Â鶹ӰԺ

From the classic U-shaped glacial valley to the convex soil-mantled hillslope, geomorphic processes leave clear signatures on the landscapes they create. However, it has been challenging to develop topographic metrics that can be used to extract process parameters. While researchers have gained significant insights into geomorphic processes through metrics like mean local relief, channel steepness, and ridgetop curvature, it is still difficult to make quantitative predictions about processes from quantitative topographic measurements.

Prior work has found that neural networks can be trained to predict geomorphic parameters from synthetic topography with a high degree of accuracy. In this work, we attempt to predict groundwater parameters from a linked geomorphic and groundwater model, and use interpretability techniques to understand what topographic patterns the network is picking up on to make this connection.