近日，广州热带海洋气象研究所冯业荣及其课题组的最新研究提出了基于深度学习的掩模方法，以改进数值天气预报中的短时降水预测。相关论文发表在2023年12月8日出版的《大气科学进展》杂志上。

为了纠正数值天气预报模型的偏差并提高短期降雨预测的准确性，研究人员提出了一种基于深度学习的方法，称为 UNetMask，该方法将数值天气预测与卷积神经网络 UNet 的输出相结合。UNetMask 基于数值天气预报模式的历史数据对 UNet 进行校准，提供 6 小时降雨预报的网格化降水观测数据。在相同的降雨阈值下，UNet 输出和数值天气预报的重叠处产生了一个掩模。UNetMask 将 UNet 输出和数值天气预报混合，取两者之间的最大值，从而提供校正后的 6 小时降雨量预报。

研究在测试集和实时验证中评估了 UNetMask。结果表明，UNetMask 通过降低 FAR 和提高 CSI 得分，在 6 小时降水预测中优于数值天气预报模型。敏感性试验还表明，应用于 UNet 和数值天气预报模式不同的小降雨阈值对 UNetMask 的预报性能有不同的影响。研究结果强调，UNetMask 是一种很有前景的方法，可以改善数值天气预报模型的降雨预报。

据介绍，由于各种技术问题，现有的数值天气预报(NWP)模式在预报最初几小时的降雨量时往往存在误差。

附：英文原文

Title: Improving Short-Range Precipitation Forecast of Numerical Weather Prediction Through a Deep Learning-Based Mask Approach

Author: Jiaqi Zheng, Qing Ling, Jia Li, Yerong Feng

Issue&Volume: 2023-12-08

Abstract: Due to various technical issues, existing numerical weather prediction (NWP) models often perform poorly at forecasting rainfall in the first several hours. To correct the bias of an NWP model and improve the accuracy of short-range precipitation forecasting, we propose a deep learning-based approach called UNetMask, which combines the NWP forecasts with the output of a convolutional neural network called UNet. The UNetMask involves training the UNet on historical data from the NWP model and gridded rainfall observations for 6-hour precipitation forecasting. The overlap of the UNet output and the NWP forecasts at the same rainfall threshold yields a mask. UNetMask blends the UNet output and the NWP forecasts by taking the maximum between them and passing through the mask, which provides the corrected 6-hour rainfall forecasts. We evaluated UNetMask on a test set and in real-time verification. The results showed that UNetMask outperforms the NWP model in 6-hour precipitation prediction by reducing FAR and improving CSI scores. Sensitivity tests also showed that different small rainfall thresholds applied to the UNet and the NWP model have different effect on UNetMask's forecast performance. This study shows that UNetMask is a promising approach for improving rainfall forecasting of NWP models.

DOI: 10.1007/s00376-023-3085-7

Source: http://www.iapjournals.ac.cn/aas/en/article/doi/10.1007/s00376-023-3085-7viewType=HTML