Using data assimilation to train a hybrid forecast system that combines machine-learning and knowledge-based components

DOI10.1063/5.0048050zbMath1462.37090arXiv2102.07819OpenAlexW3161808614MaRDI QIDQ4993713

Michelle Girvan, Brian R. Hunt, Edward Ott, Jaideep Pathak, Alexander Wikner, I. Szunyogh

Publication date: 16 June 2021

Published in: Chaos: An Interdisciplinary Journal of Nonlinear Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2102.07819

Mathematics Subject Classification ID

Time series analysis of dynamical systems (37M10)

Related Items (1)

A causality-based learning approach for discovering the underlying dynamics of complex systems from partial observations with stochastic parameterization

Uses Software

• GitHub

Cites Work

• Unnamed Item
• Unnamed Item
• Online learning of both state and dynamics using ensemble Kalman filters
• Efficient data assimilation for spatiotemporal chaos: a local ensemble transform Kalman filter
• Nonlinear analysis of hydrodynamic instability in laminar flames—I. Derivation of basic equations
• Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data
• Deterministic Nonperiodic Flow
• Machine Learning: Deepest Learning as Statistical Data Assimilation Problems
• Data Assimilation
• Fourth-Order Time-Stepping for Stiff PDEs
• Data Assimilation

This page was built for publication: Using data assimilation to train a hybrid forecast system that combines machine-learning and knowledge-based components