Deep Echo State Networks with Uncertainty Quantification for Spatio-Temporal Forecasting

no code implementations • 28 Jun 2018 • Patrick L. McDermott, Christopher K. Wikle

The methodology is first applied to a data set simulated from a novel non-Gaussian multiscale Lorenz-96 dynamical system simulation model and then to a long-lead United States (U. S.) soil moisture forecasting application.

Spatio-Temporal Forecasting Uncertainty Quantification

Bayesian Recurrent Neural Network Models for Forecasting and Quantifying Uncertainty in Spatial-Temporal Data

no code implementations • 2 Nov 2017 • Patrick L. McDermott, Christopher K. Wikle

Recurrent neural networks (RNNs) are nonlinear dynamical models commonly used in the machine learning and dynamical systems literature to represent complex dynamical or sequential relationships between variables.

Spatio-Temporal Forecasting Uncertainty Quantification

An Ensemble Quadratic Echo State Network for Nonlinear Spatio-Temporal Forecasting

no code implementations • 16 Aug 2017 • Patrick L. McDermott, Christopher K. Wikle

Spatio-temporal data and processes are prevalent across a wide variety of scientific disciplines.

Management Spatio-Temporal Forecasting +1