The traditional method for estimating weather forecast sensitivity to initial conditions uses adjoint models, which are limited to short lead times due to linearization around a control forecast. The advent of deep-learning frameworks enables a new approach using backpropagation and gradient descent to iteratively optimize initial conditions, minimizing forecast errors. We apply this approach to the June 2021 Pacific Northwest heatwave using the GraphCast model, yielding over 90% reduction in 10-day forecast errors over the Pacific Northwest. Similar improvements are found for Pangu-Weather model forecasts initialized with the GraphCast-derived optimal, suggesting that model error is an unimportant part of the perturbations. Eliminating small scales from the perturbations also yields similar forecast improvements. Extending the length of the optimization window, we find forecast improvement to about 23 days, suggesting atmospheric predictability at the upper end of recent estimates.

中文翻译：

---

来自深度学习敏感性分析的 2021 年太平洋西北热浪的可预测性极限


估计天气预报对初始条件的敏感性的传统方法使用伴随模型，由于控制预报的线性化，这些模型仅限于较短的提前期。深度学习框架的出现使一种使用反向传播和梯度下降的新方法成为可能，以迭代方式优化初始条件，从而最大限度地减少预测误差。我们使用 GraphCast 模型将这种方法应用于 2021 年 6 月的太平洋西北地区热浪，使太平洋西北地区的 10 天预报误差减少了 90% 以上。使用 GraphCast 派生的最优值初始化的 Pangu-Weather 模型预报也发现了类似的改进，这表明模型误差是扰动的一个不重要的部分。从扰动中消除小尺度也会产生类似的预报改进。延长优化窗口的长度，我们发现预测改善到大约 23 天，这表明大气的可预测性处于最近估计的上限。