Search for: All records

Quantifying and characterizing groundwater flow and discharge from barrier islands to coastal waters is crucial for assessing freshwater resources and contaminant transport to the ocean. In this study, we examined the groundwater hydrological response, discharge, and associated nutrient fluxes in Dauphin Island, a barrier island located in the northeastern Gulf of Mexico. We employed radon ( 222 Rn) and radium (Ra) isotopes as tracers to evaluate the temporal and spatial variability of fresh and recirculated submarine groundwater discharge (SGD) in the nearshore waters. The results from a 40-day continuous 222 Rn time series conducted during a rainy season suggest that the coastal area surrounding Dauphin Island was river-dominated in the days after storm events. Groundwater response was detected about 1 week after the precipitation and peak river discharge. During the period when SGD was a factor in the nutrient budget of the coastal area, the total SGD rates were as high as 1.36 m day –1 , or almost three times higher than detected fluxes during the river-dominated period. We found from a three-endmember Ra mixing model that most of the SGD from the barrier island was composed of fresh groundwater. SGD was driven by marine and terrestrial forces, and focused on the southeastern part of the island. We observed spatial variability of nutrients in the subterranean estuary across this part of the island. Reduced nitrogen (i.e., NH 4 + and dissolved organic nitrogen) fluxes dominated the eastern shore with average rates of 4.88 and 5.20 mmol m –2 day –1 , respectively. In contrast, NO 3 – was prevalent along the south-central shore, which has significant tourism developments. The contrasting nutrient dynamics resulted in N- and P-limited coastal water in the different parts of the island. This study emphasizes the importance of understanding groundwater flow and dynamics in barrier islands, particularly those urbanized, prone to storm events, or located near large estuaries. 

Submarine groundwater discharge (SGD) is an important driver of coastal biogeochemical budgets worldwide. Radon (²²²Rn) has been widely used as a natural geochemical tracer to quantify SGD, but field measurements are time consuming and costly. Here, we use deep learning to predict coastal seawater radon in SGD‐impacted regions. We hypothesize that deep learning could resolve radon trends and enable preliminary insights with limited field observations of groundwater tracers. Two deep learning models were trained on global coastal seawater radon observations (n = 39,238) with widely available inputs (e.g., salinity, temperature, water depth). The first model used a one‐dimensional convolutional neural network (1D‐CNN‐RNN) framework for site‐specific gap filling and producing short‐term future predictions. A second model applied a fully connected neural network (FCNN) framework to predict radon across geographically and hydrologically diverse settings. Both models can predict observed radon concentrations withr² > 0.76. Specifically, the FCNN model offers a compelling development because synthetic radon tracer data sets can be obtained using only basic water quality and meteorological parameters. This opens opportunities to attain radon data from regions with large data gaps, such as the Global South and other remote locations, allowing for insights that can be used to predict SGD and plan field experiments. Overall, we demonstrate how field‐based measurements combined with big‐data approaches such as deep learning can be utilized to assess radon and potentially SGD beyond local scales.