Conference Agenda

Regular performance assessment of blue-green infrastructure (BGI) is essential to ensure sustainable urban stormwater management. However, this task is challenging due to the complexity of the systems, financial constraints and workforce limitations. BGI performance assessment is often relative to municipal design regulations, such as ponding duration or overflow. Predictions of performance is typically done through physics derived hydrological modelling, that oversimplify the system or have complex data inputs and computational costs. BGI performance prediction can be improved by linking observational data and machine learning (ML). This study applies different ML models to predict ponding duration in BGI. This study leverages a database for several BGI sites, coupled with weather variables, to predict BGI performance. To address the challenge of limited high-quality observed data, we supplemented observed data with SWMM generated outputs for different types of BGI. All models show R² score above 0.70 except linear regression, however the CatBoost model performed the best (R²=0.83). Precipitation length and storm duration were found as the two most important features in the models. The ability to predict water ponding duration as an indicator of system performance, is an important stride towards sustainable and efficient management of BGI at the city-scale.

The rapid growth of urbanisation profoundly affects the urban hydrological cycle by augmenting stormwater runoff, reducing surface roughness, and increasing impermeable surfaces. In these circumstances, sewer networks may become overwhelmed, resulting in pressurised flows and backwater effects occurrences in the sewer conduits. Sustainable Drainage Systems (SuDSs) can represent a valid strategy to mitigate these effects. In this regard, the present study investigates the impact of green roof installations on the reduction of pressurised flow conditions within sewer networks. Numerical simulations were performed by simulating the flow behaviour of an urban drainage network with a basic topology and serving urban subcatchments with an increasing percentage of green roof extension. At this aim, the software EPA SWMM 5.2 was used. Preliminary findings show that green roofs can improve the hydraulic functioning of urban drainage systems by reducing filling ratios, mitigating pressurisation risks and the flood occurrence.

Tree pits are an essential component of Blue-Green Infrastructure, balancing stormwater management, urban cooling, and biodiversity. However, their design must consider both drainage efficiency and tree health, as excessive water retention can lead to waterlogging, while insufficient retention increases drought stress. Existing models either require complex parameterization or lack the ability to predict both saturated and unsaturated conditions simultaneously. This study presents a conceptual tree pit model integrated into the EPA SWMM framework, enabling long-term simulations of waterlogging and water stress probabilities. The model introduces a four-layer approach, incorporating a surface, soil, tree, and storage layer, and applies a modified groundwater model and water stress response model to predict plant-available water and waterlogging risks. A case study in Melbourne, Australia, using 18 months of water level data from nine tree pits, validates the model’s performance. Nash-Sutcliffe Efficiency (NSE) shows reasonable predictive accuracy. The results suggest that tree presence introduces additional processes not yet included in the model. Despite this, the model provides a valuable tool for optimizing tree pit designs, supporting urban water management strategies, and reducing the frequency of extreme water conditions for urban trees.

The Sustainable Drainage System module of the Town Energy Balance model (TEB-SUDS) was developed based on the Equivalent Sustainable Drainage System (E-SUDS) approach and has previously been applied to assess the hydrological responses of individual SUDS types. This study extends the analysis by evaluating the hydrological responses of aggregations of different compartments within an SUDS facility using the TEB-SUDS module. The presented results are benchmarked against the well-established Low Impact Development (LID) module of Storm Water Management Model (SWMM), demonstrating the high capability of the TEB-SUDS module in modelling the hydrological processes of SUDS facility for stormwater management.

Urban areas face increasing challenges from climate change, including flooding, heat stress, and environmental degradation. To address these, Nature-Based Solutions (NBS) offer sustainable approaches, integrating ecological and engineering principles to enhance resilience. However, the implementation of NBS often leads to lock-in effects, where suboptimal initial decisions limit future flexibility. This study presents a prioritization system for NBS implementation, ensuring maximum long-term benefits while avoiding costly redesigns. The proposed framework is informed by real-world implementations from the Interreg Central Baltic MUSTBE (2023) and LIFE LATESTAdapt (2022) projects, incorporating multi-objective performance indicators (MOPI) and cost-benefit analysis (CBA). The results highlight that early-stage decision-making significantly influences the long-term viability and economic efficiency of NBS investments. Case studies demonstrate how flexible design choices and adaptive planning approaches lead to more cost-effective, multi-functional solutions. By integrating environmental, social, and economic considerations, this research provides a practical guide for urban planners and policymakers to optimize NBS strategies while ensuring long-term sustainability.

In this study, the applicability of blue-green infrastructure (BGI) is analysed regarding its influence on flooding and on the water balance under future climate changes in Astana, Kazakhstan using two different model approaches. Therefore, different scenarios with stepwise implementation of BGI in a) a coupled 1D/2D model and b) in a conceptual model approach are used. The coupled 1D/2D model is simulated using design storms. The water balance is first calculated on a historical time series and then on 2 different RCP climate projections. The results show that BGI reduces the extent of the flooded area under the selected boundary conditions and has a positive influence on the water balance. The highest implementation level of BGI can reduce the flooded area by up to 70%. In addition, this implementation level of BGI reduces the total runoff by up to 20% in one of the RCP projections. However, it also shows that the local climate is a crucial factor in the applicability of BGI.

The present research is conducted under the TERESA project funded by the German Federal Ministry of Education and Research.