Generative Adversarial Network for Probabilistic Forecast of Random Dynamical Systems

DOI10.1137/21M1457448MaRDI QIDQ5095487zbMATH OpenWikidataFDO

Authors Kyongmin Yeo, Zan Li, Wesley M. Gifford

Publication date 9 August 2022

Published in SIAM Journal on Scientific Computing (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2111.03126

zbMATH Keywords

deep learninguncertainty quantificationrandom dynamical systemrecurrent neural networkgenerative adversarial network

Mathematics Subject Classification ID

Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Inference from stochastic processes and prediction (62M20) Artificial neural networks and deep learning (68T07) Neural nets and related approaches to inference from stochastic processes (62M45)

Recommendations

• Physics-informed generative adversarial networks for stochastic differential equations
• On generalized residual network for deep learning of unknown dynamical systems
• Learning dynamical systems in noise using convolutional neural networks
• Neural machine-based forecasting of chaotic dynamics
• Computing the invariant distribution of randomly perturbed dynamical systems using deep learning

Cites work

• A kernel two-sample test
• Chaotic attractors of an infinite-dimensional dynamical system
• Data based identification and prediction of nonlinear and complex dynamical systems
• Data driven governing equations approximation using deep neural networks
• Data-driven discovery of coordinates and governing equations
• Data-driven forecasting of high-dimensional chaotic systems with long short-term memory networks
• Deep learning
• Deep learning algorithm for data-driven simulation of noisy dynamical system
• Ensemble Transform Algorithms for Nonlinear Smoothing Problems
• Oscillation and chaos in physiological control systems
• Physics-informed generative adversarial networks for stochastic differential equations
• Time series analysis. Forecasting and control
• Unsupervised deep learning for super-resolution reconstruction of turbulence
• Variational inference formulation for a model-free simulation of a dynamical system with unknown parameters by a recurrent neural network

Cited in

(8)

• Generative Adversarial Network for Probabilistic Forecast of Random Dynamical System
• Generative adversarial networks-based stochastic approach to the modeling of individual jumping loads
• Generative adversarial networks are special cases of artificial curiosity (1990) and also closely related to predictability minimization (1991)
• Generative deep learning for decision making in gas networks
• Learning to simulate sequentially generated data via neural networks and Wasserstein training
• SDYN-GANs: adversarial learning methods for multistep generative models for general order stochastic dynamics
• Generative adversarial networks applied to synthetic financial scenarios generation
• Monte Carlo simulation of SDEs using GANs

Describes a project that uses

Uses Software

• EnKF
• Adam
• SeqGAN
• SGDR
• PyTorchTS
• DeepAR
• DeepONet

This page was built for publication: Generative Adversarial Network for Probabilistic Forecast of Random Dynamical Systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5095487)