Hybrid Forecasting of Chaotic Processes: Using Machine Learning in Conjunction with a Knowledge-Based Model

@article{Pathak2018HybridFO,
  title={Hybrid Forecasting of Chaotic Processes: Using Machine Learning in Conjunction with a Knowledge-Based Model},
  author={Jaideep Pathak and A. Wikner and R. Fussell and Sarthak Chandra and B. Hunt and M. Girvan and E. Ott},
  journal={Chaos},
  year={2018},
  volume={28 4},
  pages={
          041101
        }
}
  • Jaideep Pathak, A. Wikner, +4 authors E. Ott
  • Published 2018
  • Computer Science, Physics, Mathematics, Medicine
  • Chaos
    • A model-based approach to forecasting chaotic dynamical systems utilizes knowledge of the mechanistic processes governing the dynamics to build an approximate mathematical model of the system. In contrast, machine learning techniques have demonstrated promising results for forecasting chaotic systems purely from past time series measurements of system state variables (training data), without prior knowledge of the system dynamics. The motivation for this paper is the potential of machine… CONTINUE READING
    View on PubMed
    arxiv.org
    106 Citations
    Highly Influential Citations
    8
    Background Citations
    23
    Methods Citations
    21
    Results Citations
    4
    106 Citations
    Citation Type

    Citation Type

    Combining Machine Learning with Knowledge-Based Modeling for Scalable Forecasting and Subgrid-Scale Closure of Large, Complex, Spatiotemporal Systems
    • 9
    • PDF
    Applying Machine Learning to Improve Simulations of a Chaotic Dynamical System Using Empirical Error Correction
    • P. Watson
    • Computer Science, Medicine
    • Journal of advances in modeling earth systems
    • 2019
    • 15
    • PDF
    Forecasting of Spatio-temporal Chaotic Dynamics with Recurrent Neural Networks: a comparative study of Reservoir Computing and Backpropagation Algorithms
    • 19
    • PDF
    Attractor Ranked Radial Basis Function Network: A Nonparametric Forecasting Approach for Chaotic Dynamic Systems
    • 1
    • PDF
    Backpropagation algorithms and Reservoir Computing in Recurrent Neural Networks for the forecasting of complex spatiotemporal dynamics
    • 39
    • PDF
    Learning Ergodic Averages in Chaotic Systems
    • 2
    • Highly Influenced
    • PDF
    Using machine-learning modelling to understand macroscopic dynamics in a system of coupled maps
    • PDF
    Using machine learning to correct model error in data assimilation and forecast applications
    • 1
    • PDF
    Attractor reconstruction by machine learning.
    • 110
    • PDF
    Long-term prediction of chaotic systems with recurrent neural networks
    • PDF

    References

    SHOWING 1-10 OF 18 REFERENCES
    Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data.
    • 174
    • PDF
    Reservoir observers: Model-free inference of unmeasured variables in chaotic systems.
    • 115
    Model-Free Prediction of Large Spatiotemporally Chaotic Systems from Data: A Reservoir Computing Approach.
    • 310
    • PDF
    A hybrid neural network‐first principles approach to process modeling
    • 542
    • PDF
    Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
    • 2,499
    • PDF
    Reservoir computing approaches to recurrent neural network training
    • 1,393
    • PDF
    Reservoir computing with a single time-delay autonomous Boolean node
    • 57
    • PDF
    Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication
    • 2,085
    • PDF
    Brain-Inspired Photonic Signal Processor for Generating Periodic Patterns and Emulating Chaotic Systems
    • 35
    Long Short-Term Memory
    • 35,872
    • PDF