Ensemble Methods for Neural Network‐Based Weather Forecasts
Ensemble Methods for Neural Network‐Based Weather Forecasts
复制标题
DOI：
10.1029/2020ms002331
复制
发表时间：
2020-02
影响因子：
6.8
通讯作者：
S. Scher;G. Messori
中科院分区：
文献类型：
--
作者：
S. Scher;G. Messori
集合天气预报通过计算集合的扩散，使每个预报都能得到一个不确定性的度量。然而，生成具有良好扩散误差关系的集合远非微不足道，并且已经探索了各种实现这一目标的方法-主要是在数值天气预报模型的背景下。在这里，我们的目标是将一个确定性的神经网络天气预报系统集成预报系统。我们测试了四种方法来生成集成：随机初始扰动，神经网络的再训练，在网络中使用随机辍学，并创建初始扰动与奇异向量分解。后一种方法被广泛用于数值天气预报模式，但尚未在神经网络上进行测试。从这四种方法获得的集合平均预测都击败了未扰动的神经网络预测，再训练方法产生最高的改善。然而，神经网络预报的技能系统地低于最先进的数值天气预报模型。
Ensemble weather forecasts enable a measure of uncertainty to be attached to each forecast, by computing the ensemble's spread. However, generating an ensemble with a good spread‐error relationship is far from trivial, and a wide range of approaches to achieve this have been explored—chiefly in the context of numerical weather prediction models. Here, we aim to transform a deterministic neural network weather forecasting system into an ensemble forecasting system. We test four methods to generate the ensemble: random initial perturbations, retraining of the neural network, use of random dropout in the network, and the creation of initial perturbations with singular vector decomposition. The latter method is widely used in numerical weather prediction models, but is yet to be tested on neural networks. The ensemble mean forecasts obtained from these four approaches all beat the unperturbed neural network forecasts, with the retraining method yielding the highest improvement. However, the skill of the neural network forecasts is systematically lower than that of state‐of‐the‐art numerical weather prediction models.