A probabilistic assessment of surface water-groundwater exchange flux at a PCE contaminated site using groundwater modelling

Polluted groundwater discharge at a chlorinated solvent contaminated site in Hagfors, Sweden, is affecting a nearby stream flowing through a sparsely populated area. Because of difficulties related to source zone remediation, decision makers recently changed the short-term site management objective to mitigating discharge of polluted groundwater to the stream. To help formulating targeted remediation strategies pertaining to the new objective, we developed a groundwater numerical decision-support model. To facilitate reproducibility, the modelling workflow was scripted. The model was designed to quantify and reduce the uncertainty of surface water-groundwater (SW-GW) exchange fluxes for the studied period (2016-2020) through the use of history-matching. In addition to classical observations, thermal anomalies detected in fiber optic distributed temperature sensing (FO-DTS) measurements were used to inform the model of groundwater discharge. After assessing SW-GW exchange fluxes, we used measurements of surface water chemistry to provide a probabilistic estimation of mass influx and spatio-temporal distributions of contaminated groundwater discharge. Results show 1) SW-GW exchange fluxes are likely to be significantly larger than previously estimated, and 2) prior estimations of mass influx are located near the center of the posterior probability distribution. Based on this, we recommend decision makers to focus remediation action on specific segments of the stream.