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. The preliminary version of the proposed method won 2nd place in an online competition for daily weather forecasting.
翻译:天气预报通常通过数字天气预测解决,有时由于初始状态的不适当设置而导致业绩不尽人意。在本文中,我们设计了一种数据驱动方法,辅之以一个有效的信息聚合机制,以学习吸收来自新气候预测公司先前的知识的历史数据。我们把天气预报问题作为一个端到端深层次的学习问题,并通过提出一个新的负日志相似误差损失功能来解决。我们拟议方法的一个显著优点是,它同时执行单一值预测和不确定性量化,我们称之为深度不确定性量化(DuQ ) 。高效的深层混合战略也得到探索,以进一步改进业绩。在中国北京气象站收集的一套公共数据集上对这一新方法进行了评估。实验结果表明,拟议的NLE损失与平均正方差(MSE)损失相比,大大改进了一般化,意味着绝对错误(MAE)损失。与NWP相比,这一方法的一个显著优点是,它使准确度提高了47.76%,这是这一基准数据集上的一个最先进的结果。拟议方法的初步版本在日常的天气预报中赢得了一次竞争。