Precipitation nowcasting, the high-resolution forecasting of precipitation up to two hours ahead, supports the real-world socioeconomic needs of many sectors reliant on weather-dependent decision-making^1,2. State-of-the-art operational nowcasting methods typically advect precipitation fields with radar-based wind estimates, and struggle to capture important non-linear events such as convective initiations^3,4. Recently introduced deep learning methods use radar to directly predict future rain rates, free of physical constraints^5,6. While they accurately predict low-intensity rainfall, their operational utility is limited because their lack of constraints produces blurry nowcasts at longer lead times, yielding poor performance on rarer medium-to-heavy rain events. Here we present a deep generative model for the probabilistic nowcasting of precipitation from radar that addresses these challenges. Using statistical, economic and cognitive measures, we show that our method provides improved forecast quality, forecast consistency and forecast value. Our model produces realistic and spatiotemporally consistent predictions over regions up to 1,536 km × 1,280 km and with lead times from 5–90 min ahead. Using a systematic evaluation by more than 50 expert meteorologists, we show that our generative model ranked first for its accuracy and usefulness in 89% of cases against two competitive methods. When verified quantitatively, these nowcasts are skillful without resorting to blurring. We show that generative nowcasting can provide probabilistic predictions that improve forecast value and support operational utility, and at resolutions and lead times where alternative methods struggle.

降水临近预报，即提前两小时的高分辨率降水预报，支持许多依赖天气决策的行业的现实社会经济需求^1,2。最先进的业务临近预报方法通常使用基于雷达的风估计平流降水场，并且难以捕捉重要的非线性事件，例如对流起始^3,4。最近推出的深度学习方法使用雷达直接预测未来的降雨率，不受物理限制^5,6. 虽然它们准确地预测了低强度降雨，但它们的操作效用受到限制，因为它们缺乏限制会在较长的提前期产生模糊的临近预报，从而在罕见的中到大雨事件中表现不佳。在这里，我们提出了一个深度生成模型，用于解决这些挑战的雷达降水概率临近预报。使用统计、经济和认知措施，我们表明我们的方法提供了改进的预测质量、预测一致性和预测价值。我们的模型在高达 1,536 公里 × 1,280 公里的区域内产生现实且时空一致的预测，提前 5 到 90 分钟。通过 50 多位气象专家的系统评估，我们表明，我们的生成模型在 89% 的案例中与两种竞争方法相比，其准确性和实用性排名第一。经定量验证后，这些临近预报是熟练的，无需进行模糊处理。我们表明，生成临近预报可以提供概率预测，从而提高预测值并支持运营效用，以及替代方法难以解决的分辨率和交货时间。