Evaluating Terrain-Dependent Performance for Martian Frost Detection in Visible Satellite Observations

Seasonal frosting and defrosting on the surface of Mars is hypothe- sized to drive both climate processes and the formation and evolu- tion 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 indica- tions 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 future work to further mitigate observed biases in automated frost detection work.

火星表面的季节性结霜与融霜现象，被假说认为可同时驱动气候过程，以及冲沟等地貌特征的形成与演化。过往研究多依托轨道高分辨率可见光观测数据，手动分析火星北部中纬度区域的霜循环特征。若要将此类研究推广至全球尺度，则需借助卷积神经网络（convolutional neural networks）等数据科学技术实现霜冻的自动化检测。然而，霜冻存在的可见光表征会因霜冻附着的地质背景差异而产生显著变化。本研究中，我们（1）提出一种全新的数据空间划分方法，以降低模型性能评估中的偏差；（2）阐明地质背景对自动化霜冻检测的影响；（3）提出未来可进一步缓解自动化霜冻检测中观测到的偏差的研究方向。