Rooftops cover a large percentage of land area in urban areas, which can potentially be used for stormwater purposes. Seeking adaptation strategies, there is an increasing interest in utilising green roofs for stormwater management. However, the impact of extreme rainfall on the hydrological performance of green roofs and their design implications remain challenging to quantify. In this study, a method was developed to assess the detention performance of a detention-based green roof (underlaid with 100 mm of expanded clay) for current and future climate conditions under extreme precipitation using an artificial rainfall generator. The green roof runoff was found to be more sensitive to the initial water content than the hyetograph shape. The green roof outperformed the black roof in terms of all performance indicators (time of concentration, centroid delay, T50 or peak attenuation). While the time of concentration for the reference black roof was within 5 minutes independently of rainfall intensity, for the green roof was extrapolated between 30 and 90 minutes with intensity from 0.8 to 2.5 mm/min. Adding a layer of expanded clay under the green roof substrate provided a significant improvement to the detention performance under extreme precipitation in current and future climate conditions.
Abstract. Green roofs are increasingly popular measures to permanently reduce or delay storm-water runoff. 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. 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 potential of these ML methods for estimating green roof retention was assessed by comparing their simulations with a proven conceptual retention model. 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 ML models yielded low volumetric errors that were comparable with the conceptual retention models, which indicates good performance in estimating annual retention. 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 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. 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. 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. Follow-up studies are needed to explore the potential of ML models in estimating detention from higher temporal resolution datasets.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.