Research progress and considerations on short-term prediction of extreme wind fields based on machine learning

As global climate changes, short-term prediction of extreme wind fields has become a cutting-edge research focus and academic frontier in the area of international wind engineering. Accurate prediction of in-situ wind speed before the arrival of extreme wind fields is of great significance for the early warning of structural safety and emergency protection of engineering structures. The traditional numerical weather prediction method is effective for extreme wind field prediction. However, due to insufficient spatial resolution and high consumption of computing resources, it is difficult to provide a real-time prediction of on-site wind speed for engineering structures. With the rapid development of artificial intelligence technology, machine learning offers new ideas for solving the problems mentioned above. It is increasingly widely applied in short-term prediction of extreme wind fields, showing broad application prospects. In this regard, this paper provides a comprehensive review of recent progress in the short-term prediction of extreme wind fields using machine learning-based approaches. Firstly, the application principles and characteristics of time series models, machine learning models, and hybrid models in wind field prediction are reviewed. Subsequently, from the perspective of three frequently occurring strong winds, namely regular strong winds, typhoons, and thunderstorm winds, commonly used methods for short-term prediction of extreme wind fields are classified and discussed, and their advantages and disadvantages are summarized. Finally, in light of the current research status and challenges in the short-term prediction of extreme wind fields, the potential future research directions in this field are proposed based on the authors’ thoughts and considerations.