Data-Driven Cloud Clustering via a Rotationally Invariant Autoencoder
Data-Driven Cloud Clustering via a Rotationally Invariant Autoencoder
复制标题
DOI：
10.1109/tgrs.2021.3098008
复制
发表时间：
2021-07-26
影响因子：
8.2
通讯作者：
Foster, Ian
中科院分区：
文献类型：
--
作者：
Kurihana, Takuya;Moyer, Elisabeth;Foster, Ian
先进的星载遥感仪器每天都能产生地球仪大部分地区的高分辨率多光谱数据。这些数据集为更好地理解云动力学和反馈提供了可能性，而云动力学和反馈仍然是全球气候模型预测中最大的不确定性来源。作为回答这些问题的一步，我们描述了一种自动旋转不变云聚类（RICC）方法，该方法利用深度学习自动编码器技术以无监督的方式组织大型数据集中的云图像，不需要对预定义的类进行假设。我们描述了该方法的设计和实现及其评估，该方法使用一系列测试协议来确定所得到的集群是否：1）物理上合理（即，体现科学相关的区别）; 2）捕获有关空间分布的信息，例如纹理; 3）在潜在空间中是内聚的和可分离的;以及4）是旋转不变的（即，对图像的取向不敏感）。当这些评估协议被应用到RICC的输出结果表明，由此产生的新的云团捕获云物理学的有意义的方面，适当的空间相干，是不变的输入图像的方向。我们的研究结果支持使用无监督的数据驱动的方法在云图像中进行自动聚类和模式发现的可能性。
Advanced satellite-borne remote sensing instruments produce high-resolution multispectral data for much of the globe at a daily cadence. These datasets open up the possibility of improved understanding of cloud dynamics and feedback, which remain the biggest source of uncertainty in global climate model projections. As a step toward answering these questions, we describe an automated rotation-invariant cloud clustering (RICC) method that leverages deep learning autoencoder technology to organize cloud imagery within large datasets in an unsupervised fashion, free from assumptions about predefined classes. We describe both the design and implementation of this method and its evaluation, which uses a sequence of testing protocols to determine whether the resulting clusters: 1) are physically reasonable (i.e., embody scientifically relevant distinctions); 2) capture information on spatial distributions, such as textures; 3) are cohesive and separable in latent space; and 4) are rotationally invariant (i.e., insensitive to the orientation of an image). Results obtained when these evaluation protocols are applied to RICC outputs suggest that the resultant novel cloud clusters capture meaningful aspects of cloud physics, are appropriately spatially coherent, and are invariant to orientations of input images. Our results support the possibility of using an unsupervised data-driven approach for automated clustering and pattern discovery in cloud imagery.