Exploring the potential of neural networks in early detection of potentially hazardous near-earth objects

Abstract We propose a novel method to estimate the minimum orbit intersection distance (MOID) of a near-earth object (NEO) based on artificial neural networks (NNs). The MOID is defined as the minimum distance between the two osculating Keplerian orbits of the Earth and the NEO as curves in the three-dimensional space; it is usually used as an indicator of the possibility of a collision between the asteroid and the Earth, at least for the period during which the Keplerian orbit of the asteroid provides a reliable approximation of the actual orbit. In the present work, the MOID is estimated with a multilayer feedforward NN that takes as input the coordinates of the asteroid at a specified epoch. The NN has been trained on an artificial dataset of about 800000 NEOs, generated with NEOPOP, and tested on the population of real near-earth asteroids (NEAs). The network exhibits near-instantaneous predictions of the MOID and achieves a mean absolute error of approximately $$ 10^{-3} $$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msup> <mml:mn>10</mml:mn> <mml:mrow> <mml:mo>-</mml:mo> <mml:mn>3</mml:mn> </mml:mrow> </mml:msup> </mml:math> AU on the test set. This research represents a step forward in addressing the urgent need for effective impact monitoring techniques, partially answering the question of whether machine learning can serve as a preliminary filter for some problems of orbit determination.