Evaluating Terrain-Dependent Performance for Martian Frost Detection in Visible Satellite Observations
This work addresses the challenge of global frost detection for Martian climate and geology research, but it is incremental as it builds on existing methods with specific improvements.
The study tackled the problem of automating frost detection on Mars using visible satellite observations by addressing biases due to geologic context, resulting in a novel data partitioning approach and proposed mitigations to improve model performance.
Seasonal frosting and defrosting on the surface of Mars is hypothesized to drive both climate processes and the formation and evolution of geomorphological features such as gullies. Past studies have focused on manually analyzing the behavior of the frost cycle in the northern mid-latitude region of Mars using high-resolution visible observations from orbit. Extending these studies globally requires automating the detection of frost using data science techniques such as convolutional neural networks. However, visible indications of frost presence can vary significantly depending on the geologic context on which the frost is superimposed. In this study, we (1) present a novel approach for spatially partitioning data to reduce biases in model performance estimation, (2) illustrate how geologic context affects automated frost detection, and (3) propose mitigations to observed biases in automated frost detection.