RESUMO
As sand moves across Earth's landscapes, the shapes of individual grains evolve, and microscopic textures accumulate on their surfaces. Because transport processes vary between environments, the shape and suite of microtextures etched on sand grains provide insights into their transport histories. For example, previous efforts to link microtextures to transport environments have demonstrated that they can provide important information about the depositional environments of rocks with few other indicators. However, such analyses rely on 1) subjective human description of microtextures, which can yield biased, error-prone results; 2) nonstandard lists of microtextures; and 3) relatively large sample sizes (>20 grains) to obtain reliable results, the manual documentation of which is extremely labor intensive. These drawbacks have hindered broad adoption of the technique. We address these limitations by developing a deep neural network model, SandAI, that classifies scanning electron microscope images of modern sand grains by transport environment with high accuracy. The SandAI model was developed using images of sand grains from modern environments around the globe. Training data encompass the four most common terrestrial environments: fluvial, eolian, glacial, and beach. We validate the model on quartz grains from modern sites unknown to it, and Jurassic-Pliocene sandstones of known depositional environments. Next, the model is applied to two samples of the Cryogenian Bråvika Member (of contested origin), yielding insights into periglacial systems associated with Snowball Earth. Our results demonstrate the robustness and versatility of the model in quickly and automatically constraining the transport histories recorded in individual grains of quartz sand.
RESUMO
Today, relatively warm Circumpolar Deep Water is melting Thwaites Glacier at the base of its ice shelf and at the grounding zone, contributing to significant ice retreat. Accelerating ice loss has been observed since the 1970s; however, it is unclear when this phase of significant melting initiated. We analyzed the marine sedimentary record to reconstruct Thwaites Glacier's history from the early Holocene to present. Marine geophysical surveys were carried out along the floating ice-shelf margin to identify core locations from various geomorphic settings. We use sedimentological data and physical properties to define sedimentary facies at seven core sites. Glaciomarine sediment deposits reveal that the grounded ice in the Amundsen Sea Embayment had already retreated to within ~45 km of the modern grounding zone prior to ca. 9,400 y ago. Sediments deposited within the past 100+ y record abrupt changes in environmental conditions. On seafloor highs, these shifts document ice-shelf thinning initiating at least as early as the 1940s. Sediments recovered from deep basins reflect a transition from ice proximal to slightly more distal conditions, suggesting ongoing grounding-zone retreat since the 1950s. The timing of ice-shelf unpinning from the seafloor for Thwaites Glacier coincides with similar records from neighboring Pine Island Glacier. Our work provides robust new evidence that glacier retreat in the Amundsen Sea was initiated in the mid-twentieth century, likely associated with climate variability.