用多任务扩散模型分解降水图像，提升强降雨预测精度。
Extreme Precipitation Nowcasting using Multi-Task Latent Diffusion Models
- 将雷达图像按降水强度分解建模，分治处理不同强度区域
- 在MRMS数据集上CSI提升13%-26%，显著优于现有方法
- 适合需要高精度短时强降水预报的气象业务与灾害预警场景
深度学习模型在降水预测方面取得了显著进展，但在捕捉雷达图像的空间细节，尤其是高降水强度区域方面仍面临挑战，导致不同降水强度下空间定位精度下降。为解决这一问题，我们提出一种名为多任务潜空间扩散模型（MTLDM）的新方法。其核心思想是：降水雷达图像由不同强度的多个成分组成，因此采用分而治之策略，根据降水强度将雷达图像分解为若干子图像，并分别建模。预测阶段，MTLDM利用训练好的潜空间降水扩散模型整合各子图像表示，再通过多任务解码器生成最终预测结果。在MRMS数据集上的实验表明，所提MTLDM方法超越现有先进技术，关键成功指数（CSI）提升13%-26%。
原文摘要 · Abstract (English)
Deep learning models have achieved remarkable progress in precipitation prediction. However, they still face significant challenges in accurately capturing spatial details of radar images, particularly in regions of high precipitation intensity. This limitation results in reduced spatial localization accuracy when predicting radar echo images across varying precipitation intensities. To address this challenge, we propose an innovative precipitation prediction approach termed the Multi-Task Latent Diffusion Model (MTLDM). The core idea of MTLDM lies in the recognition that precipitation radar images represent a combination of multiple components, each corresponding to different precipitation intensities. Thus, we adopt a divide-and-conquer strategy, decomposing radar images into several sub-images based on their precipitation intensities and individually modeling these components. During the prediction stage, MTLDM integrates these sub-image representations by utilizing a trained latent-space rainfall diffusion model, followed by decoding through a multi-task decoder to produce the final precipitation prediction. Experimental evaluations conducted on the MRMS dataset demonstrate that the proposed MTLDM method surpasses state-of-the-art techniques, achieving a Critical Success Index (CSI) improvement of 13-26%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。