Learning Robust Precipitation Forecaster by Temporal Frame Interpolation

Recent advancements in deep learning have propelled the field of weather prediction models to new heights. Despite their progress, these models often struggle with real-world application due to their sensitivity to spatial-temporal shifts, a vulnerability particularly pronounced in weather prediction tasks where overfitting to local and temporal variations is common. This paper presents an investigation into the development of a robust precipitation forecasting model that stands resilient to such shifts. We introduce Temporal Frame Interpolation (TFI), an innovative technique designed to fortify forecasting models against spatial-temporal discrepancies. TFI operates by generating synthetic samples through the interpolation of adjacent frames from satellite imagery and ground radar data, thereby enriching the training dataset and bolstering the model's defense against noise on frames. Additionally, we integrate a novel multi-level dice loss, which exploits the ordinal nature of rainfall intensities to further refine model performance. These methodologies have collectively advanced our model's forecasting precision, achieving \textit{1st place} on the transfer learning leaderboard in the \textit{Weather4Cast'23 competition}.It not only demonstrates the efficacy of our approaches but also sets a new benchmark for deep learning applications in meteorological forecasting. Our code and weights have been public on \url{https://github.com/Secilia-Cxy/UNetTFI}.