability indicators. The results demonstrated that under the same budget conditions, layouts optimized using the environmental sustainability indicator proposed in this study demonstrated superior performance, primarily reflected in less flood severity, flood duration, and conduit surcharge. Furthermore, it was effective and necessary to comprehensively consider the system-level overload consequences, the component-level failure-recovery process, and the extent of restoration to the natural hydrological state in the green-grey optimization process. This framework aims to address the stormwater management challenges posed by short-term extreme storms and long-term climate changes, while balancing sustainable economic and natural hydrological states.

Machine learning-based surrogate model assisting stochastic model predictive control of urban drainage systems

Quantifying the uncertainty of stormwater inflow is critical for improving the resilience of urban drainage systems (UDSs). However, the high computational complexity and time consumption obstruct the implementation of uncertainty-addressing methods for real-time control of UDSs. To address this issue, this study developed a machine learning-based surrogate model (MLSM) that maintains high-fidelity descriptions of drainage dynamics and meanwhile diminishes the computational complexity. With stormwater inflow and controls as inputs and system overflow as the output, MLSM is able to fast evaluate system performance, and therefore stochastic optimization becomes feasible. Thus, a real-time control strategy was built by combining MLSM with the stochastic model predictive control. This strategy used stochastic stormwater inflow scenarios as input and aimed to minimize the expected overflow under all scenarios. An ensemble of stormwater inflow scenarios was generated by assuming the forecast errors follow normal distributions. To downsize the ensemble, representative scenarios with their probabilities were selected using the simultaneous backward reduction method. The proposed control strategy was applied to a combined UDS of China. Results are as follows. (1) MLSM fit well with the original high-fidelity urban drainage model, while the computational time was reduced by 99.1%. (2) The proposed strategy consistently outperformed the classical deterministic model predictive control in both magnitude and duration dimensions of system resilience, when the consumed time compatible is with the real-time operation. It is indicated that the proposed control strategy could be used to inform the real-time operation of complex UDSs and thus enhance system resilience to uncertainty.

Assessing runoff control of low impact development in Hong Kong's dense community with reliable SWMM setup and calibration

Low impact development (LID) is a sustainable practice to managing urban runoff. However, its effectiveness in densely populated areas with intense rainfall, such as Hong Kong, remains unclear due to limited studies with similar climate conditions and urban patterns. The highly mixed land use and complicated drainage network present challenges for preparing a Storm Water Management Model (SWMM). This study proposed a reliable framework for setting up and calibrating SWMM by integrating multiple automated tools to address these issues. With a validated SWMM, we examined LID's effects on runoff control in a densely built catchment of Hong Kong. A designed full-scale LID implementation can reduce total and peak runoffs by around 35-45% for 2, 10 and 50-year return rainfalls. However, LID alone may not be adequate to handle the runoff in densely built areas of Hong Kong. As the rainfall return period increases, total runoff reduction increases, but peak runoff reduction remains close. Percentages of reduction in total and peak runoffs decline. The marginal control diminishes for total runoff while remaining constant for peak runoff when increasing the extent of LID implementation. In addition, the study identifies the crucial design parameters of LID facilities using global sensitivity analysis. Overall, our study contributes to accelerating the reliable application of SWMM and deepening the understanding of the effectiveness of LID in ensuring water security in densely built urban communities located near the humid-tropical climate zone, such as Hong Kong.

Construction and application of sponge city resilience evaluation system: a case study in Xi'an, China

Urban vulnerability is evident when highly complex flood risks overlap with diverse cities, and it is important to enhance the resilience of cities to flood shocks. In this study, a sponge city resilience assessment system is established considering engineering, environmental and social indicators, and the grey relational analysis method (GRA) is used to quantify sponge city resilience. At the same time, a multi-objective optimization model is established based on the three dimensions of water ecological environment, drainage safety, and waterlogging safety. The optimal configuration of grey-green infrastructure is weighed by combining the ideal point method, aiming to ensure that cities effectively reduce flood risk through the optimal configuration scheme. Taking the Xiaozhai area in Xi'an as the study area, the evaluation results show that the grey relational degree (GRD) of the resilience indexes of the original scheme is between 0.390 and 0.661 under the seven different return periods, while the optimization scheme ranges from 0.648 to 0.765, with the best sponge city resilience at a return period of 2a. Compared with the original scheme, the optimized sponge city resilience level increases from level II to nearly level I in the low return period and from level IV to level II in the high return period, indicating that city's ability to cope with waterlogging and pollution is enhanced significantly. Besides, the main factor affecting the sponge city resilience is the runoff control rate, followed by pollutant load reduction rate, which can provide a methodological framework for the assessment and improvement of sponge city resilience.

Assessing and optimizing the hydrological performance of Grey-Green infrastructure systems in response to climate change and non-stationary time series

Climate change has led to the increased intensity and frequency of extreme meteorological events, threatening the drainage capacity in urban catchments and densely built-up cities. To alleviate urban flooding disasters, strategies coupled with green and grey infrastructure have been proposed to support urban stormwater management. However, most strategies rely largely on diachronic rainfall data and ignore long-term climate change impacts. This study described a novel framework to assess and to identify the optimal solution in response to uncertainties following climate change. The assessment framework consists of three components: (1) assess and process climate data to generate long-term time series of meteorological parameters under different climate conditions; (2) optimise the design of Grey-Green infrastructure systems to establish the optimal design solutions; and (3) perform a multi-criteria assessment of economic and hydrological performance to support decision-making. A case study in Guangzhou, China was carried out to demonstrate the usability and application processes of the framework. The results of the case study illustrated that the optimised Grey-Green infrastructure could save life cycle costs and reduce total outflow (56-66%), peak flow (22-85%), and TSS (more than 60%) compared to the fully centralised grey infrastructure system, indicating its high superior in economic competitiveness and hydrological performance under climate uncertainties. In terms of spatial configuration, the contribution of green infrastructure appeared not as critical as the adoption of decentralisation of the drainage networks. Furthermore, under extreme drought scenarios, the decentralised infrastructure system exhibited an exceptionally high degree of removal performance for non-point source pollutants.

Multi-stage planning of LID-GREI urban drainage systems in response to land-use changes

Long-term planning of urban drainage systems aimed at maintaining the sustainability of urban hydrology remains challenging. In this study, an innovative multi-stage planning framework involving two adaptation pathways for optimizing hybrid low impact development and grey infrastructure (LID-GREI) layouts in opposing chronological orders was explored. The Forward Planning and Backward Planning are adaptation pathways to increase LID in chronological order based on the initial development stage of an urban built-up area and reduce LID in reverse chronological order based on the final development stage, respectively. Two resilience indicators, which considered potential risk scenarios of extreme storms and pipeline failures, were used to evaluate the performance of optimized layouts when land-use changed and evolved over time. Compared these two pathways, Forward Planning made the optimized layouts more economical and resilient in most risk scenarios when land-use changed, while the layouts optimized by Backward Planning showed higher resilience only in the initial stage. Furthermore, a decentralized scheme in Forward Planning was chosen as the optimal solution when taking costs, reliability, resilience, and land-use changes into an overall consideration. Nevertheless, this kind of reverse optimization order offers a novel exploration in planning pathways for discovering the alternative optimization schemes. More comprehensive solutions can be provided to decision-makers. The findings will shed a light on the exploration of optimized layouts in terms of spatial configuration and resilience performance in response to land-use changes. This framework can be used to support long-term investment and planning in urban drainage systems for sustainable stormwater management.

Supply-Demand Evaluation of Green Stormwater Infrastructure (GSI) Based on the Model of Coupling Coordination

The rational spatial allocation of Green Stormwater Infrastructure (GSI), which is an alternative land development approach for managing stormwater close to the source, exerts a crucial effect on coordinating urban development and hydrological sustainability. The balance between the supply and demand of urban facilities has been an influential standard for determining the rationality of this allocation. However, at this stage, research on evaluating planning from the perspective of supply-demand in GSI is still limited. This study proposed an evaluation method for assessing supply-demand levels in GSIs in Guangzhou, China, using the coupling coordination model consisting of Coupling Degree (CD) and Coupling Coordination Degree (CCD). Furthermore, the spatial distributions of supply-demand balance and resource mismatch were identified. The results indicated that the supply and demand levels of GSI exhibited significant spatial differences in distribution, with most streets being in short supply. The GSI exhibited a high CD value of 0.575 and a poor CCD value of 0.328, implying a significant imbalance in facility allocation. A lot of newly planned facilities failed to effectively cover the streets in need of improvement, so it became essential to adjust the planning scheme. The findings of this study can facilitate the decision-makers in assessing the supply-demand levels in GSI and provide a reference of facility allocation for the sustainable construction of Sponge City.

Battle of centralized and decentralized urban stormwater networks: From redundancy perspective

Recent research underpinned the effectiveness of topological decentralization for urban stormwater networks (USNs) during the planning stage in terms of both capital savings and resilience enhancement. However, how centralized and decentralized USNs' structures with various degrees of redundancy (i.e., redundant water flow pathways) project resilience under functional and structural failure remains an unresolved issue. In this work, we present a systemic and generic framework to investigate the impact of adding redundant flow paths on resilience based on three strategies for optimal centralized versus decentralized USNs. Furthermore, a tailored graph-theory based measure (i.e., eigenvector centrality) is proposed to introduce redundant paths to the critical locations of USNs. The proposed framework is then applied to a real large-scale case study. The results confirm the critical role of layout decentralization under both functional (e.g., extreme precipitation events), and structural failure (e.g., pipe collapse). Moreover, the findings indicate that the implementation of redundant paths could increase resilience performance by up to 8% under functional failure without changing the network's major structural characteristics (i.e., sewer diameters, lengths, and storage capacity), only by leveraging the effective flow redistribution. The scheme proposed in this study can be a fruitful initiative for further improving the USNs' resilience during both planning and rehabilitation stages.

Evaluation of Cropland System Resilience to Climate Change at Municipal Scale Through Robustness, Adaptability, and Transformability: A Case Study of Hubei Province, China

A cropland system is one of the most sensitive socio-ecological systems to climate change, such as drought and flood. Facing frequent extreme weather events worldwide, how to improve cropland system resilience to climate change (CSRCC) and thus ensure food production has been concerned. Although a small number of studies have attempted to evaluate CSRCC through single or multiple indicators, few studies have considered the perspective of the three basic capacities of resilience (i.e., robustness, adaptability, and transformability), which could ignore the dynamic characteristics of cropland system resilience against shocks within a certain period. Therefore, this study first constructs an evaluation index system from the three capacities of system resilience. Then, taking Hubei province, China, as a case and comprehensively using the methods of Delphi, AHP, and TOPSIS to assess the spatio-temporal characteristics of CSRCC at the municipal scale from 2011 to 2018. On this basis, the regional disparities of CSRCC are analyzed by using the Theil coefficient. The results show that the CSRCC of Hubei province fluctuates on a downward trend, with the lowest in 2017 and the highest in 2013. Most municipalities have witnessed a pattern of fluctuated decline, except for a few ones in the plains, such as Wuhan and Jingmen. Generally, municipalities in the plains have greater scores, while some municipalities in the southern and eastern hilly regions show higher adaptability and transformability. In addition, adaptability contributes the least to the CSRCC at the municipal scale. At last, indicator selection against different research objects, influencing mechanism of CSRCC, and policy implications are discussed. This study is expected to provide a reference for the practice in sustainable management and utilization of cropland systems.