To address the structural safety of ancient masonry arch bridges under extreme flood conditions, this paper takes an ancient brick–stone arch bridge as the prototype and adopts the Coupled Eulerian–Lagrangian (CEL) method to construct a fully discrete three-dimensional refined masonry numerical model. Two parameters including cohesive surface damage (CSDMG) and contact status (CSTATUS) are introduced to analyze the flood discharge capacity, stress field evolution, and damage evolution of the bridge under different discharge conditions. The results show that when the flood discharge approaches 2030m³/s, a backwater effect occurs, adversely affecting the bridge structure. Meanwhile, due to the absence of water-deflecting stone protection, the upstream side span is prone to stress concentration, which triggers interfacial damage. When the displacement of the upstream side span exceeds 10 mm, the load-transfer path of the bridge changes, and contact failure and masonry block sliding occur at the arch springing of the second downstream span, further reducing the overall structural stability of the bridge. This study reveals the damage mechanism of ancient brick–stone arch bridges that flood impact leads to reconstruction of load-transfer paths via cohesive damage between masonry units and further induces arch springing failure, which can provide references for flood protection and reinforcement design of similar ancient masonry arch bridges.

In recent years, short-term extreme wind fields prediction has become a research hotspot and academic frontier in the area of international wind engineering due to its vital role in structural safety. Accurate prediction of in-situ wind speed before the arrival of extreme wind fields is of great significance for the early warning of engineering structures safety and emergency protection. 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 in-situ 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 extreme wind fields prediction, showing broad application prospects. In this regard, this paper provides a comprehensive review of recent progress in the short-term extreme wind fields prediction 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, we classify and evaluate prevalent methods for short-term extreme wind field prediction, focusing on three predominant wind types: regular strong winds, typhoons, and thunderstorm winds. Their advantages and limitations are summarized. Finally, considering current research gaps and challenges in short-term prediction of extreme wind fields, potential future directions are proposed.