Data-driven weather prediction (DDWP) models are increasingly becoming
popular for weather forecasting. However, while operational weather forecasts
predict a wide variety of weather variables, DDWPs currently forecast a
specific set of key prognostic variables. Non-prognostic ("diagnostic")
variables are sometimes modeled separately as dependent variables of the
prognostic variables (c.f. FourCastNet), or by including the diagnostic
variable as a target in the DDWP. However, the cost of training and deploying
bespoke models for each diagnostic variable can increase dramatically with more
diagnostic variables, and limit the operational use of such models. Likewise,
retraining an entire DDWP each time a new diagnostic variable is added is also
cost-prohibitive. We present an two-stage approach that allows new diagnostic
variables to be added to an end-to-end DDWP model without the expensive
retraining. In the first stage, we train an autoencoder that learns to embed
prognostic variables into a latent space. In the second stage, the autoencoder
is frozen and "downstream" models are trained to predict diagnostic variables
using only the latent representations of prognostic variables as input. Our
experiments indicate that models trained using the two-stage approach offer
accuracy comparable to training bespoke models, while leading to significant
reduction in resource utilization during training and inference. This approach
allows for new "downstream" models to be developed as needed, without affecting
existing models and thus reducing the friction in operationalizing new models.

使用两阶段方法，我们训练了一个自编码器来将预测变量嵌入到潜在空间，并进一步利用这些嵌入表示进行诊断变量的预测，从而实现了减少资源使用、提高准确性和降低操作新模型的摩擦。

利用预训练的天气嵌入学习预测诊断参数

Learning to forecast diagnostic parameters using pre-trained weather  embedding

We present a parsimonious deep learning weather prediction model on the
Hierarchical Equal Area isoLatitude Pixelization (HEALPix) to forecast seven
atmospheric variables for arbitrarily long lead times on a global approximately
110 km mesh at 3h time resolution. In comparison to state-of-the-art machine
learning weather forecast models, such as Pangu-Weather and GraphCast, our
DLWP-HPX model uses coarser resolution and far fewer prognostic variables. Yet,
at one-week lead times its skill is only about one day behind the
state-of-the-art numerical weather prediction model from the European Centre
for Medium-Range Weather Forecasts. We report successive forecast improvements
resulting from model design and data-related decisions, such as switching from
the cubed sphere to the HEALPix mesh, inverting the channel depth of the U-Net,
and introducing gated recurrent units (GRU) on each level of the U-Net
hierarchy. The consistent east-west orientation of all cells on the HEALPix
mesh facilitates the development of location-invariant convolution kernels that
are successfully applied to propagate global weather patterns across our
planet. Without any loss of spectral power after two days, the model can be
unrolled autoregressively for hundreds of steps into the future to generate
stable and realistic states of the atmosphere that respect seasonal trends, as
showcased in one-year simulations. Our parsimonious DLWP-HPX model is
research-friendly and potentially well-suited for sub-seasonal and seasonal
forecasting.

我们提出了一种简约的深度学习天气预测模型，使用 Hierarchical Equal Area isoLatitude Pixelization（HEALPix）在全球近似 110 公里网格上，以 3 小时时间分辨率预测任意长时间的七个大气变量。与现有的机器学习天气预测模型（如 Pangu-Weather 和 GraphCast）相比，我们的 DLWP-HPX 模型使用更粗的分辨率和更少的预报变量。然而，在一周的提前时间内，其技能仅比欧洲中期天气预报中心最先进的数值天气预报模型晚了一天。我们报告了模型设计和与数据相关的决策带来的连续预测改进，例如从立方球切换到 HEALPix 网格，反演 U-Net 的通道深度，并在 U-Net 层次结构的每个级别引入门控循环单元（GRU）。HEALPix 网格上所有单元格的一致东西方向有助于开发位置不变的卷积核，成功地将全球气象模式传播到地球上。该模型在两天后没有任何频谱损失，可以自回归地展开数百步，生成稳定且逼真的大气状态，尊重季节趋势，在一年模拟中展示了这一点。我们简约的 DLWP-HPX 模型具有很好的研究性质，可能非常适合亚季节和季节性的预测。