A decision-tree-based measure–correlate–predict approach for peak wind gust estimation from a global reanalysis dataset
oleh: S. Kartal, S. Basu, S. J. Watson
| Format: | Article |
|---|---|
| Diterbitkan: | Copernicus Publications 2023-10-01 |
Deskripsi
<p>Peak wind gust (<span class="inline-formula"><i>W</i><sub>p</sub></span>) is a crucial meteorological variable for wind farm planning and operations. However, for many wind farm sites, there is a dearth of on-site measurements of <span class="inline-formula"><i>W</i><sub>p</sub></span>. In this paper, we propose a machine-learning approach (called INTRIGUE, decIsioN-TRee-based wInd GUst Estimation) that utilizes numerous inputs from a public-domain reanalysis dataset and, in turn, generates multi-year, site-specific <span class="inline-formula"><i>W</i><sub>p</sub></span> series. Through a systematic feature importance study, we also identify the most relevant meteorological variables for <span class="inline-formula"><i>W</i><sub>p</sub></span> estimation. The INTRIGUE approach outperforms the baseline predictions for all wind gust conditions. However, the performance of this proposed approach and the baselines for extreme conditions (i.e., <span class="inline-formula"><i>W</i><sub>p</sub>>20</span> m s<span class="inline-formula"><sup>−1</sup></span>) is less satisfactory.</p>