General circulation models (GCMs) are the foundation of weather and climate prediction^1,2. GCMs are physics-based simulators that combine a numerical solver for large-scale dynamics with tuned representations for small-scale processes such as cloud formation. Recently, machine-learning models trained on reanalysis data have achieved comparable or better skill than GCMs for deterministic weather forecasting^3,4. However, these models have not demonstrated improved ensemble forecasts, or shown sufficient stability for long-term weather and climate simulations. Here we present a GCM that combines a differentiable solver for atmospheric dynamics with machine-learning components and show that it can generate forecasts of deterministic weather, ensemble weather and climate on par with the best machine-learning and physics-based methods. NeuralGCM is competitive with machine-learning models for one- to ten-day forecasts, and with the European Centre for Medium-Range Weather Forecasts ensemble prediction for one- to fifteen-day forecasts. With prescribed sea surface temperature, NeuralGCM can accurately track climate metrics for multiple decades, and climate forecasts with 140-kilometre resolution show emergent phenomena such as realistic frequency and trajectories of tropical cyclones. For both weather and climate, our approach offers orders of magnitude computational savings over conventional GCMs, although our model does not extrapolate to substantially different future climates. Our results show that end-to-end deep learning is compatible with tasks performed by conventional GCMs and can enhance the large-scale physical simulations that are essential for understanding and predicting the Earth system.

大气环流模型 (GCM) 是天气和气候预测的基础^1,2 。 GCM 是基于物理的模拟器，它将大规模动力学的数值求解器与小规模过程（例如云形成）的调谐表示相结合。最近，在再分析数据上训练的机器学习模型在确定性天气预报方面取得了与 GCM 相当或更好的技能^3,4 。然而，这些模型并未表现出改进的集合预报，也没有表现出对长期天气和气候模拟足够的稳定性。在这里，我们提出了一种 GCM，它将大气动力学的可微分求解器与机器学习组件相结合，并表明它可以生成确定性天气、集合天气和气候的预测，与最好的机器学习和基于物理的方法相当。 NeuralGCM 在 1 到 10 天的预报方面与机器学习模型具有竞争力，在 1 到 15 天的预报方面与欧洲中期天气预报中心集合预测具有竞争力。借助规定的海面温度，NeuralGCM 可以准确跟踪数十年的气候指标，并以 140 公里分辨率进行气候预报，显示热带气旋的实际频率和轨迹等紧急现象。对于天气和气候，我们的方法比传统 GCM 节省了几个数量级的计算量，尽管我们的模型并没有推断出截然不同的未来气候。我们的结果表明，端到端深度学习与传统 GCM 执行的任务兼容，并且可以增强对于理解和预测地球系统至关重要的大规模物理模拟。