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 (
- Award ID(s):
- 1936671
- NSF-PAR ID:
- 10320708
- Date Published:
- Journal Name:
- Water
- Volume:
- 14
- Issue:
- 7
- ISSN:
- 2073-4441
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
Abstract 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 withr 2 > 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. -
more » « less
Abstract Coastal groundwater‐dependent ecosystems benefit from lowered salinity, nutrient‐rich submarine groundwater discharge (SGD). Across Pacific islands marine macroalgae appear to have been challenged by and adapted to the stress of lowered salinity with a trade‐off of nutrient subsidies delivered by SGD. Human alterations of groundwater resources and climate change‐driven shifts brought modifications to the magnitude and composition of SGD. This paper discusses how native macroalgae have adapted to SGD nutrient and salinity gradients, but that invasive algae are outcompeting the natives near SGD with nutrient pollution. It is important to re‐evaluate land and water use practices by modifying groundwater sustainable yields and improving wastewater infrastructure to keep SGD reductions minimal and nitrogen inputs in optimal ranges. This task may be particularly challenging amidst global sea level rise and reductions in groundwater recharge, which threaten coastal groundwater systems and ecosystems dependent on them.
-
more » « less
Abstract Precipitation is the primary driver of hydrological models, and its spatial and temporal variability have a great impact on water partitioning. However, in data‐sparse regions, uncertainty in precipitation estimates is high and the sensitivity of water partitioning to this uncertainty is unknown. This is a particular challenge in drylands (semi‐arid and arid regions) where the water balance is highly sensitive to rainfall, yet there is commonly a lack of in situ rain gauge data. To understand the impact of precipitation uncertainty on the water balance in drylands, here we have performed simulations with a process‐based hydrological model developed to characterize the water balance in arid and semi‐arid regions (DRYP: DRYland water Partitioning model). We performed a series of numerical analyses in the Upper Ewaso Ng'iro basin, Kenya driven by three gridded precipitation datasets with different spatio‐temporal resolutions (IMERG, MSWEP, and ERA5), evaluating simulations against streamflow observations and remotely sensed data products of soil moisture, actual evapotranspiration, and total water storage. We found that despite the great differences in the spatial distribution of rainfall across a climatic gradient within the basin, DRYP shows good performance for representing streamflow (KGE >0.6), soil moisture, actual evapotranspiration, and total water storage (
r >0.5). However, the choice of precipitation datasets greatly influences surface (infiltration, runoff, and transmission losses) and subsurface fluxes (groundwater recharge and discharge) across different climatic zones of the Ewaso Ng'iro basin. Within humid areas, evapotranspiration does not show sensitivity to the choice of precipitation dataset, however, in dry lowland areas it becomes more sensitive to precipitation rates as water‐limited conditions develop. The analysis shows that the highest rates of precipitation produce high rates of diffuse recharge in Ewaso uplands and also propagate into runoff, transmission losses and, ultimately focused recharge, with the latter acting as the main mechanism of groundwater recharge in low dry areas. The results from this modelling exercise suggest that care must be taken in selecting forcing precipitation data to drive hydrological modelling efforts, especially in basins that span a climatic gradient. These results also suggest that more effort is required to reduce uncertainty between different precipitation datasets, which will in turn result in more consistent quantification of the water balance. -
null (Ed.)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.more » « less
-
more » « less
Abstract Groundwater discharge transports dissolved constituents to the ocean, affecting coastal carbon budgets and water quality. However, the magnitude and mechanisms of groundwater exchange along rapidly transitioning Arctic coastlines are largely unknown due to limited observations. Here, using first-of-its-kind coastal Arctic groundwater timeseries data, we evaluate the magnitude and drivers of groundwater discharge to Alaska’s Beaufort Sea coast. Darcy flux calculations reveal temporally variable groundwater fluxes, ranging from −6.5 cm d−1(recharge) to 14.1 cm d−1(discharge), with fluctuations in groundwater discharge or aquifer recharge over diurnal and multiday timescales during the open-water season. The average flux during the monitoring period of 4.9 cm d−1is in line with previous estimates, but the maximum discharge exceeds previous estimates by over an order-of-magnitude. While the diurnal fluctuations are small due to the microtidal conditions, multiday variability is large and drives sustained periods of aquifer recharge and groundwater discharge. Results show that wind-driven lagoon water level changes are the dominant mechanism of fluctuations in land–sea hydraulic head gradients and, in turn, groundwater discharge. Given the microtidal conditions, low topographic relief, and limited rainfall along the Beaufort Sea coast, we identify wind as an important forcing mechanism of coastal groundwater discharge and aquifer recharge with implications for nearshore biogeochemistry. This study provides insights into groundwater flux dynamics along this coastline over time and highlights an oft overlooked discharge and circulation mechanism with implications towards refining solute export estimates to coastal Arctic waters.
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3390/w14071068
