Institut for Theoretical Physics, Technische Universität Berlin, 10623 Berlin, Germany.
Institute for Research in Electronics and Applied Physics, University of Maryland, College Park, Maryland 20742, USA.
Chaos. 2023 Jul 1;33(7). doi: 10.1063/5.0152311.
We propose a new approach to dynamical system forecasting called data-informed-reservoir computing (DI-RC) that, while solely being based on data, yields increased accuracy, reduced computational cost, and mitigates tedious hyper-parameter optimization of the reservoir computer (RC). Our DI-RC approach is based on the recently proposed hybrid setup where a knowledge-based model is combined with a machine learning prediction system, but it replaces the knowledge-based component by a data-driven model discovery technique. As a result, our approach can be chosen when a suitable knowledge-based model is not available. We demonstrate our approach using a delay-based RC as the machine learning component in conjunction with sparse identification of nonlinear dynamical systems for the data-driven model component. We test the performance on two example systems: the Lorenz system and the Kuramoto-Sivashinsky system. Our results indicate that our proposed technique can yield an improvement in the time-series forecasting capabilities compared with both approaches applied individually, while remaining computationally cheap. The benefit of our proposed approach, compared with pure RC, is most pronounced when the reservoir parameters are not optimized, thereby reducing the need for hyperparameter optimization.
我们提出了一种新的动态系统预测方法，称为数据驱动的储层计算（DI-RC），它仅基于数据，提高了准确性，降低了计算成本，并减轻了储层计算机（RC）繁琐的超参数优化。我们的 DI-RC 方法基于最近提出的混合设置，其中将基于知识的模型与机器学习预测系统相结合，但它通过数据驱动的模型发现技术代替了基于知识的组件。因此，当没有合适的基于知识的模型时，可以选择我们的方法。我们使用基于延迟的 RC 作为机器学习组件，并结合非线性动力系统稀疏识别作为数据驱动的模型组件来演示我们的方法。我们在两个示例系统上测试了性能：Lorenz 系统和 Kuramoto-Sivashinsky 系统。我们的结果表明，与单独应用的两种方法相比，我们提出的技术可以提高时间序列预测能力，同时保持计算成本低廉。与纯 RC 相比，当储层参数未优化时，我们提出的方法的优势最为明显，从而减少了超参数优化的需求。
