Deep Graph Convolutional Networks for Wind Speed Prediction

TL;DR

This paper introduces novel graph convolutional network models for wind speed prediction that learn the spatial relationships between weather stations and incorporate temporal data, outperforming existing baselines on real datasets.

Contribution

The paper proposes new GCN-based models with learnable adjacency matrices and self-loop mechanisms for improved wind speed forecasting.

Findings

Models outperform baseline methods on real datasets.

Learned adjacency matrices reveal station relationships.

Incorporating temporal convolution enhances predictions.

Abstract

Wind speed prediction and forecasting is important for various business and management sectors. In this paper, we introduce new models for wind speed prediction based on graph convolutional networks (GCNs). Given hourly data of several weather variables acquired from multiple weather stations, wind speed values are predicted for multiple time steps ahead. In particular, the weather stations are treated as nodes of a graph whose associated adjacency matrix is learnable. In this way, the network learns the graph spatial structure and determines the strength of relations between the weather stations based on the historical weather data. We add a self-loop connection to the learnt adjacency matrix and normalize the adjacency matrix. We examine two scenarios with the self-loop connection setting (two separate models). In the first scenario, the self-loop connection is imposed as a constant additive. In the second scenario a learnable parameter is included to enable the network to decide about the self-loop connection strength. Furthermore, we incorporate data from multiple time steps with temporal convolution, which together with spatial graph convolution constitutes spatio-temporal graph convolution. We perform experiments on real datasets collected from weather stations located in cities in Denmark and the Netherlands. The numerical experiments show that our proposed models outperform previously developed baseline models on the referenced datasets. We provide additional insights by visualizing learnt adjacency matrices from each layer of our models.