TY - JOUR
T1 - Adaptable Hamiltonian neural networks
AU - Han, Chen Di
AU - Glaz, Bryan
AU - Haile, Mulugeta
AU - Lai, Ying Cheng
N1 - Publisher Copyright: © 2021 authors.
PY - 2021/6
Y1 - 2021/6
N2 - The rapid growth of research in exploiting machine learning to predict chaotic systems has revived a recent interest in Hamiltonian neural networks (HNNs) with physical constraints defined by Hamilton's equations of motion, which represent a major class of physics-enhanced neural networks. We introduce a class of HNNs capable of adaptable prediction of nonlinear physical systems: by training the neural network based on time series from a small number of bifurcation-parameter values of the target Hamiltonian system, the HNN can predict the dynamical states at other parameter values, where the network has not been exposed to any information about the system at these parameter values. The architecture of the HNN differs from the previous ones in that we incorporate an input parameter channel, rendering the HNN parameter-cognizant. We demonstrate, using paradigmatic Hamiltonian systems, that training the HNN using time series from as few as four parameter values bestows the neural machine with the ability to predict the state of the target system in an entire parameter interval. Utilizing the ensemble maximum Lyapunov exponent and the alignment index as indicators, we show that our parameter-cognizant HNN can successfully predict the route of transition to chaos. Physics-enhanced machine learning is a forefront area of research, and our adaptable HNNs provide an approach to understanding machine learning with broad applications.
AB - The rapid growth of research in exploiting machine learning to predict chaotic systems has revived a recent interest in Hamiltonian neural networks (HNNs) with physical constraints defined by Hamilton's equations of motion, which represent a major class of physics-enhanced neural networks. We introduce a class of HNNs capable of adaptable prediction of nonlinear physical systems: by training the neural network based on time series from a small number of bifurcation-parameter values of the target Hamiltonian system, the HNN can predict the dynamical states at other parameter values, where the network has not been exposed to any information about the system at these parameter values. The architecture of the HNN differs from the previous ones in that we incorporate an input parameter channel, rendering the HNN parameter-cognizant. We demonstrate, using paradigmatic Hamiltonian systems, that training the HNN using time series from as few as four parameter values bestows the neural machine with the ability to predict the state of the target system in an entire parameter interval. Utilizing the ensemble maximum Lyapunov exponent and the alignment index as indicators, we show that our parameter-cognizant HNN can successfully predict the route of transition to chaos. Physics-enhanced machine learning is a forefront area of research, and our adaptable HNNs provide an approach to understanding machine learning with broad applications.
UR - http://www.scopus.com/inward/record.url?scp=85112365979&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85112365979&partnerID=8YFLogxK
U2 - 10.1103/PhysRevResearch.3.023156
DO - 10.1103/PhysRevResearch.3.023156
M3 - Article
SN - 2643-1564
VL - 3
JO - Physical Review Research
JF - Physical Review Research
IS - 2
M1 - 023156
ER -