The primary goal of low impact development (LID) is to capture urban stormwater runoff; however, multiple indirect benefits (environmental and socioeconomic benefits) also exist (e.g., improvements to human health and decreased air pollution). Identifying sites with the highest demand or need for LID ensures the maximization of all benefits. This is a spatial decision-making problem that has not been widely addressed in the literature and was the focus of this research. Previous research has focused on finding feasible sites for installing LID, whilst only considering insufficient criteria which represent the benefits of LID (either neglecting the hydrological and hydraulic benefits or indirect benefits). This research considered the hydrological and hydraulic, environmental, and socioeconomic benefits of LID to identify sites with the highest demand for LID. Specifically, a geospatial framework was proposed that uses publicly available data, hydrological-hydraulic principles, and a simple additive weighting (SAW) method within a hierarchical decision-making model. Three indices were developed to determine the LID demand: (1) hydrological-hydraulic index (HHI), (2) socioeconomic index (SEI), and (3) environmental index (ENI). The HHI was developed based on a heuristic model using hydrological-hydraulic principles and validated against the results of a physical model, the Hydrologic Engineering Center-Hydrologic Modeling System model (HEC-HMS). The other two indices were generated using the SAW hierarchical model and then incorporated into the HHI index to generate the LID demand index (LIDDI). The framework was applied to the City of Toronto, yielding results that are validated against historical flooding records.
Abstract. Data-driven flow forecasting models, such as Artificial Neural Networks (ANNs), are increasingly used for operational flood warning systems. However, flow distributions are highly imbalanced, resulting in poor prediction accuracy on high flows, both in terms of amplitude and timing error. Resampling and ensemble techniques have shown to improve model performance of imbalanced datasets such as streamflow. In this research, we systematically evaluate and compare three resampling: random undersampling (RUS), random oversampling (ROS), and SMOTER; and four ensemble techniques: randomised weights and biases, bagging, adaptive boosting (AdaBoost), least squares boosting (LSBoost); on their ability to improve high flow prediction accuracy using ANNs. The methods are implemented both independently and in combined, hybrid techniques. While some of these combinations have been explored in the broader machine learning literature, this research contains many of the first instances of these algorithms to address the imbalance problem inherent in flood and high flow forecasting models. Specifically, the implementation of ROS, and new approaches for SMOTER, LSBOOST, and SMOTER-AdaBoost are presented in this research. Data from two Canadian watersheds (the Bow River in Alberta, and the Don River in Ontario), representing distinct hydrological systems, are used as the basis for the comparison of the methods. The models are evaluated on overall performance and on high flows. The results of this research indicate that resampling produces marginal improvements to high flow prediction accuracy, whereas ensemble methods produce more substantial improvements, with or without a resampling method. Compared to simple ANN flow forecast models, the use of ensemble methods is recommended to reduce the amplitude and timing error in highly imbalanced flow datasets.
Permeable pavements are a type of low impact development technology that is an alternative to conventional asphalt pavements. These pavements are used to address urban stormwater runoff concerns through infiltration and storage. Overtime, sediments carried by stormwater runoff degrade the performance of these pavements and can eventually diminish the infiltration capacity to the point where no infiltration takes place.Maintenance procedures have been developed for permeable pavements and these procedures are necessary for sufficient long-term hydraulic performance. However, these procedures are expensive and are thus performed infrequently or not at all, leading to many permeable pavement systems that no longer perform at their designed infiltration capacity.The objective of this research is to develop a data-driven model to predict the infiltration rate of permeable pavements. Four permeable concrete lab specimens were constructed and subjected to clogging cycles while obtaining surface images and infiltration data. An artificial neural network was created to investigate the relationship between the images of the pavement surface and its associated surface infiltration rate.Images of the surface were converted to grayscale and parameters of the grayscale image, namely the mean, variance, and skewness, were used as inputs to the model.Modelling results presented in this thesis demonstrate that the use of images of the surface of a pavement were adequate in predicting the surface infiltration rate. Image parameters were seen to have significant trends as test cycles progressed. In general, images of specimens that yielded lower SIRs were whiter (larger grayscale mean), more compact (smaller grayscale variance), and had a larger positive skewness. These models can be used to estimate the surface infiltration rates of permeable concrete pavements, leading to more widespread maintenance and thus, ensure the designed hydraulic performance level is maintained.iii TABLE OF CONTENTS ABSTRACT .
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.