AI can identify Solar System instability billions of years in advance

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Abbot, Dorian S., Laurence-Chasen, J. D., Webber, Robert J., Hernandez, David M., Weare, Jonathan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914648000823296
author Abbot, Dorian S.
Laurence-Chasen, J. D.
Webber, Robert J.
Hernandez, David M.
Weare, Jonathan
author_facet Abbot, Dorian S.
Laurence-Chasen, J. D.
Webber, Robert J.
Hernandez, David M.
Weare, Jonathan
contents Rare event schemes require an approximation of the probability of the rare event as a function of system state. Finding an appropriate reaction coordinate is typically the most challenging aspect of applying a rare event scheme. Here we develop an artificial intelligence (AI) based reaction coordinate that effectively predicts which of a limited number of simulations of the Solar System will go unstable using a convolutional neural network classifier. The performance of the algorithm does not degrade significantly even 3.5 billion years before the instability. We overcome the class imbalance intrinsic to rare event problems using a combination of minority class oversampling, increased minority class weighting, and pulling multiple non-overlapping training sequences from simulations. Our success suggests that AI may provide a promising avenue for developing reaction coordinates without detailed theoretical knowledge of the system.
format Preprint
id arxiv_https___arxiv_org_abs_2401_12180
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AI can identify Solar System instability billions of years in advance
Abbot, Dorian S.
Laurence-Chasen, J. D.
Webber, Robert J.
Hernandez, David M.
Weare, Jonathan
Earth and Planetary Astrophysics
Rare event schemes require an approximation of the probability of the rare event as a function of system state. Finding an appropriate reaction coordinate is typically the most challenging aspect of applying a rare event scheme. Here we develop an artificial intelligence (AI) based reaction coordinate that effectively predicts which of a limited number of simulations of the Solar System will go unstable using a convolutional neural network classifier. The performance of the algorithm does not degrade significantly even 3.5 billion years before the instability. We overcome the class imbalance intrinsic to rare event problems using a combination of minority class oversampling, increased minority class weighting, and pulling multiple non-overlapping training sequences from simulations. Our success suggests that AI may provide a promising avenue for developing reaction coordinates without detailed theoretical knowledge of the system.
title AI can identify Solar System instability billions of years in advance
topic Earth and Planetary Astrophysics
url https://arxiv.org/abs/2401.12180