Data-based wind disaster climate identification algorithm and extreme wind speed prediction

TL;DR

This paper introduces a novel wind hazard type identification algorithm using pattern recognition and machine learning, enabling more accurate extreme wind speed predictions for mixed climates, which improves structural design safety.

Contribution

It presents a new wind hazard classification method and compares machine learning models, enhancing the accuracy of wind speed estimation in complex climate conditions.

Findings

The proposed algorithm effectively identifies wind hazard types from meteorological data.

Machine learning models show varying accuracy, with some outperforming traditional methods.

Using mixed hazard types improves the precision of extreme wind speed predictions.

Abstract

An extreme wind speed estimation method that considers wind hazard climate types is critical for design wind load calculation for building structures affected by mixed climates. However, it is very difficult to obtain wind hazard climate types from meteorological data records, because they restrict the application of extreme wind speed estimation in mixed climates. This paper first proposes a wind hazard type identification algorithm based on a numerical pattern recognition method that utilizes feature extraction and generalization. Next, it compares six commonly used machine learning models using K-fold cross-validation. Finally, it takes meteorological data from three locations near the southeast coast of China as examples to examine the algorithm performance. Based on classification results, the extreme wind speeds calculated based on mixed wind hazard types is compared with those obtained from conventional methods, and the effects on structural design for different return periods are discussed.