An ensemble quadratic echo state network for non-linear spatio-temporal forecasting
From MaRDI portal
Publication:6540526
DOI10.1002/sta4.160MaRDI QIDQ6540526
Christopher K. Wikle, Patrick L. McDermott
Publication date: 16 May 2024
Published in: Stat (Search for Journal in Brave)
recurrent neural networksea surface temperaturereservoir computinggeneral quadratic non-linearitylong-lead forecasting
Cites Work
- Unnamed Item
- Unnamed Item
- Reservoir computing approaches to recurrent neural network training
- A general science-based framework for dynamical spatio-temporal models
- Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
- Polynomial nonlinear spatio‐temporal integro‐difference equation models
- Physically motivated scale interaction parameterization in reduced rank quadratic nonlinear dynamic spatio‐temporal models
- A model‐based approach for analog spatio‐temporal dynamic forecasting
- Modern perspectives on statistics for spatio-temporal data
- Sparsity in nonlinear dynamic spatiotemporal models using implied advection
Related Items (3)
Deep echo state networks with uncertainty quantification for spatio-temporal forecasting ⋮ Reds: random ensemble deep spatial prediction ⋮ Calibrated forecasts of quasi-periodic climate processes with deep echo state networks and penalized quantile regression
This page was built for publication: An ensemble quadratic echo state network for non-linear spatio-temporal forecasting
