当前位置: X-MOL 学术IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Using Conditional Generative Adversarial 3-D Convolutional Neural Network for Precise Radar Extrapolation
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing ( IF 4.7 ) Pub Date : 2021-05-25 , DOI: 10.1109/jstars.2021.3083647
Cong Wang , Ping Wang , Pingping Wang , Bing Xue , Di Wang

Radar echo extrapolation is a basic but essential task in meteorological services. It could provide radar echo prediction results with high spatiotemporal resolution in a computationally efficient way, and effectively enhance the operational system's forecasting capability for meteorological hazards. Traditional methods perform extrapolation by estimating echo motions between contiguous radar data. This strategy is difficult to characterize complex nonlinear meteorological processes effectively, and it is difficult to benefit from large historical data. Recently, machine learning (ML) models have been used for radar echo extrapolation. These methods have effectively improved extrapolation quality in a data-driven way and from the statistical perspective. Although the ML-based methods show excellent performance, they usually produce blurry extrapolations. This leads to underestimating radar echo intensity and making echo lack small-scale details. Moreover, it makes models difficult to predict severe convective hazards. To solve this problem, a two-stage extrapolation model based on 3-D convolutional neural network and conditional generative adversarial network is proposed. These two models form the “pre-extrapolation” and “postprocessing” paradigm. The pre-extrapolation model is trained in the traditional way and performs rough extrapolation. The postprocessing model uses the pre-extrapolation result as input and is trained with the adversarial strategy. It could correct the echo intensity and increase the echo's details. In the experiment, our model could provide more precise radar echo extrapolations than other methods, especially for intense echoes and convective systems, in the data of North China from 2015 to 2016.

中文翻译:


使用条件生成对抗 3D 卷积神经网络进行精确雷达外推



雷达回波外推是气象服务中一项基本但必不可少的任务。它可以通过计算高效的方式提供高时空分辨率的雷达回波预测结果,有效增强业务系统对气象灾害的预报能力。传统方法通过估计连续雷达数据之间的回波运动来执行外推。该策略难以有效表征复杂的非线性气象过程,也难以从大量历史数据中获益。最近,机器学习(ML)模型已被用于雷达回波外推。这些方法从数据驱动的角度和统计的角度有效地提高了外推质量。尽管基于机器学习的方法表现出出色的性能,但它们通常会产生模糊的外推法。这导致低估雷达回波强度并使回波缺乏小尺度细节。此外,这使得模型难以预测严重的对流灾害。为了解决这个问题,提出了一种基于3D卷积神经网络和条件生成对抗网络的两阶段外推模型。这两个模型形成了“预外推”和“后处理”范式。预外推模型以传统方式训练并进行粗略外推。后处理模型使用预外推结果作为输入,并使用对抗策略进行训练。它可以校正回波强度并增加回波的细节。在实验中,我们的模型可以比其他方法提供更精确的雷达回波外推,特别是对于2015年至2016年华北地区的强回波和对流系统。
更新日期:2021-05-25
down
wechat
bug