Weather prediction is critical for a range of human activities including transportation, agriculture and industry, as well as the safety of the general public. Machine learning is transforming numerical weather prediction (NWP) by replacing the numerical solver with neural networks, improving the speed and accuracy of the forecasting component of the prediction pipeline ^1,2,3,4,5,6. However, current models rely on numerical systems at initialisation and to produce local forecasts, limiting their achievable gains. Here we show that a single machine learning model can replace the entire NWP pipeline. Aardvark Weather, an end-to-end data-driven weather prediction system, ingests observations and produces global gridded forecasts and local station forecasts. The global forecasts outperform an operational NWP baseline for multiple variables and lead times. The local station forecasts are skillful up to ten days lead time, competing with a post-processed global NWP baseline and a state-of-the-art end-to-end forecasting system with input from human forecasters. End-to-end tuning further improves the accuracy of local forecasts. Our results show that skillful forecasting is possible without relying on NWP at deployment time, which will enable the full speed and accuracy benefits of data-driven models to be realised. We believe Aardvark Weather will be the starting point for a new generation of end-to-end models that will reduce computational costs by orders of magnitude, and enable rapid, affordable creation of customised models for a range of end-users.

天气预报对于一系列人类活动至关重要，包括交通、农业和工业，以及公众的安全。机器学习正在通过用神经网络取代数值求解器来改变数值天气预报 （NWP），从而提高预测管道预测组件的速度和准确性 ^1,2,3,4,5,6。然而，目前的模型在初始化时依赖于数值系统并产生局部预测，这限制了它们可实现的收益。在这里，我们展示了单个机器学习模型可以取代整个 NWP 管道。Aardvark Weather 是一个端到端的数据驱动型天气预报系统，可提取观测结果并生成全球网格预报和本地站点预报。对于多个变量和提前期，全球预测的表现优于运营 NWP 基线。当地站点预报的准备时间长达 10 天，与后处理的全球 NWP 基线和最先进的端到端预报系统竞争，该系统由人工预报员提供输入。端到端优化可进一步提高本地预测的准确性。我们的结果表明，在部署时无需依赖 NWP 即可进行熟练的预测，这将使数据驱动模型的全部速度和准确性优势得以实现。我们相信 Aardvark Weather 将成为新一代端到端模型的起点，它将计算成本降低几个数量级，并支持为一系列最终用户快速、经济地创建自定义模型。