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

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.

Reduction of Gray Water and Run-off in a Residential Environment with Rain Garden Model (Case Study “Settlements in Makassar City”)

Residential neighborhoods produce wastewater originating from soapy water, oil, and similar wastes which are included in the gray water category, as well as rainwater runoff from tiles and those that fall in the house, so the best way to consider is to install a water treatment system. integrated waste. The purpose of this study is to identify a Rain Garden model that is suitable for application in the residential areas of Makassar City. The method used is by identifying the suitability of the Rain Garden land, calculating the dimensions, and making the right Rain Garden model. From the results of the study it was concluded that the Rain Garden model for the reduction of gray water and rainwater runoff in the Makassar City residential environment was designed to have three cropping variations. Time to fill RG with the design of the design of Gray Water discharge reservoir and runoff discharge based on water loss in the residential environment. With a flow rate of V = 0.3 m3 / s, the depth of flow Y = l.2 m. Based on the relationship between the width and depth of flow at the best hydraulic section in rectangular shape, the channel bottom is B = 0.8 m, guard height (F) 30% Y=0.36 m. The effectiveness of household waste treatment and rainwater runoff using this Rain Garden model, for BOD = 102.8 mg / L (inlet) to 8.4 mg / L (outlet). The highest TSS value was 79 mg / L (inlet) to 8.3 mg / L (outlet). The highest detergent value was 59.84 mg / L (inlet) and showed the yield after processing was 1.25 mg / L (outlet). Treatment of gray water and rainwater runoff in residential environments is to reduce the volume of liquid waste that enters the city drainage system and create a sustainable urban sanitation ecology.

Rain garden infiltration rate modeling using gradient boosting machine and deep learning techniques

Rain garden are effective in reducing storm water runoff, whose efficiency depends upon several parameters such as soil type, vegetation and metrological factors. Evaluation of rain gardens has been done by various researchers. However, knowledge for sound design of rain gardens is still very limited, particularly the accurate modeling of infiltration rate and how much it differs from infiltration of natural ground surface. The present study uses experimentally observed infiltration rate of rain gardens with different types of vegetation (grass, candytuft, marigold and daisy with different plant densities) and flow conditions. After that, modeling has been done by the popular infiltration model i.e. Philip's model (which is valid for natural ground surface) and soft computing tools viz. Gradient Boosting Machine (GBM) and Deep Learning (DL). Results suggest a promising performance (in terms of CC, RMSE, MAE, MSE and NSE) by GBM and DL in comparison to the relation proposed by Philip's model (1957). Most of the values predicted by both GBM and DL are within scatter limits of ±5%, whereas the values by Philips model are within the range of ±25% error lines and even outside. GBM performs better than DL as the values of the correlation coefficients and Nash-Sutcliffe model efficiency (NSE) coefficient are the highest and the root mean square error is the lowest. The results of the study will be useful in selection of plant type and their density of the rain garden in the urban area.