Using Deep Learning to Model the Groundwater Tracer Radon in Coastal Waters
Open Access
- 14 March 2023
- journal article
- research article
- Published by American Geophysical Union (AGU) in Water Resources Research
- Vol. 59 (3)
Abstract
Submarine groundwater discharge (SGD) is an important driver of coastal biogeochemical budgets worldwide. Radon ( 222 Rn) 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 with r 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.Keywords
Funding Information
- HORIZON EUROPE Marie Sklodowska-Curie Actions (101026629)
- Established Program to Stimulate Competitive Research (1557349)
- Established Program to Stimulate Competitive Research (1632825)
This publication has 49 references indexed in Scilit:
- Spatial Distribution of Submarine Groundwater Discharge and Associated Nutrients within a Local Coastal AreaEnvironmental Science & Technology, 2012
- Coupled radon, methane and nitrate sensors for large-scale assessment of groundwater discharge and non-point source pollution to coastal watersJournal of Environmental Radioactivity, 2010
- The Effect of Submarine Groundwater Discharge on the OceanAnnual Review of Marine Science, 2010
- Quantification of point‐source groundwater discharges to the ocean from the shoreline of the Big Island, HawaiiLimnology and Oceanography, 2009
- Land or ocean?: Assessing the driving forces of submarine groundwater discharge at a coastal site in the Gulf of MexicoJournal of Geophysical Research: Oceans, 2009
- Combined time‐series resistivity and geochemical tracer techniques to examine submarine groundwater discharge at Dor Beach, IsraelGeophysical Research Letters, 2006
- Estimating the dynamics of groundwater input into the coastal zone via continuous radon-222 measurementsJournal of Environmental Radioactivity, 2003
- Self‐organizing linear output map (SOLO): An artificial neural network suitable for hydrologic modeling and analysisWater Resources Research, 2002
- Improving model selection by nonconvergent methodsNeural Networks, 1993
- A comparison of the Two One-Sided Tests Procedure and the Power Approach for assessing the equivalence of average bioavailabilityJournal of Pharmacokinetics and Biopharmaceutics, 1987