Saved in:
Bibliographic Details
Main Authors: Hillier, Adeline, Sleeman, Jennifer, Brett, Jay, Tang, Caroline, Millison, Jenelle, Gnanadesikan, Anand
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.20580
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911700162183168
author Hillier, Adeline
Sleeman, Jennifer
Brett, Jay
Tang, Caroline
Millison, Jenelle
Gnanadesikan, Anand
author_facet Hillier, Adeline
Sleeman, Jennifer
Brett, Jay
Tang, Caroline
Millison, Jenelle
Gnanadesikan, Anand
contents This work explores a dynamics-informed Temporal Fusion Transformer (TFT) as a data-driven surrogate for computationally intensive Earth system simulations. Focusing on multivariate time series describing global ocean transport, we demonstrate the surrogate's ability to forecast tip events across thousands of time steps. The data involve up to 21 non-stationary time series in addition to static covariates describing free parameters and initial conditions. Modifications to the architecture and objective function yield a surrogate that anticipates the timing of Atlantic and Pacific collapses to high fidelity and captures the stochastic uncertainty in transition timing across ensemble predictions. The learned surrogate achieves a 465x computational speedup over the numerical simulator while maintaining differentiability with respect to parameters and initial conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2605_20580
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Deep Learning Surrogates for Emulating Stochastic Climate Tipping Dynamics
Hillier, Adeline
Sleeman, Jennifer
Brett, Jay
Tang, Caroline
Millison, Jenelle
Gnanadesikan, Anand
Machine Learning
This work explores a dynamics-informed Temporal Fusion Transformer (TFT) as a data-driven surrogate for computationally intensive Earth system simulations. Focusing on multivariate time series describing global ocean transport, we demonstrate the surrogate's ability to forecast tip events across thousands of time steps. The data involve up to 21 non-stationary time series in addition to static covariates describing free parameters and initial conditions. Modifications to the architecture and objective function yield a surrogate that anticipates the timing of Atlantic and Pacific collapses to high fidelity and captures the stochastic uncertainty in transition timing across ensemble predictions. The learned surrogate achieves a 465x computational speedup over the numerical simulator while maintaining differentiability with respect to parameters and initial conditions.
title Deep Learning Surrogates for Emulating Stochastic Climate Tipping Dynamics
topic Machine Learning
url https://arxiv.org/abs/2605.20580