Popular modelling tools that implement these models include the EPA-SWMM ( Rossman et al., 2010) and MIKE URBAN ( DHI, 2017). These models have proven to be accurate and to rely only on measurable parameters ( Sims et al., 2019) and can be powerful tools for studies that aim at in-depth understanding of the hydraulic behaviours of the different green roof layers ( Brunetti et al., 2016).Īnother category of physically based models apply simplified and analytical forms of physical equations, such as the Green–Ampt equation for infiltration and the Darcy law for saturated water flow ( Krebs et al., 2016 She and Pang, 2010 Hernes et al., 2020). Several tools exist that can be used to implement this type of model, such as HYDRUS ( Simunek et al., 2005), SWMS-2D ( Simunek et al., 1994) and COMSOL Multiphysics ( Multiphysics, 2013 Sims et al., 2019). Physically based models simulate the water flow in porous media by solving physical equations numerically, such as the Richards equations, either in 1D ( Bouzouidja et al., 2018 Liu and Fassman-Beck, 2017 Peng et al., 2019), 2D ( Li and Babcock, 2015 Palla et al., 2009) or 3D ( Brunetti et al., 2016). Several models have been tested successfully in the literature, which can be categorized into physically based and conceptual models. Hence, numerous studies have investigated different approaches and tools to simulate outflows from green roofs to estimate retention and detention metrics.įor estimating green roof detention, models that simulate rainfall–runoff events in short time steps (sub-hourly) are required.
Both retention and detention metrics are needed to justify the widespread implementation of green roofs by the storm-water community and for planning and design by practicing engineers. Quantifying the hydrological performance of a green roof is usually done by estimating “retention”, a permanent reduction of storm water by evapotranspiration, and “detention”, flow peak reduction and delay. Many studies have confirmed the potential of green roofs to mitigate rainfall events from field measurements ( Fassman-Beck et al., 2013 Johannessen et al., 2018 Liu and Chui, 2019 Stovin, 2010). Roof areas represent around 40 %–50 % of impermeable areas in dense urban catchments ( Dunnett and Kingsbury, 2004) therefore, retrofitting current roofs with substrate/growing media and vegetation offers an efficient and area-free GI option. In contrast to conventional storm-water infrastructure, green roofs attempt to decrease storm-water outflows while providing other services, such as reducing urban heat island effect, preserving the cities ecosystems and improving the urban visual amenity among other benefits ( Berndtsson, 2010). Green roofs are a type of green infrastructure (GI) that have received significant attention in recent years. Follow-up studies are needed to explore the potential of ML models in estimating detention from higher temporal resolution datasets.
However, we recommend the use of the conceptual retention model over the transferred ML models, to estimate the retention of new green roofs, as it gives more accurate volume estimates.
Transferred ML models between cities with similar rainfall events characteristics (Bergen–Sandnes, Trondheim–Oslo) could yield satisfactory modelling performance (Nash–Sutcliffe efficiency NSE >0.5 and percentage bias |PBIAS | <25 %) in most cases. The variations in ML models' performance between the cities was larger than between the different configurations, which was attributed to the different climatic characteristics between the four cities. The ML models yielded satisfactory modelling results (NSE >0.5) in most of the roofs, which indicates an ability to estimate green roof detention.
The ML models yielded low volumetric errors that were comparable with the conceptual retention models, which indicates good performance in estimating annual retention. Furthermore, the transferability of ML models between the different green roofs in the study was tested to investigate the potential of using ML models as a tool for planning and design purposes. The potential of these ML methods for estimating green roof retention was assessed by comparing their simulations with a proven conceptual retention model. Four machine learning methods, artificial neural network (ANN), M5 model tree, long short-term memory (LSTM) and k nearest neighbour (kNN), were applied to simulate storm-water runoff from 16 extensive green roofs located in four Norwegian cities across different climatic zones. The main objective of the study was to examine the potential of using machine learning (ML) to simulate runoff from green roofs to estimate their hydrological performance. Green roofs are increasingly popular measures to permanently reduce or delay storm-water runoff.