|
深度不确定性量化：一种用于天气预报的机器学习方法
Deep Uncertainty Quantification: A Machine Learning Approach for Weather Forecasting |
|
| |
| 课程网址: |
http://videolectures.net/kdd2019_wang_lu_yan/
|
| 主讲教师: |
Bin Wang
|
| 开课单位: |
悉尼理工大学
|
| 开课时间: |
2020-03-02
|
| 课程语种: |
英语
|
| 中文简介: |
天气预报通常通过数值天气预报（NWP）来解决，由于初始状态设置不当，有时会导致性能不佳。在本文中，我们设计了一种数据驱动的方法，该方法通过有效的信息融合机制进行增强，以从包含NWP先验知识的历史数据中学习。我们将天气预报问题看作一个端到端的深度学习问题，并通过提出一个新的负对数似然误差（NLE）损失函数来解决它。我们提出的方法的一个显著优点是，它同时实现了单值预测和不确定性量化，我们称之为深度不确定性量化（DUQ）。还探索了有效的深度集成策略，以进一步提高性能。这一新方法是在中国北京气象站收集的公共数据集上进行评估的。实验结果表明，与均方误差（MSE）损失和平均绝对误差（MAE）损失相比，所提出的NLE损失显著提高了泛化能力。与NWP相比，此方法显著提高了47.76%的准确性，这是此基准数据集的最新结果。
|
| 课程简介: |
Weather forecasting is usually solved through numerical weather prediction (NWP), which can sometimes lead to unsatisfactory performance due to inappropriate setting of the initial states. In this paper, we design a data-driven method augmented by an effective information fusion mechanism to learn from historical data that incorporates prior knowledge from NWP. We cast the weather forecasting problem as an end-to-end deep learning problem and solve it by proposing a novel negative log-likelihood error (NLE) loss function. A notable advantage of our proposed method is that it simultaneously implements single-value forecasting and uncertainty quantification, which we refer to as deep uncertainty quantification (DUQ). Efficient deep ensemble strategies are also explored to further improve performance. This new approach was evaluated on a public dataset collected from weather stations in Beijing, China. Experimental results demonstrate that the proposed NLE loss significantly improves generalization compared to mean squared error (MSE) loss and mean absolute error (MAE) loss. Compared with NWP, this approach significantly improves accuracy by 47.76%, which is a state-of-the-art result on this benchmark dataset.
|
| 关 键 词: |
深度不确定性量化; 用于天气预报方法; 机器学习方法
|
| 课程来源: |
视频讲座网
|
| 数据采集: |
2022-09-19：cyh
|
| 最后编审: |
2022-09-19：cyh
|
| 阅读次数: |
60
|
|
图 书 馆