Ground-based Detection of Martian Dust Devils With a Fine-tuned Fast R-CNN

Overview

Development stage

In development or acquisitionSource: a) Pre-deployment – The use case is in a development or acquisition status.

High-impact designation

Not high-impactSource: c) Not high-impact

Impact justification

Not reported

Start date

Not reported

Withheld from public reporting

NoSource: a) No

Mission

Topic area

Science

Operational functions

Image and video analysis Derived by keyword rules; see methodology

Problem the AI is intended to solve

We developed a two-stage pipeline for efficient dust devil detection in Mars rover imagery. Our approach combines preprocessing filters to remove unsuitable images, followed by a Faster R-CNN with ResNet-50 backbone and Feature Pyramid Network, effectively detecting nonrigid, low-opacity dust devils that traditional methods frequently miss. We demonstrated clear advantages over generic object detection models.

Expected benefits

Our fine-tuned model significantly outperforms general-purpose architectures, highlighting the critical importance of domain-specific training for specialized atmospheric phenomena detection across multiple rover platforms and mission phases. This work has established a foundation for onboard implementation in future Mars missions. Our model could enable intelligent data prioritization, allowing rovers to retain high-resolution imagery of dust devil activity while applying aggressive compression to less scientifically valuable frames, optimizing limited bandwidth resources.

System outputs

Detecting nonrigid, low-opacity dust devils

Technology

AI classification

Computer visionSource: Computer Vision: AI that processes and interprets visual data (e.g., images and videos).

System name(s)

Not reported

Custom-developed code

Not reported

Public source code

Not reported

Sourcing

How it was built

Not reported

Vendor (as reported)

Not reported

Vendors (standardized)

None on the standard list

A vendor is the supplier named by the agency. It does not identify the underlying model or AI technology.

Data and privacy

Involves PII

Not reported

Privacy Impact Assessment

Not reported

Authorization to Operate

Not reported

Demographic features

Not reported

Training and evaluation data

Not reported

Federal Data Catalog

Not reported

Governance

0 of 8 minimum-practice questions answered. A blank answer means the agency reported nothing; it does not mean the practice is absent.

Potential impacts and how they were identified

Not reported