Predicting the performance of green stormwater infrastructure using multivariate long short-term memory (LSTM) neural network

Mehedi, Md Abdullah Al; Amur, Achira; Metcalf, Jessica L.; McGauley, Matthew; Smith, Virginia; Wadzuk, Bridget

doi:10.1016/j.jhydrol.2023.130076

Cited by 6 publications

(2 citation statements)

References 107 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Addressing urban rain-flood and waterlogging predicaments, scholars both domestically and internationally have historically relied on a variety of hydrological coupling models in their research [11]. These studies involve simulations and control analyses of the rain-flood storage capabilities of infrastructures at different scales: small-scale lowimpact development facilities [12,13], medium-scale municipal infrastructure [14][15][16], and large-scale river wetlands [17][18][19]. These investigations also take into account the impact of environmental factors that contribute to rain-flood disaster risks [20].…”

Section: Introductionmentioning

confidence: 99%

Simulation Study on Rain-Flood Regulation in Urban “Gray-Green-Blue” Spaces Based on System Dynamics: A Case Study of the Guitang River Basin in Changsha

Jiang,

Xiong,

Yang

et al. 2023

Water

View full text Add to dashboard Cite

Urban rainstorms and flood disasters are the most common and severe environmental problems worldwide. Many factors influence rain-flood control simulation, forming a complex network system of interconnected and mutually constraining elements. In terms of spatial scale selection, existing research on rain-flood disaster risk largely relies on a single-scale infrastructure index system and has not yet focused on urban “gray-green-blue” spatial scale simulations for rain-flood storage. Regarding research methodology, applying system dynamics methods to the simulation of rain-flood storage and disaster prevention planning in watershed cities is still in its initial stages. System dynamics models can simulate the feedback interactions among various sub-elements in the coupled mega-system, fully addressing complex issues within the system structure that involve multiple variables, non-linear relationships, and numerous feedback loops, thereby compensating for the inadequacies of traditional linear models in the collaborative management of rain-flood risks. Taking the Changsha Guitang River Basin as an example, this paper constructs a system dynamics model covering four dimensions: natural environment, socio-economics, internal structure, and policy development. It aims to derive the optimal planning scheme for gray-green-blue spatial coordination in rain-flood storage by weighing four different development scenarios. The simulation results show: (1) Simply changing the surface substrates without considering rainwater discharge and the plan that emphasizes the construction of municipal drainage facilities will see the capacity gap for rain-flood storage-space construction continue to widen by 2035. This indicates that the plans mentioned above will struggle to bear the socio-economic losses cities face during rain-flood disasters. (2) The plan of combining gray and green infrastructures sees the rain-flood storage construction capacity turn from negative to positive from 2024, rising to 52.259 billion yuan by 2035. This reflects that the plan can significantly reduce the rainwater volume in the later stages of low-impact development infrastructure construction, mitigate rain-flood disaster risks, and reduce government investment in rain-flood disaster risk management, making it a relatively excellent long-term rain-flood storage space planning option. (3) The rain-flood regulation space planning scheme, under the combined effect of the urban “gray-green-blue” network system, sees the capacity for rain-flood storage construction turn positive a year earlier than the previous plan, reaching 54.232 billion yuan by 2035. This indicates that the scheme can not only effectively respond to extreme flood and rainstorm disasters but also maintain ecological environment benefits and mitigate the socio-economic losses caused by disasters, making it the optimal choice for future government disaster management planning. The research results provide a theoretical framework and practical insights for territorial spatial planning, rain-flood control management, and resilient city construction in watershed areas.

show abstract

Section: Introductionmentioning

confidence: 99%

Simulation Study on Rain-Flood Regulation in Urban “Gray-Green-Blue” Spaces Based on System Dynamics: A Case Study of the Guitang River Basin in Changsha

Jiang,

Xiong,

Yang

et al. 2023

Water

View full text Add to dashboard Cite

show abstract

“…The engineered soil layer underneath the bowl is 120 cm-deep and comprised of a mixture of sand and in situ soil (United States Department of Agriculture-classified "silt") in a 1:1 ratio. Typical recession rates at the rain garden have been observed between 0.5 and 2.5 cm/hr post-rainfall (Amur et al, 2022;Mehedi et al, 2023). Soil moisture recovery of the rain garden's engineered soil layer has been estimated on the order of 1-2 days (Shakya et al, 2023).…”

mentioning

confidence: 99%

A Complete Water Balance of a Rain Garden

McGauley,

Amur,

Shakya

et al. 2023

Water Resources Research

Self Cite

View full text Add to dashboard Cite

A bioinfiltration rain garden was retrofitted from an existing traffic island at Villanova University in 2001. It has been monitored continuously since 2003 at a 5‐min timeseries resolution and with instrumentation that would enable a water balance calculation. This 20‐year data set allows for an in‐depth analysis of the hydrologic pathways and management in the rain garden. Using physical equations and modeled data (based on real‐time measurements), a balance of all influent, stored, and effluent water within the rain garden was constructed. Analysis shows the rain garden captures 73.5% of runoff, resulting in a post‐implementation management of 86.2% of all rainfall in its watershed. In comparison to the hydrology of other land covers, implementing the rain garden resulted in the management of 37.6% more rainfall than pre‐implementation, producing a hydrological signature similar to that of cultivated land or low development levels (e.g., 30% impervious). Additionally, with the long data record, several statistical techniques were applied to determine the amount of monitoring needed for a certain level of precision in system performance assessment. For 5% uncertainty, approximately 3 years of continuous data is needed to assess performance. This analysis not only facilitates understanding the function of rain garden systems, but also provides conclusions and methodology for understanding the uncertainty associated with the extent of monitoring performed on these green stormwater infrastructure systems. These findings provide practical knowledge as monitoring of stormwater management infrastructures is becoming a more standard part of their operation.

show abstract

Deep dependence in hydroclimatological variables

Lee,

Kim

2024

Appl Intell

View full text Add to dashboard Cite

Predicting the performance of green stormwater infrastructure using multivariate long short-term memory (LSTM) neural network

Cited by 6 publications

References 107 publications

Simulation Study on Rain-Flood Regulation in Urban “Gray-Green-Blue” Spaces Based on System Dynamics: A Case Study of the Guitang River Basin in Changsha

Simulation Study on Rain-Flood Regulation in Urban “Gray-Green-Blue” Spaces Based on System Dynamics: A Case Study of the Guitang River Basin in Changsha

A Complete Water Balance of a Rain Garden

Deep dependence in hydroclimatological variables

Contact Info

Product

Resources

About