Data-Driven Modeling and Prediction of Complex Spatio-Temporal Dynamics in Excitable Media

Frontiers in Applied Mathematics and Statistics

Herzog, Sebastian¹  tter, Florentin²  Wö²  rgö³  Parlitz, Ulrich³ 

[1] Max Planck Institute for Dynamics and Self-Organization, Germany;Third Institute of Physics and Bernstein Center for Computational Neuroscience, University of Göttingen, Germany

关键词: deep learning;    Conditional random fields;    excitable media;    spatio-temporal chaos;    Cardiac dynamics;    Nonlinear observer;   

DOI  :  10.3389/fams.2018.00060

学科分类：数学（综合）

来源: Frontiers

【 摘 要 】

Spatio-temporal chaotic dynamics in a two-dimensional excitable medium is (cross-) estimated using a machine learning method based on a convolutional neural network combined with a conditional random field. The performance of this approach is demonstrated using the four variables of the Bueno-Orovio-Fenton-Cherry model describing electrical excitation waves in cardiac tissue. Using temporal sequences of two-dimensional fields representing the values of one or more of the model variables as input the network successfully cross-estimated all variables and provides excellent forecasts when applied iteratively.

【 授权许可】

CC BY