Machine Learning (ML) has shown great promise in revolutionizing weather forecasting, yet most ML systems still rely on initial conditions generated by Numerical Weather Prediction (NWP) systems. End-to-end ML models aim to eliminate this dependency, but they often rely on observation-specific encoders and require redesign or retraining when observation sources change, thereby limiting their operational robustness. Here, we introduce XiChen, a global weather observation-to-forecast ML system via four-dimensional variational (4DVar) gradient-guided flexible assimilation. We demonstrate that the gradient of the 4DVar cost function serves as a physically grounded interface that maps heterogeneous observations into a common state space. This novel formulation enables XiChen to flexibly assimilate diverse conventional and raw satellite observations while preserving physical consistency. Experiments show that the system achieves forecasting metrics competitive with operational NWP systems. This work provides a practical and physically consistent route toward operational ML-based global weather forecasting systems with heterogeneous and evolving observations.

翻译：机器学习（ML）在革新天气预报方面展现出巨大潜力，然而大多数ML系统仍依赖于数值天气预报（NWP）系统生成的初始条件。端到端ML模型旨在消除这种依赖性，但它们通常依赖于观测特定的编码器，并且在观测源发生变化时需要重新设计或重新训练，从而限制了其业务稳健性。本文提出曦辰（XiChen），一种基于四维变分（4DVar）梯度引导灵活同化的全球天气观测到预报ML系统。我们证明，4DVar代价函数的梯度可作为一个物理基础接口，将异构观测映射到统一的状态空间。这种新颖的框架使曦辰能够灵活同化多样化的常规观测和原始卫星观测，同时保持物理一致性。实验表明，该系统取得的预报指标可与业务NWP系统相媲美。这项工作为构建基于ML、能处理异构且动态变化观测的业务化全球天气预报系统，提供了一条实用且物理一致的路径。