Astronomy16 papers
Artificial Intelligence and Machine Learning in Planetary Science
A companion collection for the ACM 2026 talk by Valerio Carruba
VC
Valerio Carruba
All Reviews
AstronomyWorth Reading
intermediate
Vision Transformers for identifying asteroids interacting with secular resonances
Carruba, V. et al. (2025)
- Published
- Jan 1, 2025
- Journal
- Icarus · Vol. 425
- DOI
- 10.1016/j.icarus.2024.116346
At a GlanceAI
Vision transformers help identify asteroids affected by secular resonances, offering a new AI tool for Solar System dynamics.
SummaryAI
The paper applies vision transformers to the problem of identifying asteroids that interact with secular resonances, an important process shaping asteroid orbits over time. Its novelty lies in bringing a modern image-based deep learning approach to a celestial mechanics task that is traditionally handled with dynamical analysis. If effective, this could provide a faster or more scalable way to classify resonant asteroid populations and improve studies of asteroid-belt evolution.
Method SnapshotAI
The study uses a vision transformer deep learning approach to identify asteroids interacting with secular resonances.
BackgroundAI
Basic background in asteroid dynamics, secular resonances, and machine learning for scientific data analysis is helpful.
An important methodological contribution, this paper was among the first to apply vision transformers to the identification of secular resonances in asteroid dynamics. It illustrates the potential of modern deep-learning architectures to complement traditional dynamical analyses and represents a significant step toward AI-driven classification of resonant populations.
— VC