Multi-node wind speed forecasting is greatly important for offshore wind power. It is a challenging task due to unknown complex spatial dependencies. Recently, graph neural networks (GNN) have been applied to wind forecasting because of their capability in modeling dependencies. However, existing methods usually require a pre-defined graph structure, which is not optimal for the downstream task and limits the application scope...

Research on the wind environment provides an important reference for tackling desertification and related environmental issues in desert regions. This article examines spatial and temporal variation of the near‐surface wind environment in the dune fields of northern China, using data from 40 meteorological stations inside and around the dune fields. Wind speed series were first subjected to homogenization, with monthly mean wi...