Articles | Volume 15, issue 17
Research article
14 Sep 2022
Research article |  | 14 Sep 2022

Segmentation-based multi-pixel cloud optical thickness retrieval using a convolutional neural network

Vikas Nataraja, Sebastian Schmidt, Hong Chen, Takanobu Yamaguchi, Jan Kazil, Graham Feingold, Kevin Wolf, and Hironobu Iwabuchi

Related authors

The Education and Research 3D Radiative Transfer Toolbox (EaR3T) – towards the mitigation of 3D bias in airborne and spaceborne passive imagery cloud retrievals
Hong Chen, K. Sebastian Schmidt, Steven T. Massie, Vikas Nataraja, Matthew S. Norgren, Jake J. Gristey, Graham Feingold, Robert E. Holz, and Hironobu Iwabuchi
Atmos. Meas. Tech., 16, 1971–2000,,, 2023
Short summary

Related subject area

Subject: Clouds | Technique: Remote Sensing | Topic: Data Processing and Information Retrieval
Retrieval of surface solar irradiance from satellite imagery using machine learning: pitfalls and perspectives
Hadrien Verbois, Yves-Marie Saint-Drenan, Vadim Becquet, Benoit Gschwind, and Philippe Blanc
Atmos. Meas. Tech., 16, 4165–4181,,, 2023
Short summary
Retrieving 3D distributions of atmospheric particles using Atmospheric Tomography with 3D Radiative Transfer – Part 2: Local optimization
Jesse Loveridge, Aviad Levis, Larry Di Girolamo, Vadim Holodovsky, Linda Forster, Anthony B. Davis, and Yoav Y. Schechner
Atmos. Meas. Tech., 16, 3931–3957,,, 2023
Short summary
Particle inertial effects on radar Doppler spectra simulation
Zeen Zhu, Pavlos Kollias, and Fan Yang
Atmos. Meas. Tech., 16, 3727–3737,,, 2023
Short summary
Detection of aerosol and cloud features for the EarthCARE atmospheric lidar (ATLID): the ATLID FeatureMask (A-FM) product
Gerd-Jan van Zadelhoff, David P. Donovan, and Ping Wang
Atmos. Meas. Tech., 16, 3631–3651,,, 2023
Short summary
A unified synergistic retrieval of clouds, aerosols, and precipitation from EarthCARE: the ACM-CAP product
Shannon L. Mason, Robin J. Hogan, Alessio Bozzo, and Nicola L. Pounder
Atmos. Meas. Tech., 16, 3459–3486,,, 2023
Short summary

Cited articles

Abel, S. J., Barrett, P. A., Zuidema, P., Zhang, J., Christensen, M., Peers, F., Taylor, J. W., Crawford, I., Bower, K. N., and Flynn, M.: Open cells exhibit weaker entrainment of free-tropospheric biomass burning aerosol into the south-east Atlantic boundary layer, Atmos. Chem. Phys., 20, 4059–4084,, 2020. a
Anderson, G. P., Clough, S. A., Kneizys, F., Chetwynd, J. H., and Shettle, E. P.: AFGL atmospheric constituent profiles (0.120 km), Tech. rep., AIR FORCE GEOPHYSICS LAB HANSCOM AFB MA, 1986. a
Barker, H. W. and Liu, D.: Inferring optical depth of broken clouds from Landsat data, J. climate, 8, 2620–2630,<2620:IODOBC>2.0.CO;2, 1995. a
Bodhaine, B. A., Wood, N. B., Dutton, E. G., and Slusser, J. R.: On Rayleigh optical depth calculations, J. Atmos. Ocean. Technol., 16, 1854–1861,<1854:ORODC>2.0.CO;2, 1999. a
Cahalan, R. F.: Bounded cascade clouds: albedo and effective thickness, Nonlin. Processes Geophys., 1, 156–167,, 1994. a
Short summary
A convolutional neural network (CNN) is introduced to retrieve cloud optical thickness (COT) from passive cloud imagery. The CNN, trained on large eddy simulations from the Sulu Sea, learns from spatial information at multiple scales to reduce cloud inhomogeneity effects. By considering the spatial context of a pixel, the CNN outperforms the traditional independent pixel approximation (IPA) across several cloud morphology metrics.