From Winter Storm Thermodynamics to Wind Gust Extremes: Discovering Interpretable Equations from Data
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908761971490816 |
|---|---|
| author | Tam, Frederick Iat-Hin Augsburger, Fabien Beucler, Tom |
| author_facet | Tam, Frederick Iat-Hin Augsburger, Fabien Beucler, Tom |
| contents | Reliably identifying and understanding temporal precursors to extreme wind gusts is crucial for early warning and mitigation. This study proposes a simple data-driven approach to extract key predictors from a dataset of historical extreme European winter windstorms and derive simple equations linking these precursors to extreme gusts over land. A major challenge is the limited training data for extreme events, increasing the risk of model overfitting. Testing various mitigation strategies, we find that combining dimensionality reduction, careful cross-validation, feature selection, and a nonlinear transformation of maximum wind gusts informed by Generalized Extreme Value distributions successfully reduces overfitting. These measures yield interpretable equations that generalize across regions while maintaining satisfactory predictive skill. The discovered equations reveal the association between a steady drying low-troposphere before landfall and wind gust intensity in Northwestern Europe. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_07905 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From Winter Storm Thermodynamics to Wind Gust Extremes: Discovering Interpretable Equations from Data Tam, Frederick Iat-Hin Augsburger, Fabien Beucler, Tom Atmospheric and Oceanic Physics Applications Reliably identifying and understanding temporal precursors to extreme wind gusts is crucial for early warning and mitigation. This study proposes a simple data-driven approach to extract key predictors from a dataset of historical extreme European winter windstorms and derive simple equations linking these precursors to extreme gusts over land. A major challenge is the limited training data for extreme events, increasing the risk of model overfitting. Testing various mitigation strategies, we find that combining dimensionality reduction, careful cross-validation, feature selection, and a nonlinear transformation of maximum wind gusts informed by Generalized Extreme Value distributions successfully reduces overfitting. These measures yield interpretable equations that generalize across regions while maintaining satisfactory predictive skill. The discovered equations reveal the association between a steady drying low-troposphere before landfall and wind gust intensity in Northwestern Europe. |
| title | From Winter Storm Thermodynamics to Wind Gust Extremes: Discovering Interpretable Equations from Data |
| topic | Atmospheric and Oceanic Physics Applications |
| url | https://arxiv.org/abs/2504.07905 |