Search for: All records

Real-time control of stormwater systems can reduce flooding and improve water quality. Current industry real-time control strategies use simple rules based on water quantity parameters at a local scale. However, system-level control methods that also incorporate observations of water quality could provide improved control and performance. Therefore, the objective of this research is to evaluate the impact of local and system-level control approaches on flooding and sediment-related water quality in a stormwater system within the flood-prone coastal city of Norfolk, Virginia, USA. Deep reinforcement learning (RL), an emerging machine learning technique, is used to learn system-level control policies that attempt to balance flood mitigation and treatment of sediment. RL is compared to the conventional stormwater system and two methods of local-scale rule-based control: (i) industry standard predictive rule-based control with a fixed detention time and (ii) rules based on water quality observations. For the studied system, both methods of rule-based control improved water quality compared to the passive system, but increased total system flooding due to uncoordinated releases of stormwater. An RL agent learned controls that maintained target pond levels while reducing total system flooding by 4% compared to the passive system. When pre-trained from the RL agent that learned to reduce flooding, another RL agent was able to learn to decrease TSS export by an average of 52% compared to the passive system and with an average of 5% less flooding than the rule-based control methods. As the complexity of stormwater RTC implementations grows and climate change continues, system-level control approaches such as the RL used here will be needed to help mitigate flooding and protect water quality. 

Climate change poses water resource challenges for many already water stressed watersheds throughout the world. One such watershed is the Upper Neuse Watershed in North Carolina, which serves as a water source for the large and growing Research Triangle Park region. The aim of this study was to quantify possible changes in the watershed’s water balance due to climate change. To do this, we used the Soil and Water Assessment Tool (SWAT) model forced with different climate scenarios for baseline, mid‐century, and end‐century time periods using five different downscaled General Circulation Models. Before running these scenarios, the SWAT model was calibrated and validated using daily streamflow records within the watershed. The study results suggest that, even under a mitigation scenario, precipitation will increase by 7.7% from the baseline to mid‐century time period and by 9.8% between the baseline and end‐century time period. Over the same periods, evapotranspiration (ET) would decrease by 5.5 and 7.6%, water yield would increase by 25.1% and 33.2%, and soil water would increase by 1.4% and 1.9%. Perhaps most importantly, the model results show, under a high emission scenario, large seasonal differences with ET estimated to decrease by up to 42% and water yield to increase by up to 157% in late summer and fall. Planning for the wetter predicted future and corresponding seasonal changes will be critical for mitigating the impacts of climate change on water resources.