Prediction of chaotic time series using recurrent neural networks and reservoir computing techniques: A comparative study
Prediction of chaotic time series using recurrent neural networks and reservoir computing techniques: A comparative study
复制标题
DOI：
10.1016/j.mlwa.2022.100300
复制
发表时间：
2022-04
影响因子：
--
通讯作者：
S. Shahi;F. Fenton;E. Cherry
中科院分区：
文献类型：
--
作者：
S. Shahi;F. Fenton;E. Cherry
近年来，机器学习技术，特别是深度学习，在许多情况下都优于传统的时间序列预测方法，包括单变量和多变量预测。本研究旨在研究（i）门控递归神经网络的能力，包括长短期记忆（LSTM）和门控递归单元（GRU）网络，（ii）水库计算（RC）技术，如回声状态网络（ESN）和混合物理信息ESN，以及（iii）非线性向量自回归（NVAR）方法，最近被引入作为下一代RC，的混沌时间序列的预测，并比较其性能方面的准确性，效率和鲁棒性。我们应用的方法来预测从两个广泛使用的混沌基准，麦基玻璃和洛伦兹-63模型，以及其他两个混沌数据集代表一个爆裂的神经元和厄尔尼诺南方涛动的动态，并表示一个实验数据集的时间序列的心脏电压与复杂的动态。我们发现，即使门控RNN技术在预测时间序列方面取得了成功，但对于本文所考虑的方法、数据集和超参数值范围，它们在预测混沌时间序列方面可能存在不足。相比之下，对于所研究的混沌数据集，我们发现水库计算和NVAR技术的计算效率更高，在混沌时间序列的长期预测中提供了更多的希望。
In recent years, machine-learning techniques, particularly deep learning, have outperformed traditional time-series forecasting approaches in many contexts, including univariate and multivariate predictions. This study aims to investigate the capability of (i) gated recurrent neural networks, including long short-term memory (LSTM) and gated recurrent unit (GRU) networks, (ii) reservoir computing (RC) techniques, such as echo state networks (ESNs) and hybrid physics-informed ESNs, and (iii) the nonlinear vector autoregression (NVAR) approach, which has recently been introduced as the next generation RC, for the prediction of chaotic time series and to compare their performance in terms of accuracy, efficiency, and robustness. We apply the methods to predict time series obtained from two widely used chaotic benchmarks, the Mackey–Glass and Lorenz-63 models, as well as two other chaotic datasets representing a bursting neuron and the dynamics of the El Niño Southern Oscillation, and to one experimental dataset representing a time series of cardiac voltage with complex dynamics. We find that even though gated RNN techniques have been successful in forecasting time series generally, they can fall short in predicting chaotic time series for the methods, datasets, and ranges of hyperparameter values considered here. In contrast, for the chaotic datasets studied, we found that reservoir computing and NVAR techniques are more computationally efficient and offer more promise in long-term prediction of chaotic time series.