论文标题
大气对流的生成建模
Generative Modeling for Atmospheric Convection
论文作者
论文摘要
虽然解决云的模型可以明确模拟小规模风暴形成和形态的细节，但由于缺乏计算资源，气候模型通常会忽略这些细节。在这里，我们通过设计和实施差异自动编码器（VAE）来探索生成建模对廉价重现小规模风暴的潜力，该风暴（VAE）执行结构复制，降低尺寸降低以及高分辨率垂直速度场的聚类。 VAE在跨过地球的〜6*10^6个样本上进行了训练，成功地重建了对流的空间结构，对对流组织制度进行了无监督的聚类，并确定了异常的风暴活动，从而确保了在气候模型中发生造成生成建模的潜在，从而使生成模型的动力随机性参数。
While cloud-resolving models can explicitly simulate the details of small-scale storm formation and morphology, these details are often ignored by climate models for lack of computational resources. Here, we explore the potential of generative modeling to cheaply recreate small-scale storms by designing and implementing a Variational Autoencoder (VAE) that performs structural replication, dimensionality reduction, and clustering of high-resolution vertical velocity fields. Trained on ~6*10^6 samples spanning the globe, the VAE successfully reconstructs the spatial structure of convection, performs unsupervised clustering of convective organization regimes, and identifies anomalous storm activity, confirming the potential of generative modeling to power stochastic parameterizations of convection in climate models.
