[论文解读] On some limitations of data-driven weather forecasting models

Massimo Bonavita|arXiv (Cornell University)|Sep 15, 2023

Meteorological Phenomena and Simulations被引用 8

一句话总结

该论文分析数据驱动天气预报（以盘古天气为例）的保真度和物理一致性，并指出尽管机器学习模型在特定应用中可以增加价值，但与基于物理的模型相比，可能在保真度和物理一致性方面存在不足，从而影响传统的预报技能解释。

ABSTRACT

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 possibly 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 at least partly attributed to these peculiarities. Balancing forecast skill and physical consistency of ML-driven predictions will be an important consideration for future ML models. However, and similarly to other modern post-processing technologies, the current ML models appear to be already able to add value to standard NWP output for specific forecast applications and combined with their extremely low computational cost during deployment, are set to provide an additional, useful source of forecast information. .

研究动机与目标

• 推动在传统技能评估之外对数据驱动天气预报进行评估。
• 评估ML预报相对于基于物理的模型的保真度。
• 检验数据驱动预测的物理一致性及其对可信预报的意义。
• 识别在存在局限性情况下，ML模型在特定应用中仍可增加价值。

提出的方法

• 检视一个典型数据驱动模型（盘古天气）的预报。
• 在天气预测背景下评估ML预报的保真度和物理一致性。
• 将ML预报特征与基于物理的模型的期望进行比较。
• 讨论低计算成本和后处理如何影响预报的实用性。

实验结果

研究问题

• RQ1 数据驱动天气预报是否具备与基于物理的模型相当的保真度？
• RQ2 预报是否与已建立的大气动力学和守恒定律在物理上保持一致？
• RQ3 ML模型的表观预报技能如何与其保真度和物理一致性相关？
• RQ4 尽管存在局限性，ML模型能否为特定应用提供有价值的附加预报信息？

主要发现

• 与基于物理的模型相比，ML预报可能缺乏保真度和物理一致性。
• ML在传统确定性技能指标上的优势部分地反映了这些特性，而不一定代表真正的物理准确性。
• ML预报在特定预报应用中仍可增加价值。
• ML部署的极低计算成本支持在与标准NWP输出结合时，作为额外的预报信息来源使用。