Diagnosing Storm Mode with Deep Learning in Convection-Allowing Models
Diagnosing Storm Mode with Deep Learning in Convection-Allowing Models
复制标题
利用允许对流模型中的深度学习诊断风暴模式
DOI：
10.1175/mwr-d-22-0342.1
复制
发表时间：
2023
影响因子：
3.2
通讯作者：
Schwartz, Craig S.
中科院分区：
文献类型：
--
作者：
Sobash, Ryan A.;Gagne, David John;Becker, Charlie L.;Ahijevych, David;Gantos, Gabrielle N.;Schwartz, Craig S.
虽然对流允许模式（CAM）输出中明确描述了对流风暴模式，但在大量CAM预报中主观诊断模式可能是繁重的。在这项工作中，训练了四个机器学习（ML）模型，以概率将CAM风暴分类为三种模式之一：超级单体、准线性对流系统和无组织对流。这四种ML模型包括密集神经网络（DNN）、逻辑回归（LR）、卷积神经网络（CNN）和半监督CNN -高斯混合模型（GMM）。DNN、CNN和LR使用一组手工标记的CAM风暴进行训练，而半监督的GMM使用上升气流螺旋度和风暴大小来生成集群，然后手工标记。当使用未训练的风暴进行评估时，四种分类器在模式之间具有相似的区分能力，但GMM的校准较差。DNN和LR具有与CNN相似的客观性能，这表明基于CNN的方法可能不需要模式分类任务。所有四种分类器的模式分类成功地近似于美国已知的模式气候学，包括美国中部平原超级单体发生的最大值。此外，这些模式也发生在被认为支持三种不同风暴形态的环境中。最后，风暴模式提供了关于危险类型的有用信息，例如，风暴报告最有可能与超级单体一起，进一步支持分类器的有效性。未来的应用，包括在ML系统中使用客观CAM模式分类作为一种新的预测器，可能会提高对流危害的预测。意义声明雷暴是否会产生龙卷风、冰雹或强阵风等危险，部分取决于风暴是形成单个单体还是形成一条线。数值预报模型现在可以提供描述这种结构的预报。我们测试了几种自动算法，使用机器学习从预测输出中提取这些信息。所有的自动化方法都能够区分一组三种对流类型，与复杂的方法相比，简单的技术提供了类似的熟练分类。自动分类还成功地区分了雷暴灾害，可能会带来新的预报工具和更好的高影响对流灾害预报。
While convective storm mode is explicitly depicted in convection-allowing model (CAM) output, subjectively diagnosing mode in large volumes of CAM forecasts can be burdensome. In this work, four machine learning (ML) models were trained to probabilistically classify CAM storms into one of three modes: supercells, quasi-linear convective systems, and disorganized convection. The four ML models included a dense neural network (DNN), logistic regression (LR), a convolutional neural network (CNN), and semisupervised CNN–Gaussian mixture model (GMM). The DNN, CNN, and LR were trained with a set of hand-labeled CAM storms, while the semisupervised GMM used updraft helicity and storm size to generate clusters, which were then hand labeled. When evaluated using storms withheld from training, the four classifiers had similar ability to discriminate between modes, but the GMM had worse calibration. The DNN and LR had similar objective performance to the CNN, suggesting that CNN-based methods may not be needed for mode classification tasks. The mode classifications from all four classifiers successfully approximated the known climatology of modes in the United States, including a maximum in supercell occurrence in the U.S. Central Plains. Further, the modes also occurred in environments recognized to support the three different storm morphologies. Finally, storm mode provided useful information about hazard type, e.g., storm reports were most likely with supercells, further supporting the efficacy of the classifiers. Future applications, including the use of objective CAM mode classifications as a novel predictor in ML systems, could potentially lead to improved forecasts of convective hazards.Significance StatementWhether a thunderstorm produces hazards such as tornadoes, hail, or intense wind gusts is in part determined by whether the storm takes the form of a single cell or a line. Numerical forecasting models can now provide forecasts that depict this structure. We tested several automated algorithms to extract this information from forecast output using machine learning. All of the automated methods were able to distinguish between a set of three convective types, with the simple techniques providing similarly skilled classifications compared to the complex approaches. The automated classifications also successfully discriminated between thunderstorm hazards, potentially leading to new forecast tools and better forecasts of high-impact convective hazards.