In the last two decades, machine learning has found application in a wide range of areas of science and scientific computing. In a number of cases this has led to new developments beyond the simple application of existing machine learning algorithms. More recently, machine learning has found interesting applications in the fields of astronomy, astrophysics and in space engineering, where machine learning for optimal control and trajectory design was applied to solve problems in mission analysis, space traffic management and on board autonomy.

This Topical Collection invites authors to submit high quality original contributions that address the many aspects of the use and development of machine learning in celestial mechanics and dynamical astronomy.

Authors are invited to submit papers on one or more of the following topics:

Coordinate transformation / Discovery of dynamical laws / Motion classification / Modelling of physical properties from data / Uncertainty quantification / Trajectory design / Orbit determination (ground-based and space-based) / Attitude determination

The use of computational methods, for the integrations of the equations of motion or the analysis of regular and chaotic dynamics, has represented a breakthrough in modern Celestial Mechanics, starting from the second half of the past century. Computer-asssisted proofs have also played a very relevant role to analyze, for example, the stability of N-body problems. In recent times, new computational methods entered the scene through machine learning and AI techniques. This Topical Collection aims at collecting the most recent results in the field of computational Dynamical Astronomy.

Based on contributions from the Eighth International Meeting on Celestial Mechanics (CELMEC VIII), Rome, Italy, 5–9 September 2022.