用轴向注意力UNet模型，实现高精度短时降雨预报。
Axial-UNet: A Neural Weather Model for Precipitation Nowcasting
- 引入轴向注意力机制，捕捉雷达图像的长程空间依赖。
- 在港科大7号雷达数据集上达到PSNR 47.67、SSIM 0.9943。
- 轻量高效，适合实时低算力场景下的降雨预测。
准确预测短时降水对灾害管理、航空和城市规划至关重要。传统数值天气预报在高分辨率和短预报时效下计算成本高昂。本文提出一种基于UNet的轻量级编码器-解码器架构，引入轴向注意力模块，沿图像行和列方向建模长程空间依赖，同时通过多帧历史雷达图提供时间上下文。该混合结构可有效捕获雷达序列中的局部与长程时空依赖，实现固定预报时长的短时降雨预测，且计算开销小。在预处理后的HKO-7雷达数据集上的实验表明，该模型在像素级保真度指标上优于ConvLSTM、pix2pix风格cGAN和普通UNet，达到PSNR 47.67和SSIM 0.9943。未来工作将扩展至气象学相关评估指标（如CSI/FSS）。该方法简单、可扩展，适用于资源受限的实时预报场景。
原文摘要 · Abstract (English)
Accurately predicting short-term precipitation is critical for weather-sensitive applications such as disaster management, aviation, and urban planning. Traditional numerical weather prediction can be computationally intensive at high resolution and short lead times. In this work, we propose a lightweight UNet-based encoder-decoder augmented with axial-attention blocks that attend along image rows and columns to capture long-range spatial interactions, while temporal context is provided by conditioning on multiple past radar frames. Our hybrid architecture captures both local and long-range spatio-temporal dependencies from radar image sequences, enabling fixed lead-time precipitation nowcasting with modest compute. Experimental results on a preprocessed subset of the HKO-7 radar dataset demonstrate that our model outperforms ConvLSTM, pix2pix-style cGANs, and a plain UNet in pixel-fidelity metrics, reaching PSNR 47.67 and SSIM 0.9943. We report PSNR/SSIM here; extending evaluation to meteorology-oriented skill measures (e.g., CSI/FSS) is left to future work. The approach is simple, scalable, and effective for resource-constrained, real-time forecasting scenarios.
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。