We present an ensemble prediction system using a Deep Learning Weather Prediction (DLWP) model that recursively predicts six key atmospheric variables with six-hour time resolution. This computationally efficient model uses convolutional neural networks (CNNs) on a cubed sphere grid to produce global forecasts. The trained model requires just three minutes on a single GPU to produce a 320-member set of six-week forecasts at 1.4° resolution. Ensemble spread is primarily produced by randomizing the CNN training process to create a set of 32 DLWP models with slightly different learned weights. Although our DLWP model does not forecast precipitation, it does forecast total column water vapor and gives a reasonable 4.5-day deterministic forecast of Hurricane Irma. In addition to simulating mid-latitude weather systems, it spontaneously generates tropical cyclones in a one-year free-running simulation. Averaged globally and over a two-year test set, the ensemble mean RMSE retains skill relative to climatology beyond two-weeks, with anomaly correlation coefficients remaining above 0.6 through six days. Our primary application is to subseasonal-to-seasonal (S2S) forecasting at lead times from two to six weeks. Current forecast systems have low skill in predicting one- or 2-week-average weather patterns at S2S time scales. The continuous ranked probability score (CRPS) and the ranked probability skill score (RPSS) show that the DLWP ensemble is only modestly inferior in performance to the European Center for Medium Range Weather Forecasts (ECMWF) S2S ensemble over land at lead times of 4 and 5–6 weeks. At shorter lead times, the ECMWF ensemble performs better than DLWP.

中文翻译：

---

使用大量深度学习天气预报模型进行亚季节预报

我们提出了一个使用深度学习天气预报 (DLWP) 模型的集合预测系统，该模型以六小时的时间分辨率递归预测六个关键大气变量。这种计算效率高的模型在立方球面网格上使用卷积神经网络 (CNN) 来生成全球预测。经过训练的模型在单个 GPU 上仅需三分钟即可以 1.4° 的分辨率生成 320 名成员的六周预测集。集成传播主要是通过随机化 CNN 训练过程来创建一组 32 个 DLWP 模型的，这些模型的学习权重略有不同。尽管我们的 DLWP 模型不预测降水，但它确实预测了总柱状水汽，并给出了对飓风艾玛的合理的 4.5 天确定性预测。除了模拟中纬度天气系统，它在为期一年的自由运行模拟中自发产生热带气旋。在全球范围内和两年的测试集上取平均值，整体平均 RMSE 保留了两周以上与气候学相关的技能，异常相关系数在六天内保持在 0.6 以上。我们的主要应用是在两到六周的提前期进行次季节到季节性 (S2S) 预测。当前的预报系统在 S2S 时间尺度上预测 1 周或 2 周平均天气模式方面的技能较低。连续排名概率得分 (CRPS) 和排名概率技能得分 (RPSS) 表明，DLWP 集合在陆地上的领先时间为 4 和5-6 周。在更短的交货时间内，