Surrogate-based multiobjective optimization to rapidly size low impact development practices for outflow capture

The present work aims at quantifying the benefit of Low Impact Development (LID) practices in reducing peak runoff and runoff volume, and at comparing LID practices to conventional stormwater solutions. The hydrologic-hydraulic model used was the Storm Water Management Model (SWMM5.1). The LID practices modeled were: (i) Green roofs; and (ii) Permeable pavements. Each LID was tested independently and compared to two different conventional practices, i.e., sewer enlargement and detention pond design. Results showed that for small storm events LID practices are comparable to conventional measures, in reducing flooding. Overall, smaller storms should be included in the design process.

Low Impact Development (LID) was promoted as an alternative to conventional urban drainage methods. The effects of LID at the site or urban scales have been widely evaluated. This project aims to investigate the impact of LID implementation on basin runoff at a regional scale in a half-urbanized catchment, particularly the overlap of urban and rural sub-flows at peak times. A SUPERFLEX conceptual model framework is adapted as a semi-distributed model to simulate the rainfall-runoff relationship in the catchment for San Antonio, Texas, as a case study. Scenario analyses of both urban development and LID implementation are conducted. Results show that (1) the infill urban development strategy benefits more from runoff control than the sprawl urban development; (2) in non-flood season, permeable pavements, bioretention cells, and vegetated swales decrease peak runoff significantly, and permeable pavements, bioretention cells, and green roofs are good at runoff volume retention; (3) contrary to the general opinion about the peak reduction effect of LID, for a partly urbanized, partly rural basin, the LID implementation delays urban peaks and may cause larger stacking of rural and urban peak runoffs, leading to larger basin peaks under extremely wet conditions.

Urban flooding poses a growing challenge, intensified by rapid urbanization and climate change, which strains traditional drainage systems. This study investigates the application of Low Impact Development (LID) techniques as a sustainable solution to enhance urban drainage system resilience. Using Gurugram, India, as a case study, the research evaluates the functional and structural resilience improvements achieved through LID implementation, alongside a Life Cycle Cost (LCC) analysis to assess cost-effectiveness.LID Performance Index (LPI) was employed to quantify the functional resilience – a  measure of system resilience under varying scenarios of urbanization and increased rainfall intensities. Structural resilience was analyzed by assessing reductions in vulnerable locations through one-at-a-time failure simulations. To effectively integrate the green roofs and rain gardens in the runoff management, the subcatchments with substantial impervious area and high runoff volume were designated as the potential subcatchments for LIDs’ application. The study examines four LID implementation scenarios, incorporating green roofs and rain gardens into 10% (S1), 25% (S2), 50% (S3), and 100% (S4) potential subcatchments.The finding reveals that incorporating LIDs into 10% of potential subcatchments (Scenario S1) enhances functional resilience by 21% and reduces vulnerable nodes by 8.7%. The corresponding Benefit-Cost Ratio (BCR) for Scenario S1 is 2.05 under a 5-year return period design storm, indicating its cost-effectiveness. While increasing LID coverage improves resilience, the cost-effectiveness diminishes due to higher implementation costs.The LCC analysis incorporates construction, maintenance, and salvage costs to evaluate the economic viability of LID practices. It highlights that LIDs are particularly effective for moderate storm events, with a noticeable decrease in effectiveness for extreme storms with higher return periods. The findings underscore the limitations of relying solely on LIDs for stormwater management, advocating for their integration with conventional drainage systems to address extreme scenarios effectively.The insights provided in study are valuable for urban planners, engineers, and policymakers aiming to develop sustainable and resilient urban drainage systems capable of mitigating urban flooding impacts.

Low Impact Development (LID) is an alternative to conventional urban stormwater management practices, which aims at mitigating the impacts of urbanization on water quantity and quality. Plot and local scale studies provide evidence of LID effectiveness; however, little is known about the overall watershed scale influence of LID practices. This is particularly true in watersheds with a land cover that is more diverse than that of urban or suburban classifications alone. We address this watershed-scale gap by assessing the effects of three common LID practices (rain gardens, permeable pavement, and riparian buffers) on the hydrology of a 0.94 km2 mixed land cover watershed. We used a spatially-explicit ecohydrological model, called Visualizing Ecosystems for Land Management Assessments (VELMA), to compare changes in watershed hydrologic responses before and after the implementation of LID practices. For the LID scenarios, we examined different spatial configurations, using 25%, 50%, 75% and 100% implementation extents, to convert sidewalks into rain gardens, and parking lots and driveways into permeable pavement. We further applied 20 m and 40 m riparian buffers along streams that were adjacent to agricultural land cover. The results showed overall increases in shallow subsurface runoff and infiltration, as well as evapotranspiration, and decreases in peak flows and surface runoff across all types and configurations of LID. Among individual LID practices, rain gardens had the greatest influence on each component of the overall watershed water balance. As anticipated, the combination of LID practices at the highest implementation level resulted in the most substantial changes to the overall watershed hydrology. It is notable that all hydrological changes from the LID implementation, ranging from 0.01 to 0.06 km2 across the study watershed, were modest, which suggests a potentially limited efficacy of LID practices in mixed land cover watersheds.

This study aims to investigate the effectiveness of the low impact development (LID) practices on sustainable urban flood storm water management. We applied three LID techniques, i.e. green roof, permeable pavements and bioretention cells, on a highly urbanized watershed in Istanbul, Turkey. The EPA-SWMM was used as a hydrologic-hydraulic model and the model calibration was performed by the well-known Parameter ESTimation (PEST) tool. The rainfall-runoff events occurred between 2012 and 2020. A sensitivity analysis on the parameter selection was applied to reduce the computational cost. The Nash-Sutcliffe efficiency coefficient (NSE) was used as the objective function and it was calculated as 0.809 in the model calibration. The simulations were conducted for six different return periods of a storm event, i.e. 2, 5, 10, 25, 50 and 100 years, in which the synthetic storm event hyetographs were produced by means of the alternating block method. The results revealed that the combination of green roof and permeable pavements have the major impact on both the peak flood reduction and runoff volume reduction compared to the single LIDs. The maximum runoff reduction percentage was obtained as 56.02% for a 10 years return period of a storm event in the combination scenario.

Total organic carbon (TOC) is important geochemical data for evaluating the hydrocarbon generation potential of source rocks. TOC is commonly measured experimentally using cutting and core samples. The coring process and experimentation are always expensive and time-consuming. In this study, we evaluated the use of three machine learning (ML) models and two multiple regression models to predict TOC based on well logs. The well logs involved gamma rays (GR), deep resistivity (RT), density (DEN), acoustic waves (AC), and neutrons (CN). The ML models were developed based on random forest (RF), extreme learning machine (ELM), and back propagation neural network (BPNN). The source rock of Paleocene Yueguifeng Formation in Lishui–Jiaojiang Sag was taken as a case study. The number of TOC measurements used for training and testing were 50 and 27. All well logs and selected well logs (including AC, CN, and DEN) were used as inputs, respectively, for comparison. The performance of each model has been evaluated using different factors, including R2, MAE, MSE, and RMSE. The results suggest that using all well logs as input improved the TOC prediction accuracy, and the error was reduced by more than 30%. The accuracy comparison of ML and multiple regression models indicated the BPNN was the best, followed by RF and then multiple regression. The worst performance was observed in the ELM models. Considering the running time, the BPNN model has higher prediction accuracy but longer running time in small-sample regression prediction. The RF model can run faster while ensuring a certain prediction accuracy. This study confirmed the ability of ML models for estimating TOC using well logs data in the study area.

Stormwater runoff is a major concern in urban areas which is mostly the result of vast urbanization. To reduce urban stormwater runoff and improve water quality, low impact development (LID) is used in urban areas. Therefore, it is vital to find the optimal combination of LID controls to achieve maximum reduction in both stormwater runoff and pollutants with optimal cost. In this study, a simulation-optimization model was developed by linking the EPA Storm Water Management Model (SWMM) to the Multi-Objective Particle Swarm Optimization (MOPSO) using MATLAB. The coupled model could carry out multi-objective optimization (MOO) and find potential solutions to the optimization objectives using the SWMM simulation model outputs. The SWMM model was developed using data from the BUNUS catchment in Kuala Lumpur, Malaysia. The total suspended solids (TSS) and total nitrogen (TN) were selected as pollutants to be used in the simulation model. Vegetated swale and rain garden were selected as LID controls for the study area. The LID controls were assigned to the model using the catchment characteristics. The target objectives were to minimize peak stormwater runoff, TSS, and TN with the minimum number of LID controls applications. The LID combination scenarios were also tested in SWMM to identify the best LID types and combination to achieve maximum reduction in both peak runoff and pollutants. This study found that the peak runoff, TSS, and TN were reduced by 13%, 38%, and 24%, respectively. The optimal number of LID controls that could be used at the BUNUS catchment area was also found to be 25.

Green roof is a low impact development (LID) practice used to mitigate imperviousness in urban areas and to reduce flood risks. In order to have sufficient designs and accurate runoff predictions, computer models should be utilized with full understanding of green roofs' hydrologic processes. Evapotranspiration is usually considered important by researchers in the water balance modeling of a green roof. The Storm Water Management Model (SWMM) version 5.1 is widely utilized rainfall-runoff modeling software which has LID controls capable of modeling green roofs. A previous study has evaluated the performance of this model in green roof simulations for single events without considering evapotranspiration in its application, but attained negative outcomes. Thus, the objective of this study is to determine the significance of considering evapotranspiration in producing accurate runoff simulations specifically using SWMM 5.1. The results of this study have shown that when evapotranspiration was not considered, simulations failed to agree with observed values, whereas when evapotranspiration was considered, simulated runoff volumes attained a very good fit with the observed runoff volumes proving the significance of evapotranspiration as an important parameter in green roof modeling.

High urbanization rate and climate change are the main drivers of urban floods in developing countries. The increase in urban flooding incidents has become a significant threat to cities, which also result into considerable losses of life and the economy. Adapting to the risks of a changing climate and ill-effects of urbanization is imperative for national and local governments. This calls for a functionally and structurally resilient urban drainage infrastructure. Functional resilience is the coping capacity of system against external threats such as urbanization and climate change, whereas structural resilience is the resilience against internal failures such as blockage of inlets or sewers, structural damage of a pipe, bed load sediment deposition, asset aging/decay, and sewer collapse. This work aims to understand the impact of nature-based solutions on urban drainage resilience. Various researchers have identified Low Impact development (LID) practices as a potential solution to enhance drainage systems' resilience. LID can be defined as a land development and retrofit strategy that emphasizes the protection and use of distributed interventions to reduce the volume and rate of stormwater runoff from a developed landscape. In the present study, the green roofs and rain gardens are simulated in a part of Gurugram city of India using the Storm Water Management Model (SWMM) 5.2. Sensitivity analysis is conducted to overcome the problem of a lack of in-depth data to perform model calibration and validation. The simulations were carried out by developing various scenarios for functional and structural resilience assessment. The results indicate that if 25% of potential subcatchments are deployed with LIDs, functional resiliency of the system enhances by 25%, and structural resilience of vulnerable nodes decreases by 17%.  The study reveals that introduction of LIDs aids into enhancing the functional resilience of the system rather than structural resilience. This research provides evidence of LIDs' positive influence on the resilience performance of drainage systems. Overall, the study can help urban planners and drainage management engineers to develop understanding on LIDs role vis-à-vis city's resilience to urban flood problems.

The aim of this work was to develop an accurate model to swiftly forecast the ultimate conditions and the stress–strain curves of ultra-high-performance concrete (UHPC) confined by fibre-reinforced polymer (FRP). Four neural network predictive models based on machine learning (back-propagation neural network (BPNN), support vector regression (SVR), extreme learning machine (ELM) and generalised regression neural network (GRNN)) were constructed to forecast the ultimate conditions. A BPNN-based model to predict stress–strain curves was developed. A database of 193 compression test results of FRP-confined UHPC members was collected from the open literature and a thorough evaluation of data quality was conducted. The results showed that the SVR, BPNN, GRNN and ELM prediction models exhibited excellent accuracy when compared with a design-oriented model. The GRNN exhibited the highest predictive precision, followed by SVR. The developed prediction models establish a foundation for the design and quick prediction of FRP-confined UHPC.

In recent years, plenty of simulation research about the low impact development(LID) control effect has emerged, but studies on scheme comparison and evaluation are lacking. In this study, a comprehensive benefit evaluation system for LID, including environmental, economic, and social benefits, was established on the basis of Analytic Hierarchy Process(AHP) and urban storm water model. Above all, benefit identification, quantitative evaluation and scheme comparison of single LID measures were obtained according to site investigation, simulated calculation and theoretical analysis. Whereafter, LID combination plans were designed based on single LID measures with high comprehensive benefit values, and their comprehensive benefits were evaluated to obtain the optimal plan. Then, based on well-founded system combined with Storm Water Management Model (SWMM), the design and optimization of LID were conducted, with a case in Xi’an, China. It turned out that the preferential order of the LID single measures according to the comprehensive benefit was: bio-retention > rain barrels > low-elevation greenbelt > green roofs > permeable pavement. Five LID combination plans were designed based on bio-retention, rain barrels, low-elevation greenbelt, and green roofs. Evaluation results showed that plan I (bio-retention and green roofs) was the optimal LID combination plan.

Optimization of low impact development layout designs for megacity flood mitigation

Low impact development (LID) methods have been shown to be efficient in reducing the peak flow and total volume of urban stormwater, which is a top priority for effective urban stormwater management in many municipalities. However, decision-makers need information on the effects of LIDs and their associated costs before allocating limited resources. In this study, the Storm Water Management Model (SWMM) was used to investigate the effects of five different LID scenarios on urban flooding in a district in Tehran, Iran. The LID scenarios included rain barrel (RB) at two sizes, bio-retention cell (BRC), and combinations of the two structures. The results showed that significant node flooding and overflow volume would occur in the study area under the existing conditions, especially for rainfall events with longer return periods. BRC and combinations of BRC and RBs were the most effective options in reducing flooding, while the smaller-size RB was the cheapest alternative. However, normalized cost, obtained through dividing the total cost by the percent reduction in node flooding and/or overflow volume, was smallest for BRC. The results of this study demonstrate how hydraulic modeling can be combined with economic analysis to identify the most efficient and affordable LID practices for urban areas.

Improving water quality modelling for green roof runoff using Storm Water Management Model

To quickly and accurately assess tea plant growth, this study aims to find a new way to predict the chlorophyll content in tea plant canopies using machine learning. Using remotely piloted aircraft equipped with multispectral cameras, images of tea plantation areas are captured and reflectance from four spectral bands is extracted, leading to the calculation of vegetation indices. Simultaneously, chlorophyll relative content in the tea plant canopies was collected on the ground using a detector. Four models, namely Random Forest (RF), Backpropagation neural network (BPNN), Radial basis function network (RBFN), and General Regression Neural Network (GRNN), were constructed to predict the chlorophyll relative content in tea plant canopies. Subsequently, important remote sensing variables were identified through RF filtering, followed by a comparison of the predictive performance of machine learning models under different input conditions. Lastly, by integrating the Sparrow Search Algorithm (SSA) to optimize the smoothing factor in the GRNN, the study explores the impact of optimization algorithms on the predictive performance of the GRNN model. Experiments indicate that within the established machine learning models, the GRNN demonstrates the highest predictive accuracy. By ranking the importance of remote sensing variables through RF, 18 significant remote sensing variables were selected, which enhanced the predictive accuracy of the machine learning models. The optimization of the GRNN smoothing factor through the SSA algorithm can significantly enhance the predictive accuracy of the GRNN model. Based on a series of experiments, the established RFSSA-GRNN prediction model demonstrates good predictive performance, with an reaching 0.84.