图 书 馆
气候模拟中极端事件统计降尺度的平滑分位数回归Smoothed Quantile Regression for Statistical Downscaling of Extreme Events in Climate Modeling |
|
| 课程网址: | http://videolectures.net/cidu2011_abraham_regression/ |
| 主讲教师: | Zubin Abraham |
| 开课单位: | 密歇根州立大学 |
| 开课时间: | 2012-06-12 |
| 课程语种: | 英语 |
| 中文简介: |  统计降尺度通常用于气候建模，以从全球气候模型预测的粗分辨率输出中获取未来气候情景的高分辨率空间预测。不幸的是，大多数使用标准回归方法的统计降尺度方法倾向于强调预测数据的条件平均值，而很少关注极值，这些极值很少发生，但对气候影响评估和适应研究至关重要。本文提出了一个统计降尺度框架，该框架通过直接估计响应变量的条件分位数，专注于对未来极值的准确预测。我们还将提议的框架扩展到半监督学习环境，并证明其在推断气候极端事件的幅度、频率和时间方面的有效性。就极端数据点预测的幅度而言，所提出的方法在评估的 37 个站点中的 85% 优于基线统计缩减方法。 |
| 课程简介: | Statistical downscaling is commonly used in climate modeling to obtain high-resolution spatial projections of future climate scenarios from the coarse-resolution outputs projected by global climate models. Unfortunately, most of the statistical downscaling approaches using standard regression methods tend to emphasize projecting the conditional mean of the data while paying scant attention to the extreme values that are rare in occurrence yet critical for climate impact assessment and adaptation studies. This paper presents a statistical downscaling framework that focuses on the accurate projection of future extreme values by estimating directly the conditional quantiles of the response variable. We also extend the proposed framework to a semi-supervised learning setting and demonstrate its efficacy in terms of inferring the magnitude, frequency, and timing of climate extreme events. The proposed approach outperformed baseline statistical down-scaling approaches in 85% of the 37 stations evaluated, in terms of the magnitude projected for extreme data points. |
| 关 键 词: | 统计降尺度; 气候建模; 半监督学习 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2021-06-09：zyk |
| 最后编审: | 2021-06-09：zyk |
| 阅读次数: | 43 |