# CESAR: A Convolutional Echo State AutoencodeR for High-Resolution Wind Forecasting

arXiv: https://arxiv.org/abs/2412.10578 · HTML: https://mlsanity.com/paper/2412.10578/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 68 references that are in the map.
- First posted on arXiv 13 Dec 2024.

## Builds on (most cited first, 12 of 12)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Escaping From Saddle Points --- Online Stochastic Gradient for Tensor Decomposition](https://mlsanity.com/paper/1503.02101/) (2015)
- [Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark](https://mlsanity.com/paper/2109.14545/) (2021)
- [Modeling the Dynamics of PDE Systems with Physics-Constrained Deep Auto-Regressive Networks](https://mlsanity.com/paper/1906.05747/) (2019)
- [Revisiting Small Batch Training for Deep Neural Networks](https://mlsanity.com/paper/1804.07612/) (2018)
- [Bayesian Recurrent Neural Network Models for Forecasting and Quantifying Uncertainty in Spatial-Temporal Data](https://mlsanity.com/paper/1711.00636/) (2017)
- [Deep Echo State Networks with Uncertainty Quantification for Spatio-Temporal Forecasting](https://mlsanity.com/paper/1806.10728/) (2018)
- [An Ensemble Quadratic Echo State Network for Nonlinear Spatio-Temporal Forecasting](https://mlsanity.com/paper/1708.05094/) (2017)
- [Using Echo State Networks to Inform Physical Models for Fire Front Propagation](https://mlsanity.com/paper/2302.04960/) (2023)
- [Echo State Networks for Spatio-Temporal Area-Level Data](https://mlsanity.com/paper/2410.10641/) (2024)
- [A Bayesian Convolutional Neural Network-based Generalized Linear Model](https://mlsanity.com/paper/2210.09560/) (2022)

## Abstract (arXiv)

An accurate and timely assessment of wind speed and energy output allows an efficient planning and management of this resource on the power grid. Wind energy, especially at high resolution, calls for the development of nonlinear statistical models able to capture complex dependencies in space and time. This work introduces a Convolutional Echo State AutoencodeR (CESAR), a spatio-temporal, neural network-based model which first extracts the spatial features with a deep convolutional autoencoder, and then models their dynamics with an echo state network. We also propose a two-step approach to also allow for computationally affordable inference, while also performing uncertainty quantification. We focus on a high-resolution simulation in Riyadh (Saudi Arabia), an area where wind farm planning is currently ongoing, and show how CESAR is able to provide improved forecasting of wind speed and power for proposed building sites by up to 17% against the best alternative methods.