Recent advances in deep learning have significantly elevated weather prediction models. However, these models often falter in real-world scenarios due to their sensitivity to spatial-temporal shifts. This issue is particularly acute in weather forecasting, where models are prone to overfit to local and temporal variations, especially when tasked with fine-grained predictions. In this paper, we address these challenges by developing a robust precipitation forecasting model that demonstrates resilience against such spatial-temporal discrepancies. We introduce Temporal Frame Interpolation (TFI), a novel technique that enhances the training dataset by generating synthetic samples through interpolating adjacent frames from satellite imagery and ground radar data, thus improving the model's robustness against frame noise. Moreover, we incorporate a unique Multi-Level Dice (ML-Dice) loss function, leveraging the ordinal nature of rainfall intensities to improve the model's performance. Our approach has led to significant improvements in forecasting precision, culminating in our model securing \textit{1st place} in the transfer learning leaderboard of the \textit{Weather4cast'23} competition. This achievement not only underscores the effectiveness of our methodologies but also establishes a new standard for deep learning applications in weather forecasting. Our code and weights have been public on \url{https://github.com/Secilia-Cxy/UNetTFI}.

翻译：近年来，深度学习领域的进展显著提升了天气预报模型的性能。然而，这些模型在实际应用中常因对时空分布变化的敏感性而表现不佳。这一问题在天气预报中尤为突出，尤其是在需要细粒度预测时，模型容易过度拟合局部时空变化。本文通过开发对时空差异具有鲁棒性的降水预报模型来解决上述挑战。我们提出时间帧插值（TFI）技术，该技术通过插值卫星影像与地面雷达数据的相邻帧生成合成样本，从而增强训练数据集，提升模型对帧噪声的鲁棒性。此外，我们引入创新的多层级骰子损失函数（ML-Dice），利用降雨强度的序数特性改善模型性能。本方法显著提升了预报精度，最终模型在Weather4cast'23竞赛的迁移学习排行榜中荣获第一名。这一成就不仅验证了所提方法的有效性，也为深度学习在天气预报领域的应用树立了新标杆。我们的代码与模型权重已开源至：\url{https://github.com/Secilia-Cxy/UNetTFI}。