Weather forecasting is essential for various human activities. Recent
data-driven models have outperformed numerical weather prediction by utilizing
deep learning in forecasting performance. However, challenges remain in
efficiently handling multiple meteorological variables. This study proposes a
new variable aggregation scheme and an efficient learning framework for that
challenge. Experiments show that VarteX outperforms the conventional model in
forecast performance, requiring significantly fewer parameters and resources.
The effectiveness of learning through multiple aggregations and regional split
training is demonstrated, enabling more efficient and accurate deep
learning-based weather forecasting.

通过使用数据驱动模型中的深度学习，我们提出了一种新的变量聚合方案和高效的学习框架，以增强天气预报的性能和准确性。实验证明，VarteX 在预报性能方面优于传统模型，所需的参数和资源明显减少。通过多种聚合和区域分割训练，学习的有效性得到了证明，从而实现更高效和准确的深度学习天气预报。

通过分布式变量表示增强天气预报

VarteX: Enhancing Weather Forecast through Distributed Variable  Representation

As in many other areas of engineering and applied science, Machine Learning
(ML) is having a profound impact in the domain of Weather and Climate
Prediction. A very recent development in this area has been the emergence of
fully data-driven ML prediction models which routinely claim superior
performance to that of traditional physics-based models. In this work, we
examine some aspects of the forecasts produced by an exemplar of the current
generation of ML models, Pangu-Weather, with a focus on the fidelity and
physical consistency of those forecasts and how these characteristics relate to
perceived forecast performance. The main conclusion is that Pangu-Weather
forecasts, and by extension those of similar ML models, do not have the
fidelity and physical consistency of physics-based models and their advantage
in accuracy on traditional deterministic metrics of forecast skill can be
attributed, to a large extent, to these peculiarities. Similarly to other
current post-processing technologies, ML models appear to be able to add value
to standard NWP outputs for specific forecast applications and combined with
their extremely low computational cost during deployment, will likely provide
an additional, useful source of forecast information.

在天气与气候预测领域，机器学习（ML）正对传统基于物理模型的预测模型提供有力的挑战，并取得了更高的预测准确性。本研究通过对当前 ML 模型中 Pangu-Weather 预测的准确性和物理一致性进行考察，发现相比于基于物理模型的预测，ML 模型在准确性指标上的优势主要是由于其独特性而产生的。此外，ML 模型在特定的预测应用中与传统数值天气预报输出具有协同作用，并且在实际应用中具有极低的计算成本，因此能够为预测信息提供一种有价值的额外来源。

数据驱动的天气预报模型的局限性

On the limitations of data-driven weather forecasting models

Time series forecasting has received a lot of attention with recurrent neural
networks (RNNs) being one of the widely used models due to their ability to
handle sequential data. Prior studies of RNNs for time series forecasting yield
inconsistent results with limited insights as to why the performance varies for
different datasets. In this paper, we provide an approach to link the
characteristics of time series with the components of RNNs via the versatile
metric of distance correlation. This metric allows us to examine the
information flow through the RNN activation layers to be able to interpret and
explain their performance. We empirically show that the RNN activation layers
learn the lag structures of time series well. However, they gradually lose this
information over a span of a few consecutive layers, thereby worsening the
forecast quality for series with large lag structures. We also show that the
activation layers cannot adequately model moving average and heteroskedastic
time series processes. Last, we generate heatmaps for visual comparisons of the
activation layers for different choices of the network hyperparameters to
identify which of them affect the forecast performance. Our findings can,
therefore, aid practitioners in assessing the effectiveness of RNNs for given
time series data without actually training and evaluating the networks.

通过距离相关度的多功能度量方法，我们研究了 RNNs 的组成部分与时间序列特征之间的联系并解释了它们的性能差异。我们发现 RNN 的激活层能够很好地学习时间序列的滞后结构，但在连续几个层中逐渐丧失了该信息，从而降低了具有较大滞后结构的序列的预测质量。我们还发现激活层无法充分建模移动平均和异方差时间序列过程，并通过热图可视化不同网络超参数选择下的激活层进行比较，以识别其对预测性能的影响。因此，我们的研究结果可以帮助从业者在无需进行实际训练和评估网络的情况下评估 RNNs 在给定时间序列数据上的效果。