Development of an Anisotropic Geological-Based Land Use Regression and Bayesian Maximum Entropy Model for Estimating Groundwater Radon across Northing Carolina

Abstract:

Radon (²²²Rn) is a naturally occurring chemically inert, colorless, and odorless radioactive gas produced from the decay of uranium (²³⁸U), which is ubiquitous in rocks and soils worldwide. Exposure to ²²²Rn is likely the second leading cause of lung cancer after cigarette smoking via inhalation; however, exposure through untreated groundwater is also a contributing factor to both inhalation and ingestion routes. A land use regression (LUR) model for groundwater ²²²Rn with anisotropic geological and ²³⁸U based explanatory variables is developed, which helps elucidate the factors contributing to elevated ²²²Rn across North Carolina. Geological and uranium based variables are constructed in elliptical buffers surrounding each observation such that they capture the lateral geometric anisotropy present in groundwater ²²²Rn. Moreover, geological features are defined at three different geological spatial scales to allow the model to distinguish between large area and small area effects of geology on groundwater ²²²Rn. The LUR is also integrated into the Bayesian Maximum Entropy (BME) geostatistical framework to increase accuracy and produce a point-level LUR-BME model of groundwater ²²²Rn across North Carolina including prediction uncertainty. The LUR-BME model of groundwater ²²²Rn results in a leave-one out cross-validation of 0.46 (Pearson correlation coefficient= 0.68), effectively predicting within the spatial covariance range. Modeled results of ²²²Rn concentrations show variability among Intrusive Felsic geological formations likely due to average bedrock ²³⁸U defined on the basis of overlying stream-sediment ²³⁸U concentrations that is a widely distributed consistently analyzed point-source data.