Stormwater Runoff Treatment Using Rain Garden: Performance Monitoring and Development of Deep Learning-Based Water Quality Prediction Models

Abstract

Twenty-three rainfall events were monitored to determine the characteristics of the stormwater runoff entering a rain garden facility and evaluate its performance in terms of pollutant removal and volume reduction. Data gathered during the five-year monitoring period were utilized to develop a deep learning-based model that can predict the concentrations of Total Suspended Solids (TSS), Chemical Oxygen Demand (COD), Total Nitrogen (TN), and Total Phosphorus (TP). Findings revealed that the rain garden was capable of effectively reducing solids, organics, nutrients, and heavy metals from stormwater runoff during the five-year period when hydrologic and climate conditions have changed. Volume reduction was also high but can decrease over time due to the accumulation of solids in the facility which reduced the infiltration capacity and increased ponding and overflows especially during heavy rainfalls. A preliminary development of a water quality prediction model based on long short-term memory (LSTM) architecture was also developed to be able to potentially reduce the labor and costs associated with on-site monitoring in the future. The LSTM model predicted pollutant concentrations that are close to the actual values with a mean square error of 0.36 during calibration and a less than 10% difference from the measured values during validation. The study showed the potential of using deep learning architecture for the prediction of stormwater quality parameters entering rain gardens. While this study is still in the preliminary stage, it can potentially be improved for use in performance monitoring, decision-making regarding maintenance, and design of similar technologies in the future.

Balancing development and sustainability: Assessing risks and protecting aquatic biodiversity on US college and university campuses

“…Green roofs have the potential to reduce peak runoff rates by 60%–80%, however, they do tend to increase phosphorus within the first few years of implementation (Palla & Gnecco, 2018). In contrast, rain gardens have little stormwater retention capacity, but have been shown to effectively remove suspended solids and nutrients from stormwater runoff (Jeon et al, 2021). Pervious pavements have been shown to greatly reduce both peak runoff and TSS transport.…”

Evaluating the Effectiveness of Bioretention Cells for Urban Stormwater Management: A Systematic Review

“…Adding a certain amount of suitable admixtures to the BRC filter material might provide a solution. However, the admixtures must be affordable, conveniently accessible, beneficial to plant growth, long-lasting, and, most importantly, efficient in removing pollutants [72][73][74][75]. On the whole, several changes may be made to filter media to affect their water-holding, adsorption, and infiltration capacities, and these can all be considered when evaluating BRC hydrologic performance.…”

“…The effectiveness of bioretention in removing heavy metals depends on factors such as the plant species used, the soil's composition and properties, and other environmental conditions (e.g., climate). The water-holding capacity and nutrient availability of the soil have a significant impact on the qualities of plant roots; hence, it is reasonable to assert that plants frequently play a secondary role in heavy metal removal [73,124,125]. However, further study and analysis are required to identify the role of vegetation (including root structure) in the removal of heavy metals in the context of BRCs.…”

Behaviour and Peculiarities of Oil Hydrocarbon Removal from Rain Garden Structures

“…One of the most effective ways to solve this problem is to organise rain gardens of various types and designs. Various scientific studies have shown that the efficiency of removing total phosphorus (TP) by rain gardens is 90% [25], total nitrogen (TN) is 60-97% [26], suspended solids (TSSs) is 53-60% [27], zinc (Zn) is 80-95%, copper (Cu) is 72-95%, lead (Pb) is 95%, cadmium (Cd) is 81-99% [28], mercury is 37%, methylmercury is 49% [29], microplastics is 70-99% [30], pesticides is 99.7% [31], faecal coliform counts is 69% [32], and E. coli is 71-83% [33].…”