MAD-SmaAt-GNet：一种多模态输运引导的神经网络用于降水nowcasting
MAD-SmaAt-GNet: A Multimodal Advection-Guided Neural Network for Precipitation Nowcasting
AI总结：
MAD-SmaAt-GNet通过多模态输入和物理输运组件提升降水nowcasting的准确性与效率
摘要：
降水nowcasting（短期预测）仍然常常使用数值求解器来求解物理方程，这计算成本高且对可用的大量天气数据利用有限。深度学习模型在降水nowcasting中展现出强大潜力，既具有准确性又具有计算效率。在这些模型中，卷积神经网络（CNNs）特别有效于图像到图像的预测任务。SmaAt-UNet是一种轻量级的CNN基础架构，已在降水nowcasting中表现出色。本文介绍了多模态输运引导的小注意力GNet（MAD-SmaAt-GNet），它在核心SmaAt-UNet的基础上进行了扩展，（i）加入了额外的编码器来学习多种天气变量，（ii）集成了基于物理的输运组件以确保预测的一致性。我们证明了每个扩展单独改善降雨预测，并且它们的结合带来了进一步的提升。MAD-SmaAt-GNet在四步降水预测中，相比基线SmaAt-UNet将均方误差（MSE）减少了8.9%，在四小时前的预测中。此外，实验表明，多模态输入对短预报时间特别有益，而基于输运的组件在短和长预报时间范围内都提高了性能。
英文摘要：
Precipitation nowcasting (short-term forecasting) is still often performed using numerical solvers for physical equations, which are computationally expensive and make limited use of the large volumes of available weather data. Deep learning models have shown strong potential for precipitation nowcasting, offering both accuracy and computational efficiency. Among these models, convolutional neural networks (CNNs) are particularly effective for image-to-image prediction tasks. The SmaAt-UNet is a lightweight CNN based architecture that has demonstrated strong performance for precipitation nowcasting. This paper introduces the Multimodal Advection-Guided Small Attention GNet (MAD-SmaAt-GNet), which extends the core SmaAt-UNet by (i) incorporating an additional encoder to learn from multiple weather variables and (ii) integrating a physics-based advection component to ensure physically consistent predictions. We show that each extension individually improves rainfall forecasts and that their combination yields further gains. MAD-SmaAt-GNet reduces the mean squared error (MSE) by 8.9% compared with the baseline SmaAt-UNet for four-step precipitation forecasting up to four hours ahead. Additionally, experiments indicate that multimodal inputs are particularly beneficial for short lead times, while the advection-based component enhances performance across both short and long forecasting horizons.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
