Next Article in Journal
Broad Area Target Search System for Ship Detection via Deep Convolutional Neural Network
Next Article in Special Issue
Three Dimensional Radiative Effects in Passive Millimeter/Sub-Millimeter All-sky Observations
Previous Article in Journal
From BIM to Scan Planning and Optimization for Construction Control
Article

Retrieval of Cloud Optical Thickness from Sky-View Camera Images using a Deep Convolutional Neural Network based on Three-Dimensional Radiative Transfer

1
Graduate School of Science, Tohoku University, Sendai, Miyagi 980-8578, Japan
2
Department of Atmospheric and Oceanic Sciences, University of Colorado, Boulder, CO 80309-0311, USA
3
Laboratory for Atmospheric and Space Physics, University of Colorado, Boulder, CO 80303-7814, USA
4
Center for Environmental Remote Sensing, Chiba University, Chiba 263-8522, Japan
5
Meteorological Research Institute, Japan Meteorological Agency, Tsukuba 305-0052, Japan
*
Author to whom correspondence should be addressed.
Remote Sens. 2019, 11(17), 1962; https://doi.org/10.3390/rs11171962
Received: 2 July 2019 / Revised: 13 August 2019 / Accepted: 17 August 2019 / Published: 21 August 2019
Observation of the spatial distribution of cloud optical thickness (COT) is useful for the prediction and diagnosis of photovoltaic power generation. However, there is not a one-to-one relationship between transmitted radiance and COT (so-called COT ambiguity), and it is difficult to estimate COT because of three-dimensional (3D) radiative transfer effects. We propose a method to train a convolutional neural network (CNN) based on a 3D radiative transfer model, which enables the quick estimation of the slant-column COT (SCOT) distribution from the image of a ground-mounted radiometrically calibrated digital camera. The CNN retrieves the SCOT spatial distribution using spectral features and spatial contexts. An evaluation of the method using synthetic data shows a high accuracy with a mean absolute percentage error of 18% in the SCOT range of 1–100, greatly reducing the influence of the 3D radiative effect. As an initial analysis result, COT is estimated from a sky image taken by a digital camera, and a high correlation is shown with the effective COT estimated using a pyranometer. The discrepancy between the two is reasonable, considering the difference in the size of the field of view, the space–time averaging method, and the 3D radiative effect. View Full-Text
Keywords: deep learning; cloud; 3D radiative transfer; sky-view camera; convolutional neural network deep learning; cloud; 3D radiative transfer; sky-view camera; convolutional neural network
Show Figures

Graphical abstract

MDPI and ACS Style

Masuda, R.; Iwabuchi, H.; Schmidt, K.S.; Damiani, A.; Kudo, R. Retrieval of Cloud Optical Thickness from Sky-View Camera Images using a Deep Convolutional Neural Network based on Three-Dimensional Radiative Transfer. Remote Sens. 2019, 11, 1962. https://doi.org/10.3390/rs11171962

AMA Style

Masuda R, Iwabuchi H, Schmidt KS, Damiani A, Kudo R. Retrieval of Cloud Optical Thickness from Sky-View Camera Images using a Deep Convolutional Neural Network based on Three-Dimensional Radiative Transfer. Remote Sensing. 2019; 11(17):1962. https://doi.org/10.3390/rs11171962

Chicago/Turabian Style

Masuda, Ryosuke; Iwabuchi, Hironobu; Schmidt, Konrad S.; Damiani, Alessandro; Kudo, Rei. 2019. "Retrieval of Cloud Optical Thickness from Sky-View Camera Images using a Deep Convolutional Neural Network based on Three-Dimensional Radiative Transfer" Remote Sens. 11, no. 17: 1962. https://doi.org/10.3390/rs11171962

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop