{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T13:19:52Z","timestamp":1770815992655,"version":"3.50.1"},"reference-count":52,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2019,8,21]],"date-time":"2019-08-21T00:00:00Z","timestamp":1566345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["Kiban B 17H02963"],"award-info":[{"award-number":["Kiban B 17H02963"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004020","name":"Japan Aerospace Exploration Agency","doi-asserted-by":"publisher","award":["ER2GCF204"],"award-info":[{"award-number":["ER2GCF204"]}],"id":[{"id":"10.13039\/501100004020","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency","doi-asserted-by":"publisher","award":["JPMJCR15K4"],"award-info":[{"award-number":["JPMJCR15K4"]}],"id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>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\u2013100, 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\u2013time averaging method, and the 3D radiative effect.<\/jats:p>","DOI":"10.3390\/rs11171962","type":"journal-article","created":{"date-parts":[[2019,8,21]],"date-time":"2019-08-21T11:19:06Z","timestamp":1566386346000},"page":"1962","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["Retrieval of Cloud Optical Thickness from Sky-View Camera Images using a Deep Convolutional Neural Network based on Three-Dimensional Radiative Transfer"],"prefix":"10.3390","volume":"11","author":[{"given":"Ryosuke","family":"Masuda","sequence":"first","affiliation":[{"name":"Graduate School of Science, Tohoku University, Sendai, Miyagi 980-8578, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9311-8598","authenticated-orcid":false,"given":"Hironobu","family":"Iwabuchi","sequence":"additional","affiliation":[{"name":"Graduate School of Science, Tohoku University, Sendai, Miyagi 980-8578, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3899-228X","authenticated-orcid":false,"given":"Konrad Sebastian","family":"Schmidt","sequence":"additional","affiliation":[{"name":"Department of Atmospheric and Oceanic Sciences, University of Colorado, Boulder, CO 80309-0311, USA"},{"name":"Laboratory for Atmospheric and Space Physics, University of Colorado, Boulder, CO 80303-7814, USA"}]},{"given":"Alessandro","family":"Damiani","sequence":"additional","affiliation":[{"name":"Center for Environmental Remote Sensing, Chiba University, Chiba 263-8522, Japan"}]},{"given":"Rei","family":"Kudo","sequence":"additional","affiliation":[{"name":"Meteorological Research Institute, Japan Meteorological Agency, Tsukuba 305-0052, Japan"}]}],"member":"1968","published-online":{"date-parts":[[2019,8,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2881","DOI":"10.1016\/j.solener.2011.08.025","article-title":"Intra-hour forecasting with a total sky imager at the UC San Diego solar energy testbed","volume":"85","author":"Chow","year":"2011","journal-title":"Sol. Energy"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1911","DOI":"10.1175\/1520-0469(2004)061<1911:TRVNPT>2.0.CO;2","article-title":"The \u201cRED versus NIR\u201d plane to retrieve broken-cloud optical depth from ground-based measurements","volume":"61","author":"Marshak","year":"2004","journal-title":"J. Atmos. Sci."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"14202","DOI":"10.1029\/2009JD013121","article-title":"Cloud optical depth retrievals from the Aerosol Robotic Network (AERONET) cloud mode observations","volume":"115","author":"Chiu","year":"2010","journal-title":"J. Geophys. Res."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"07205","DOI":"10.1029\/2005JD006363","article-title":"Cloud optical thickness and effective particle radius derived from transmitted solar radiation measurements: Comparison with cloud radar observations","volume":"111","author":"Kikuchi","year":"2006","journal-title":"J. Geophys. Res.-Atmos."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"7235","DOI":"10.5194\/acp-11-7235-2011","article-title":"A spectral method for retrieving cloud optical thickness and effective radius from surface-based transmittance measurements","volume":"11","author":"McBride","year":"2011","journal-title":"Atmos. Chem. Phys."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"4167","DOI":"10.5194\/amt-9-4167-2016","article-title":"Application of oxygen A-band equivalent width to disambiguate downwelling radiances for cloud optical depth measurement","volume":"9","author":"Niple","year":"2016","journal-title":"Atmos. Meas. Tech."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"4151","DOI":"10.5194\/amt-9-4151-2016","article-title":"Coupling sky images with radiative transfer models: A new method to estimate cloud optical depth","volume":"9","author":"Mejia","year":"2016","journal-title":"Atmos. Meas. Tech."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2434","DOI":"10.1175\/1520-0469(1994)051<2434:TAOFSC>2.0.CO;2","article-title":"The albedo of fractal stratocumulus clouds","volume":"51","author":"Cahalan","year":"1994","journal-title":"J. Atmos. Sci."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"9387","DOI":"10.1029\/96JD03719","article-title":"Effect of cloud inhomogeneities on the solar zenith angle dependence of nadir reflectance","volume":"102","author":"Loeb","year":"1997","journal-title":"J. Geophys. Res. Atmos."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"4206","DOI":"10.1175\/1520-0469(1999)056<4206:EOCHOS>2.0.CO;2","article-title":"Effects of cloud heterogeneities on shortwave radiation: Comparison of cloud-top variability and internal heterogeneity","volume":"56","author":"Davies","year":"1999","journal-title":"J. Atmos. Sci."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.1175\/1520-0469(2002)059<1607:OOTDRE>2.0.CO;2","article-title":"Observations of three-dimensional radiative effects that influence MODIS cloud optical thickness retrievals","volume":"59","author":"Marshak","year":"2002","journal-title":"J. Atmos. Sci."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"17201","DOI":"10.1029\/2005JD006668","article-title":"Estimate of satellite-derived cloud optical thickness and effective radius errors and their effect on computed domain-averaged irradiances","volume":"111","author":"Kato","year":"2006","journal-title":"J. Geophys. Res. Atmos."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"09207","DOI":"10.1029\/2005JD006686","article-title":"Impact of three-dimensional radiative effects on satellite retrievals of cloud droplet sizes","volume":"111","author":"Marshak","year":"2006","journal-title":"J. Geophys. Res. Atmos."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1016\/j.rse.2003.08.005","article-title":"A multi-spectral non-local method for retrieval of boundary layer cloud properties from optical remote sensing data","volume":"88","author":"Iwabuchi","year":"2003","journal-title":"Remote Sens. Environ."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1016\/S0034-4257(01)00199-7","article-title":"Neural network retrieval of cloud parameters of inhomogeneous and fractional clouds: Feasibility study","volume":"77","author":"Faure","year":"2001","journal-title":"Remote Sens. Environ."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1016\/S0034-4257(01)00310-8","article-title":"Neural network retrieval of cloud parameters from high-resolution multispectral radiometric data: A feasibility study","volume":"80","author":"Faure","year":"2002","journal-title":"Remote Sens. Environ."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"12203","DOI":"10.1029\/2003JD004186","article-title":"Neural network retrieval of cloud parameters of inhomogeneous clouds from multispectral and multiscale radiance data: Feasibility study","volume":"109","author":"Cornet","year":"2004","journal-title":"J. Geophys. Res. Atmos."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"13807","DOI":"10.1029\/2005GL022791","article-title":"Case study of inhomogeneous cloud parameter retrieval from MODIS data","volume":"32","author":"Cornet","year":"2005","journal-title":"Geophys. Res. Lett."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"3179","DOI":"10.1175\/2008JAS2627.1","article-title":"The potential for improved boundary layer cloud optical depth retrievals from the multiple directions of MISR","volume":"65","author":"Evans","year":"2008","journal-title":"J. Atmos. Sci."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"4747","DOI":"10.5194\/amt-10-4747-2017","article-title":"Feasibility study of multi-pixel retrieval of optical thickness and droplet effective radius of inhomogeneous clouds using deep learning","volume":"10","author":"Okamura","year":"2017","journal-title":"Atmos. Meas. Tech."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.atmosres.2017.05.008","article-title":"Effective cloud optical depth and enhancement effects for broken liquid water clouds in Valencia (Spain)","volume":"195","author":"Serrano","year":"2017","journal-title":"Atmos. Res."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"10912","DOI":"10.1002\/2014JD021742","article-title":"A novel ensemble method for retrieving properties of warm cloud in 3-D using ground-based scanning radar and zenith radiances","volume":"119","author":"Fielding","year":"2014","journal-title":"J. Geophys. Res. Atmos."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Levis, A., Schechner, Y., and Aides, A. (2015, January 7\u201313). Airborne Three-Dimensional Cloud Tomography. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.386"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Levis, A., Schechner, Y.Y., and Davis, A.B. (2017, January 21\u201326). Multiple-scattering Microphysics Tomography. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.614"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Holodovsky, V., Schechner, Y.Y., Levin, A., Levis, A., and Aides, A. (2016, January 13\u201315). In-situ Multi-view Multi-scattering Stochastic Tomography. Proceedings of the 2016 IEEE International Conference on Computational Photography (ICCP), Evanston, IL, USA.","DOI":"10.1109\/ICCPHOT.2016.7492869"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/j.jqsrt.2017.09.031","article-title":"A demonstration of adjoint methods for multi-dimensional remote sensing of the atmosphere and surface","volume":"204","author":"Martin","year":"2018","journal-title":"J. Quant. Spectrosc. Radiat. Transf."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1016\/j.solener.2018.10.023","article-title":"Cloud tomography applied to sky images: A virtual testbed","volume":"176","author":"Mejia","year":"2018","journal-title":"Sol. Energy"},{"key":"ref_28","first-page":"10","article-title":"Potential of retrieving shallow-cloud life cycle from future generation satellite observations through cloud evolution diagrams: A suggestion from a large eddy simulation","volume":"10","author":"Sato","year":"2014","journal-title":"Sci. Online Lett. Atmos."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1186\/s40645-015-0053-6","article-title":"Impacts of cloud microphysics on trade wind cumulus: Which cloud microphysics processes contribute to the diversity in a large eddy simulation?","volume":"2","author":"Sato","year":"2015","journal-title":"Prog. Earth Planet. Sci."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"3393","DOI":"10.5194\/gmd-8-3393-2015","article-title":"Influence of grid aspect ratio on planetary boundary layer turbulence in large-eddy simulations","volume":"8","author":"Nishizawa","year":"2015","journal-title":"Geosci. Model Dev."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"2324","DOI":"10.1175\/JAS3755.1","article-title":"Efficient Monte Carlo methods for radiative transfer modeling","volume":"63","author":"Iwabuchi","year":"2006","journal-title":"J. Atmos. Sci."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/j.jqsrt.2017.01.025","article-title":"Multispectral Monte Carlo radiative transfer simulation by the maximum cross-section method","volume":"193","author":"Iwabuchi","year":"2017","journal-title":"J. Quant. Spectrosc. Radiat. Transf."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1016\/S0065-2687(08)60142-9","article-title":"The properties of atmospheric aerosol particles as functions of the relative humidity at thermodynamic equilibrium with the surrounding moist air","volume":"19","year":"1976","journal-title":"Adv. Geophys."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., and Jia, J. (2017, January 21\u201326). Pyramid Scene Parsing Network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016). Identity Mappings in Deep Residual Networks. European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., and Komodakis, N. (2016, January 19\u201322). Wide Residual Networks. Proceedings of the British Machine Vision Conference (BMVC), York, UK.","DOI":"10.5244\/C.30.87"},{"key":"ref_38","unstructured":"Ioffe, S., and Szegedy, C. (2015, January 7\u20139). Batch Normalization Accelerating Deep Network Training by Reducing Internal Covariate Shift. Proceedings of the 32nd International Conference on Machine Learning, Lille, France."},{"key":"ref_39","unstructured":"Goodfellow, I.J., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press."},{"key":"ref_40","unstructured":"Kingma, D.P., and Ba, J. (2015, January 7\u20139). Adam: A Method for Stochastic Optimization CoRR, abs\/1412.6980. Proceedings of the 3rd International Conference on Learning Representations (ICLR 2015), San Diego, CA, USA."},{"key":"ref_41","unstructured":"Tokui, S., Oono, K., Hido, S., and Clayton, J. (2015, January 7\u201312). Chainer: A Next-generation Open Source Framework for Deep Learning. Proceedings of the Workshop on Machine Learning Systems (LearningSys) in the Twenty-Ninth Annual Conference on Neural Information Processing Systems (NIPS), Montreal CANADA ."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Marshak, A., and Davis, A. (2005). 3D Radiative Transfer in Cloudy Atmospheres, Springer Science Business Media.","DOI":"10.1007\/3-540-28519-9"},{"key":"ref_43","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., and Yuille, A.L. (2015, January 7\u20139). Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs. Proceedings of the International Conference Learning Representations, San Diego, CA, USA."},{"key":"ref_44","unstructured":"Yu, F., and Koltun, V. (2016, January 2\u20134). Multi-scale Context Aggregation by Dilated convolutions. Proceedings of the International Conference Learning Representations, San Juan, PR, USA."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Yu, F., Koltun, V., and Funkhouser, T. (2017, January 21\u201326). Dilated residual networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.75"},{"key":"ref_46","unstructured":"Loshchilov, I., and Hutter, F. (May, January 30). Fixing weight decay regularization in Adam, CoRR, abs\/1711.05101. Proceedings of the ICLR 2018 Conference Blind Submission, Vancouver, BC, Canada."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"4615","DOI":"10.5194\/amt-9-4615-2016","article-title":"Ground-based imaging remote sensing of ice clouds: Uncertainties caused by sensor, method and atmosphere","volume":"9","author":"Zinner","year":"2016","journal-title":"Atmos. Meas. Tech."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1364\/AO.55.000415","article-title":"Estimation of spectral distribution of sky radiance using a commercial digital camera","volume":"55","author":"Saito","year":"2016","journal-title":"Appl. Opt."},{"key":"ref_49","first-page":"190","article-title":"An intensive campaign-based intercomparison of cloud optical depth from ground and satellite instruments under overcast conditions","volume":"15","author":"Damiani","year":"2019","journal-title":"Sci. Online Lett. Atmos."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"3939","DOI":"10.1002\/joc.3953","article-title":"Effective cloud optical depth for overcast conditions determined with a UV radiometers","volume":"34","author":"Serrano","year":"2014","journal-title":"Int. J. Climatol."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"2501","DOI":"10.5194\/amt-11-2501-2018","article-title":"Evaluation of Himawari-8 surface downwelling solar radiation by ground-based measurements","volume":"11","author":"Damiani","year":"2018","journal-title":"Atmos. Meas. Tech."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"2898","DOI":"10.1002\/2016JD025384","article-title":"High-resolution photography of clouds from the surface: Retrieval of optical depth of thin clouds down to centimeter scales","volume":"122","author":"Schwartz","year":"2017","journal-title":"J. Geophys. Res. Atmos."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/11\/17\/1962\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T13:12:43Z","timestamp":1760188363000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/11\/17\/1962"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8,21]]},"references-count":52,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2019,9]]}},"alternative-id":["rs11171962"],"URL":"https:\/\/doi.org\/10.3390\/rs11171962","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,8,21]]}}}