Research about Oak Ridge, Tennessee

USGS2026

Localization of spatiotemporally heterogeneous subsurface flows using autoencoder-based deep learning framework for time-lapse self-potential tomography

Self-potential (SP) monitoring has emerged as a valuable method for characterizing subsurface hydrogeological features and processes due to its sensitivity to fluid-induced electrokinetic effects. Despite advancements in SP inversion, challenges remain in imaging groundwater dynamics from SP activities due to complex hydrological settings and transient noise. In this study, a deep learning autoencoder (AE)-based framework is proposed for the spatiotemporal localization of subsurface fluid movement from time-lapse SP tomography. Temporal segments of time-lapse numerical inversions were first derived from long-term SP monitoring conducted from a floodplain site in Oak Ridge, Tennessee, known for active hyporheic exchange. Subsequently, AE models based on vision transformer (ViT), convolutional long short-term memory (ConvLSTM), convolutional neural network, and temporal convolutional network were individually trained and compared on the SP tomography segments for reconstruction performance. Finally, the reconstruction error over time serves as an anomaly score to identify moments of active SP variation, whereas spatial distributions of errors within these moments are analyzed to image and localize regions associated with anomalous subsurface fluid movement. The results demonstrate that ConvLSTM- and ViT-AE are most capable for the localization task with contrasting error distributions and consistent delineation of anomalies. Applying the method to both SP arrays parallel and perpendicular to the stream produced consistent anomaly zones near a fault or karst feature, validating the robustness and generalization of the approach. These results demonstrate the potential of the proposed framework as a scalable and interpretable tool for spatiotemporal analysis of subsurface flow dynamics in complex hydrogeological systems.

Tennessee↗

USGS1989

An investigation of shallow ground-water quality near East Fork Poplar Creek, Oak Ridge, Tennessee

Alluvial soils and fill materials in and near the floodplain of East Fork Poplar Creek in Oak Ridge, Tennessee, are contaminated with various trace metals (primarily mercury), organic compounds, and radionuclides that were lost to the stream as a result of past operations at the Y-12 Plant, a nuclear-processing facility located within the U.S. Department of Energy’s Oak Ridge Reservation. Observation wells were installed in the shallow (above bedrock) aquifer in and near the floodplain of East Fork Poplar Creek and water-quality samples were collected to determine if contaminants found in the soils and fill are also present in the shallow ground water. The shallow aquifer in the East Fork Poplar Creek flood plain consists primarily of alluvial silt and clay with lesser amounts of sand and gravel. Thickness of the shallow aquifer ranges from essentially zero to as much as 20 feet. A silty-clay glei horizon is present between the base of the alluvium and the top of bedrock at most flood-plain locations and, where present, likely impedes downward ground-water movement. Water in the shallow aquifer near East Fork Poplar Creek occurs under water-table conditions. Recharge to the shallow aquifer is principally from precipitation, and discharge is through springs and seeps to East Fork Poplar Creek and its tributaries. During spring, summer; and fall, evapotranspiration also accounts for the removal of water in storage in the shallow aquifer. Water levels in the shallow aquifer fluctuate seasonally in response to variations in recharge and evapotranspiration. Generally, the depth to water in the observation wells ranged from about 1 to 4 feet below land surface in late winter, and from about 2 to 7 feet below land surface in late fall. During extremely dry periods, the water table recedes below the top of bedrock in some flood-plain areas, possibly causing East Fork Poplar Creek to lose water to the shallow aquifer along some reaches. Contaminants found in water samples collected from several of the observation wells in concentrations (total and (or) total-recoverable) which equaled or exceeded drinking-water standards established by the U.S. Environmental Protection Agency are antimony, chromium, lead, mercury, selenium, total phenols, and strontium-90. Total and dissolved uranium concentrations exceeded 1.0 microgram per liter in samples from nearly 70 percent of the wells in the East Fork Poplar Creek flood plain. Organic compounds that were identified in low concentrations in samples from a few wells in the flood plain are: Arochlor 1260, benzo(a)anthracene, benzo(b)fluoranthene, chrysene, 3,3-dichlorobenzidine, di-n-butylphthalate, N-nitrosodiphenylamine, and pyrene. Water from one well in the East Fork Poplar Creek flood plain at a contaminated fill site contained 37and 8 micrograms per liter of trichloroethene and trans-1,2-dichloroethene, respectively. Comparison of the results of total and (or) total-recoverable trace-metal determinations with those from dissolved determinations demonstrates that elevated concentrations of these substances in water collected from several of the wells in the East Fork Poplar Creek flood plain resulted from sorption of trace metals (and possibly organic compounds and radionuclides) by fine sediment suspended in the samples. The occurrence of contaminated sediment in these samples is suspected to be the result of borehole contamination during well installation.

Tennessee↗