Skip to main content
U.S. flag

An official website of the United States government

September 6, 2024

This summer Astrogeology hosted four undergraduate student researchers through the National Science Foundation (NSF) Research Experiences for Undergraduates (REU) program. The REU students were hosted by Northern Arizona University in Flagstaff, Arizona, visiting from universities from all over the U.S. 

The NSF provides funding for host institutions to bring undergraduate students from other institutions to conduct research, share knowledge, network, and complete and present a research project. USGS Astrogeology partners closely with host institution Northern Arizona University to provide relevant, high-impact research projects in a variety of planetary science fields that answer real questions to real problems. This allows REU students to work directly with Federal scientists and technicians on high-impact projects in mutual areas of interest.

This year, Astrogeology had the privilege of working with four REU students, the most Astrogeology has hosted in the NAU REU program’s recent history.  The partnership between NAU and USGS Astrogeology provides access to additional projects and resources that benefit students and broaden collaborations.

We caught up with one student, Liberty Mallison from the University of Florida, to share her reflections on the experience. The title of her project was “Identifying Outliers in Emission Spectroscopy Data with Curiosity Rover’s ChemCam Instrument.”

“This summer, I had the opportunity to work on a research project at the USGS Astrogeology Center through NAU’s NSF-sponsored REU program. I am a rising senior at the University of Florida with a major in Astrophysics and a minor in Geology.”

"One of my goals was to combine the fields of astrophysics and geology through a research project and interning at the USGS has done exactly that."

The challenges of her work were considerable. Liberty rapidly and successfully tackled challenges in software development, getting up to speed on diverse machine learning algorithms, and understanding the physics behind remote sensing platforms onboard the International Space Station and the Mars Science Laboratory Curiosity rover on Mars.

“My project focuses on using machine learning to identify outliers in Mars Curiosity Rover emission spectroscopy datasets, allowing us to quickly identify anomalies, pure minerals, and unique geologic targets. This means that after the rover shoots rocks with the ChemCam laser and collects its spectra, my model identifies whether the geologic target has unexpected spectral signatures. Because the model works quickly and can attribute spectra to potential compositional groups, it enables critical operations decisions to be made on the fly. Some interesting outliers the model picked out from Curiosity Rover’s data include rocks with bright veins, nodules, fracture halos, and even iron meteorites.“

Early in her summer, the models were developed using Earth observation data, and the insight from this work was applied to tackle more challenging datasets. By the end, the project had produced machine learning tools developed and benchmarked on emission spectroscopy datasets collected at the Department of Energy’s Los Alamos National Laboratory and on Mars by Curiosity rover. 

Oblique view of Curiosity rover's traverse, with inset images showing where outliers were identified in ChemCam data

“This type of work is relevant to future Moon, Mars, or other deep space missions, where operational decisions must happen rapidly,” Liberty said. “It is also relevant to the search for critical minerals in a variety of settings.  Throughout the summer, I learned how to improve my coding skills to solve problems, practiced professional communication, and connected my geologic knowledge to the terrain on Mars.”

Lessons learned from Liberty’s work have already influenced the development of machine learning and artificial intelligence solutions in lunar instrument development programs and in nuclear science. "As part of an X-ray Fluorescence instrument development project, I'm looking for novel ways to quickly identify outliers and anomalies on the Moon in real time. This gives our astronauts the best chance of collecting samples most relevant to their mission objectives." said Liberty's mentor, Dr. Travis S.J. Gabriel. He continues, "Our team aims to put machine learning and artificial intelligence solutions into the hands of future Artemis astronauts, and this work is already making an impact on laboratory and off-world robotic nuclear and optical remote sensing platforms. Students in this program have a real opportunity to make an impact at this scale."

"This internship has been the most valuable experience of my undergraduate career, and moving forward, I plan to apply to graduate school programs to pursue a higher degree in Planetary Science or Astrophysics."

Get Our News

These items are in the RSS feed format (Really Simple Syndication) based on categories such as topics, locations, and more. You can install and RSS reader browser extension, software, or use a third-party service to receive immediate news updates depending on the feed that you have added. If you click the feed links below, they may look strange because they are simply XML code. An RSS reader can easily read this code and push out a notification to you when something new is posted to our site.

Was this page helpful?