AI-powered crater detection algorithm to unlock the secrets of the universe

Researchers from the University of Aberdeen develop an AI algorithm to detect planetary craters with high accuracy, efficiency, and flexibility.
Can Emir
Craters on a planet surface
Craters on a planet surface


A team of scientists from the University of Aberdeen has developed a new algorithm that could revolutionize planetary studies. The new technology enables scientists to detect planetary craters and accurately map their surfaces using different data types, according to a release.

The team used a new universal crater detection algorithm (CDA) developed using the Segment Anything Model (SAM), an artificial intelligence (AI) model that can automatically identify and cut out any object in any image.

The Segment Anything project aims to democratize image segmentation, a core task in computer vision, by introducing a general, promptable segmentation model and a new dataset. SAM is trained on a diverse, high-quality dataset of over 1 billion masks and is flexible enough to cover a broad set of use cases.

The technique could be a "game-changer" in planetary science, reducing the need to manually identify craters, which can be time-consuming. The CDA approach can work with different data and celestial bodies, giving it the potential to be a universal solution for crater detection on various planetary surfaces. This will enable scientists to study craters' distribution, size, and morphology to better understand a planet or moon's geological history, surface processes, and potential habitability.

The technology could also help identify possible landing sites for robotic or human missions, leading to automatic navigation based on terrain observations. Furthermore, the CDA approach could help identify locations where resources, such as water ice, may be concentrated, which can be important for future human missions and resource utilization strategies in space exploration scenarios.

Dr. Iraklis Giannakis, from the University’s School of Geosciences, led the research in collaboration with colleagues from the University. Dr. Giannakis said the new technology had created new possibilities for planetary science and future exploration missions.

“Crater detection is a crucial task in planetary science enabling us to better understand the geology, history, and evolution of celestial bodies such as Mars, the Moon, and other planets," he said.

“Our universal CDA approach leverages the power of SAM to automatically detect craters with high accuracy and efficiency, reducing the need for manual identification. With its advanced segmentation capabilities, SAM has proven to be a game-changer for CDA, allowing us to accurately identify craters of various sizes, shapes, and orientations – even in challenging terrain conditions."

The study’s findings were published in the arXiv preprint server, and the researchers believe their work has created new possibilities for planetary science and exploration missions in the future. The new technique for detecting planetary craters and mapping their surfaces could help us unlock the secrets of the universe and understand more about the geological history and potential habitability of celestial bodies.

Add Interesting Engineering to your Google News feed.
Add Interesting Engineering to your Google News feed.
message circleSHOW COMMENT (1)chevron
Job Board