TY - JOUR
T1 - Machine learning prediction of critical transition and system collapse
AU - Kong, Ling Wei
AU - Fan, Hua Wei
AU - Grebogi, Celso
AU - Lai, Ying Cheng
N1 - Publisher Copyright: © 2021 authors. Published by the American Physical Society.
PY - 2021/1/28
Y1 - 2021/1/28
N2 - To predict a critical transition due to parameter drift without relying on a model is an outstanding problem in nonlinear dynamics and applied fields. A closely related problem is to predict whether the system is already in or if the system will be in a transient state preceding its collapse. We develop a model-free, machine-learning-based solution to both problems by exploiting reservoir computing to incorporate a parameter input channel. We demonstrate that, when the machine is trained in the normal functioning regime with a chaotic attractor (i.e., before the critical transition), the transition point can be predicted accurately. Remarkably, for a parameter drift through the critical point, the machine with the input parameter channel is able to predict not only that the system will be in a transient state, but also the distribution of the transient lifetimes and their average before the final collapse, revealing an important physical property of transient chaos.
AB - To predict a critical transition due to parameter drift without relying on a model is an outstanding problem in nonlinear dynamics and applied fields. A closely related problem is to predict whether the system is already in or if the system will be in a transient state preceding its collapse. We develop a model-free, machine-learning-based solution to both problems by exploiting reservoir computing to incorporate a parameter input channel. We demonstrate that, when the machine is trained in the normal functioning regime with a chaotic attractor (i.e., before the critical transition), the transition point can be predicted accurately. Remarkably, for a parameter drift through the critical point, the machine with the input parameter channel is able to predict not only that the system will be in a transient state, but also the distribution of the transient lifetimes and their average before the final collapse, revealing an important physical property of transient chaos.
UR - http://www.scopus.com/inward/record.url?scp=85102664572&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85102664572&partnerID=8YFLogxK
U2 - 10.1103/PhysRevResearch.3.013090
DO - 10.1103/PhysRevResearch.3.013090
M3 - Article
SN - 2643-1564
VL - 3
JO - Physical Review Research
JF - Physical Review Research
IS - 1
M1 - 013090
ER -