Evaluating Terrain-Dependent Performance for Martian Frost Detection in Visible Satellite Observations
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914718976835584 |
|---|---|
| author | Doran, Gary Diniega, Serina Lu, Steven Wronkiewicz, Mark Wagstaff, Kiri L. |
| author_facet | Doran, Gary Diniega, Serina Lu, Steven Wronkiewicz, Mark Wagstaff, Kiri L. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_12080 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Evaluating Terrain-Dependent Performance for Martian Frost Detection in Visible Satellite Observations Doran, Gary Diniega, Serina Lu, Steven Wronkiewicz, Mark Wagstaff, Kiri L. Computer Vision and Pattern Recognition Machine Learning 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. |
| title | Evaluating Terrain-Dependent Performance for Martian Frost Detection in Visible Satellite Observations |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2403.12080 |