Reconstruction of Cloud Vertical Structure With a Generative Adversarial Network

Abstract

We demonstrate the feasibility of solving atmospheric remote sensing problems with machine learning using conditional generative adversarial networks (CGANs), implemented using convolutional neural networks. We apply the CGAN to generating two‐dimensional cloud vertical structures that would be observed by the CloudSat satellite‐based radar, using only the collocated Moderate‐Resolution Imaging Spectrometer measurements as input. The CGAN is usually able to generate reasonable guesses of the cloud structure and can infer complex structures such as multilayer clouds from the Moderate‐Resolution Imaging Spectrometer data. This network, which is formulated probabilistically, also estimates the uncertainty of its own predictions. We examine the statistics of the generated data and analyze the response of the network to each input parameter. The success of the CGAN in solving this problem suggests that generative adversarial networks are applicable to a wide range of problems in atmospheric science, a field characterized by complex spatial structures and observational uncertainties.

Stochastic Super-Resolution for Downscaling Time-Evolving Atmospheric Fields With a Generative Adversarial Network

“…GANs offer a natural way to model uncertainty using modern machine-learning methods, less dependent on particular statistical assumptions than the traditional methods. Regardless, the uncertainty aspect has been largely ignored in earlier attempts at improving the resolution of climate fields using deep learning even when employing GANs for this problem [16] or for other super-resolution applications related to climate or remote sensing [17]- [19] although a few studies have used GANs to represent uncertainty in other atmospheric data problems [20], [21]. Moreover, while GANs have been recently also used to model the time evolution of atmospheric fields [22], few studies using deep learning have investigated modeling the uncertainty of the generated high-resolution image in a manner consistent with the time evolution of atmospheric fields-a problem analogous to video super-resolution, which has also been studied using GANs [23], [24].…”

Unsupervised classification of snowflake images using a generative adversarial network and <i>K</i>-medoids classification

“…The computer processing of the image data is not straightforward because much of the information is provided by shape and the surface texture of the snowflake. Feind (2006) and Lindqvist et al (2012), among others, previously developed algorithms to classify ice crystals based on images from airborne probes. To enable large-scale analysis of microphysics from MASC data, Praz et al (2017, hereafter P17) introduced a machine-learning-based classification algorithm that uses features extracted from the images with image-processing software, providing information about the size, shape and surface patterns of each snowflake.…”

Leveraging spatial textures, through machine learning, to identify aerosols and distinct cloud types from multispectral observations

“…strated improvements upon current methodologies in atmospheric science. For example, neural networks have been employed to (1) approximate computationally demanding radiative transfer models to decrease computation time (Boukabara et al, 2019;Blackwell, 2005;Takenaka et al, 2011), (2) infer tropical cyclone intensity from microwave imagery (Wimmers et al, 2019), (3) infer cloud vertical structures and cirrus or high-altitude cloud optical depths from MODIS imagery (Leinonen et al, 2019;Minnis et al, 2016), and (4) predict the formation of large hailstones from land-based radar imagery (Gagne et al, 2019). Specific to cloud and volcanic ash detection from radiometer images, Bayesian inference has been employed where the posterior distribution functions were empirically generated using hand-labeled (Pavolonis et al, 2015) or coincident Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP) observations (Heidinger et al, 2016(Heidinger et al, , 2012 or from a scientific product (Merchant et al, 2005).…”