Shannon Andrew, Houghton Conor, Barton David A W, Homer Martin
School of Computer Science, University of Bristol, Bristol, BS8 1UB, UK.
School of Engineering Mathematics and Technology, University of Bristol, Bristol, BS8 1TW, UK.
Sci Rep. 2025 Jul 2;15(1):22497. doi: 10.1038/s41598-025-03957-x.
Surrogate modeling of non-linear oscillator networks remains challenging due to discrepancies between simplified analytical models and real-world complexity. To bridge this gap, we investigate hybrid reservoir computing, combining reservoir computing with "expert" analytical models. Simulating the absence of an exact model, we first test the surrogate models with parameter errors in their expert model. Second, in a residual physics task, we assess the performance when the expert model lacks key non-linear coupling terms present in an extended ground-truth model. We focus on short-term forecasting across diverse dynamical regimes, evaluating the use of these surrogates for control applications. We show that hybrid reservoir computers generally outperform standard reservoir computers and exhibit greater robustness to parameter tuning. This advantage is less pronounced in the residual physics task. Notably, unlike standard reservoir computers, the performance of the hybrid does not degrade when crossing an observed spectral radius threshold. Furthermore, there is good performance for dynamical regimes not accessible to the expert model, demonstrating the contribution of the reservoir.
由于简化的分析模型与现实世界的复杂性之间存在差异，非线性振荡器网络的替代建模仍然具有挑战性。为了弥合这一差距，我们研究了混合储层计算，即将储层计算与“专家”分析模型相结合。在模拟不存在精确模型的情况下，我们首先用专家模型中的参数误差测试替代模型。其次，在一个残余物理任务中，我们评估当专家模型缺乏扩展的真实模型中存在的关键非线性耦合项时的性能。我们专注于跨不同动力学状态的短期预测，评估这些替代模型在控制应用中的使用。我们表明，混合储层计算机通常优于标准储层计算机，并且对参数调整表现出更大的鲁棒性。在残余物理任务中，这种优势不太明显。值得注意的是，与标准储层计算机不同，混合模型的性能在超过观察到的谱半径阈值时不会下降。此外，对于专家模型无法访问的动力学状态，也有良好的性能，这证明了储层的贡献。
