Many coastal cities are facing frequent flooding from storm events that are made worse by sea level rise and climate change. The groundwater table level in these low relief coastal cities is an important, but often overlooked, factor in the recurrent flooding these locations face. Infiltration of stormwater and water intrusion due to tidal forcing can cause already shallow groundwater tables to quickly rise toward the land surface. This decreases available storage which increases runoff, stormwater system loads, and flooding. Groundwater table forecasts, which could help inform the modeling and management of coastal flooding, are generally unavailable. This study explores two machine learning models, Long Short-term Memory (LSTM) networks and Recurrent Neural Networks (RNN), to model and forecast groundwater table response to storm events in the flood prone coastal city of Norfolk, Virginia. To determine the effect of training data type on model accuracy, two types of datasets (i) the continuous time series and (ii) a dataset of only storm events, created from observed groundwater table, rainfall, and sea level data from 2010–2018 are used to train and test the models. Additionally, a real-time groundwater table forecasting scenario was carried out to compare the models’ abilities to predict groundwater table levels given forecast rainfall and sea level as input data. When modeling the groundwater table with observed data, LSTM networks were found to have more predictive skill than RNNs (root mean squared error (RMSE) of 0.09 m versus 0.14 m, respectively). The real-time forecast scenario showed that models trained only on storm event data outperformed models trained on the continuous time series data (RMSE of 0.07 m versus 0.66 m, respectively) and that LSTM outperformed RNN models. Because models trained with the continuous time series data had much higher RMSE values, they were not suitable for predicting the groundwater table in the real-time scenario when using forecast input data. These results demonstrate the first use of LSTM networks to create hourly forecasts of groundwater table in a coastal city and show they are well suited for creating operational forecasts in real-time. As groundwater table levels increase due to sea level rise, forecasts of groundwater table will become an increasingly valuable part of coastal flood modeling and management.

Flooding in many areas is becoming more prevalent due to factors such as urbanization and climate change, requiring modernization of stormwater infrastructure. Retrofitting standard passive systems with controllable valves/pumps is promising, but requires real-time control (RTC). One method of automating RTC is reinforcement learning (RL), a general technique for sequential optimization and control in uncertain environments. The notion is that an RL algorithm can use inputs of real-time flood data and rainfall forecasts to learn a policy for controlling the stormwater infrastructure to minimize measures of flooding. In real-world conditions, rainfall forecasts and other state information are subject to noise and uncertainty. To account for these characteristics of the problem data, we implemented Deep Deterministic Policy Gradient (DDPG), an RL algorithm that is distinguished by its capability to handle noise in the input data. DDPG implementations were trained and tested against a passive flood control policy. Three primary cases were studied: (i) perfect data, (ii) imperfect rainfall forecasts, and (iii) imperfect water level and forecast data. Rainfall episodes (100) that caused flooding in the passive system were selected from 10 years of observations in Norfolk, Virginia, USA; 85 randomly selected episodes were used for training and the remaining 15 unseen episodes served as test cases. Compared to the passive system, all RL implementations reduced flooding volume by 70.5% on average, and performed within a range of 5%. This suggests that DDPG is robust to noisy input data, which is essential knowledge to advance the real-world applicability of RL for stormwater RTC.

Reinforcement learning agents can learn real-time stormwater system control strategies that balance the competing goals of flood mitigation and sediment capture in urban watersheds.

Coastal cities face recurrent flooding from storm events and rising seas. A contributing factor to flooding in these low relief areas is the groundwater table, which, already relatively shallow, can quickly rise towards the land surface during storm events. This leads to increased surface runoff entering stormwater drainage systems and a greater probability of flooding. As such, groundwater table forecasts could be an important component of real-time flood forecasting systems, but are generally unavailable. Because traditional physics-based models require extensive amounts of subsurface data that is difficult to obtain, especially in urban environments, this research evaluates two types of machine learning models, Recurrent Neural Networks (RNN) and Long Short-term Memory neural networks (LSTM), for creating groundwater table forecasts. The two types of networks were built with Tensorflow/Keras to forecast the groundwater table response to forecasted storm events and appropriate hyperparameters were tuned using the Hyperas library. Using observed hourly groundwater levels, rainfall, and tide from the City of Norfolk, Virginia, the networks were trained with data from 2010-2016 and tested with data from 2016-2018. Archived forecast rainfall and tide from two large storms in the test period (Hurricane Hermine and Tropical Storm Julia) were then used to evaluate the effect of forecast inputs on model performance. Results indicate that LSTM is slightly more accurate when forecasting the groundwater table than RNN, likely because of its increased ability to preserve and learn from past information. Average root mean squared error and Nash-Sutcliffe efficiency values for an 18hr forecast for the LSTM were 0.06m and 0.89, respectively, and 0.07m and 0.85, respectively, for the RNN. These forecasts could provide valuable information to aid in planning and response to storm events and will become an increasingly important part of effectively modeling and predicting coastal urban flooding as sea level rises.

Estimating Potential Climate Change Effects on the Upper Neuse Watershed Water Balance Using the SWAT Model