{"@context":{"@vocab":"https://cir.nii.ac.jp/schema/1.0/","rdfs":"http://www.w3.org/2000/01/rdf-schema#","dc":"http://purl.org/dc/elements/1.1/","dcterms":"http://purl.org/dc/terms/","foaf":"http://xmlns.com/foaf/0.1/","prism":"http://prismstandard.org/namespaces/basic/2.0/","cinii":"http://ci.nii.ac.jp/ns/1.0/","datacite":"https://schema.datacite.org/meta/kernel-4/","ndl":"http://ndl.go.jp/dcndl/terms/","jpcoar":"https://github.com/JPCOAR/schema/blob/master/2.0/"},"@id":"https://cir.nii.ac.jp/crid/1360004240187400448.json","@type":"Article","productIdentifier":[{"identifier":{"@type":"DOI","@value":"10.5194/amt-10-4747-2017"}},{"identifier":{"@type":"URI","@value":"https://amt.copernicus.org/articles/10/4747/2017/amt-10-4747-2017.pdf"}}],"resourceType":"学術雑誌論文(journal article)","dc:title":[{"@value":"Feasibility study of multi-pixel retrieval of optical thickness and droplet effective radius of inhomogeneous clouds using deep learning"}],"description":[{"type":"abstract","notation":[{"@value":"<jats:p>Abstract. Three-dimensional (3-D) radiative-transfer effects are a major source of retrieval errors in satellite-based optical remote sensing of clouds. The challenge is that 3-D effects manifest themselves across multiple satellite pixels, which traditional single-pixel approaches cannot capture. In this study, we present two multi-pixel retrieval approaches based on deep learning, a technique that is becoming increasingly successful for complex problems in engineering and other areas. Specifically, we use deep neural networks (DNNs) to obtain multi-pixel estimates of cloud optical thickness and column-mean cloud droplet effective radius from multispectral, multi-pixel radiances. The first DNN method corrects traditional bispectral retrievals based on the plane-parallel homogeneous cloud assumption using the reflectances at the same two wavelengths. The other DNN method uses so-called convolutional layers and retrieves cloud properties directly from the reflectances at four wavelengths. The DNN methods are trained and tested on cloud fields from large-eddy simulations used as input to a 3-D radiative-transfer model to simulate upward radiances. The second DNN-based retrieval, sidestepping the bispectral retrieval step through convolutional layers, is shown to be more accurate. It reduces 3-D radiative-transfer effects that would otherwise affect the radiance values and estimates cloud properties robustly even for optically thick clouds.</jats:p>"}]}],"creator":[{"@id":"https://cir.nii.ac.jp/crid/1380004240187400320","@type":"Researcher","foaf:name":[{"@value":"Rintaro Okamura"}]},{"@id":"https://cir.nii.ac.jp/crid/1380004240187400448","@type":"Researcher","foaf:name":[{"@value":"Hironobu Iwabuchi"}]},{"@id":"https://cir.nii.ac.jp/crid/1380004240187400576","@type":"Researcher","foaf:name":[{"@value":"K. Sebastian Schmidt"}]}],"publication":{"publicationIdentifier":[{"@type":"EISSN","@value":"18678548"}],"prism:publicationName":[{"@value":"Atmospheric Measurement Techniques"}],"dc:publisher":[{"@value":"Copernicus GmbH"}],"prism:publicationDate":"2017-12-05","prism:volume":"10","prism:number":"12","prism:startingPage":"4747","prism:endingPage":"4759"},"reviewed":"false","dcterms:accessRights":"http://purl.org/coar/access_right/c_abf2","dc:rights":["https://creativecommons.org/licenses/by/3.0/"],"url":[{"@id":"https://amt.copernicus.org/articles/10/4747/2017/amt-10-4747-2017.pdf"}],"createdAt":"2017-12-05","modifiedAt":"2025-02-07","foaf:topic":[{"@id":"https://cir.nii.ac.jp/all?q=Earthwork.%20Foundations","dc:title":"Earthwork. Foundations"},{"@id":"https://cir.nii.ac.jp/all?q=TA715-787","dc:title":"TA715-787"},{"@id":"https://cir.nii.ac.jp/all?q=Environmental%20engineering","dc:title":"Environmental engineering"},{"@id":"https://cir.nii.ac.jp/all?q=TA170-171","dc:title":"TA170-171"}],"project":[{"@id":"https://cir.nii.ac.jp/crid/1040282256805991296","@type":"Project","projectIdentifier":[{"@type":"KAKEN","@value":"15H03729"},{"@type":"JGN","@value":"JP15H03729"},{"@type":"URI","@value":"https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-15H03729/"}],"notation":[{"@language":"ja","@value":"マルチスケール大気放射モデルを用いた全球雲解像放射エネルギー収支の定量化"},{"@language":"en","@value":"Quantification of global cloud-resolving radiative energy budget using multi-scale atmospheric radiation model"}]}],"relatedProduct":[{"@id":"https://cir.nii.ac.jp/crid/1050564289060621568","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["references"],"jpcoar:relatedTitle":[{"@language":"en","@value":"Determination of the Optical Thickness and Effective Particle Radius of Clouds from Reflected Solar Radiation Measurements. Part 1: Theory"},{"@value":"Determination of the Optical Thickness and Effective Particle Radius of Clouds from Reflected Solar Radiation Measurements. Part I: Theory"},{"@value":"Determination of optical thickness and effective particle radius of clouds from reflected solar radiation measurements. Part 1: theory"},{"@value":"Determination of the optical thickness and effective particle radius of clouds from reflected solar radiation measurements. Part II: Marine stratocumulus observations"},{"@value":"Determination of the optical thickness and effective particle radius of clouds reflected solar radiation measurements. Part I: theory"}]},{"@id":"https://cir.nii.ac.jp/crid/1360011142936021632","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Algorithms for radiative intensity calculations in moderately thick atmospheres using a truncation approximation"}]},{"@id":"https://cir.nii.ac.jp/crid/1360011142940931072","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"A k-distribution-based radiation code and its computational optimization for an atmospheric general circulation model"}]},{"@id":"https://cir.nii.ac.jp/crid/1360011143733139328","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Neural network retrieval of cloud parameters of inhomogeneous clouds from multispectral and multiscale radiance data: Feasibility study"}]},{"@id":"https://cir.nii.ac.jp/crid/1360022305566000384","@type":"Article","resourceType":"preprint","relationType":["hasPreprint"],"jpcoar:relatedTitle":[{"@value":"Retrieval of optical thickness and droplet effective radius of inhomogeneous clouds using deep learning"}]},{"@id":"https://cir.nii.ac.jp/crid/1360287219306484096","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["isReferencedBy"],"jpcoar:relatedTitle":[{"@value":"Retrieval of Cloud Optical Thickness from Sky-View Camera Images using a Deep Convolutional Neural Network based on Three-Dimensional Radiative Transfer"}]},{"@id":"https://cir.nii.ac.jp/crid/1360292620044061056","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Neural network retrieval of cloud parameters from high-resolution multispectral radiometric data"}]},{"@id":"https://cir.nii.ac.jp/crid/1360292620935751424","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Estimating nocturnal opaque ice cloud optical depth from MODIS multispectral infrared radiances using a neural network method"}]},{"@id":"https://cir.nii.ac.jp/crid/1360292621414101760","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"A multi-spectral non-local method for retrieval of boundary layer cloud properties from optical remote sensing data"}]},{"@id":"https://cir.nii.ac.jp/crid/1360567190140850688","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["isReferencedBy"],"jpcoar:relatedTitle":[{"@value":"Evaluation of Himawari-8 surface downwelling solar radiation by ground-based measurements"}]},{"@id":"https://cir.nii.ac.jp/crid/1360574093636626048","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Influence of grid aspect ratio on planetary boundary layer turbulence in large-eddy simulations"}]},{"@id":"https://cir.nii.ac.jp/crid/1360574094544886784","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Impact of three‐dimensional radiative effects on satellite retrievals of cloud droplet sizes"}]},{"@id":"https://cir.nii.ac.jp/crid/1360574095870272128","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Case study of inhomogeneous cloud parameter retrieval from MODIS data"}]},{"@id":"https://cir.nii.ac.jp/crid/1360855567865740544","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Deep Residual Learning for Image Recognition"}]},{"@id":"https://cir.nii.ac.jp/crid/1360855567870249984","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Matrix formulations for the transfer of solar radiation in a plane-parallel scattering atmosphere"}]},{"@id":"https://cir.nii.ac.jp/crid/1360855569379956096","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Effects of Cloud Heterogeneities on Shortwave Radiation: Comparison of Cloud-Top Variability and Internal Heterogeneity"}]},{"@id":"https://cir.nii.ac.jp/crid/1360855570556892672","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Vertical photon transport in cloud remote sensing problems"}]},{"@id":"https://cir.nii.ac.jp/crid/1361137046282888448","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"A global analysis on the view‐angle dependence of plane‐parallel oceanic liquid water cloud optical thickness using data synergy from MISR and MODIS"}]},{"@id":"https://cir.nii.ac.jp/crid/1361418519993151104","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"A framework based on 2‐D Taylor expansion for quantifying the impacts of subpixel reflectance variance and covariance on cloud optical thickness and effective radius retrievals based on the bispectral method"}]},{"@id":"https://cir.nii.ac.jp/crid/1361981470283268608","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Efficient Monte Carlo Methods for Radiative Transfer Modeling"}]},{"@id":"https://cir.nii.ac.jp/crid/1361981470665447168","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"View‐angle consistency in reflectance, optical thickness and spherical albedo of marine water‐clouds over the northeastern Pacific through MISR‐MODIS fusion"}]},{"@id":"https://cir.nii.ac.jp/crid/1362262945520749056","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Effects of Cloud Horizontal Inhomogeneity on the Optical Thickness Retrieved from Moderate-Resolution Satellite Data"}]},{"@id":"https://cir.nii.ac.jp/crid/1362544418552454912","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"The Effect of Data Pre-processing on Optimized Training of Artificial Neural Networks"}]},{"@id":"https://cir.nii.ac.jp/crid/1362544419238352128","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Effective radiative properties of bounded cascade nonabsorbing clouds: Definition of the equivalent homogeneous cloud approximation"}]},{"@id":"https://cir.nii.ac.jp/crid/1362544420009542144","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Neural network retrieval of cloud parameters of inhomogeneous and fractional clouds"}]},{"@id":"https://cir.nii.ac.jp/crid/1362544420613897472","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"The impact of cloud vertical profile on liquid water path retrieval based on the bispectral method: A theoretical study based on large‐eddy simulations of shallow marine boundary layer clouds"}]},{"@id":"https://cir.nii.ac.jp/crid/1363107369050727424","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Interpretation of Multiwavelength-Retrieved Droplet Effective Radii for Warm Water Clouds in Terms of In-Cloud Vertical Inhomogeneity by Using a Spectral Bin Microphysics Cloud Model"}]},{"@id":"https://cir.nii.ac.jp/crid/1363107370605082752","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"The effect of solar zenith angle on MODIS cloud optical and microphysical retrievals within marine liquid water clouds"}]},{"@id":"https://cir.nii.ac.jp/crid/1363388843598691200","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Observations of Three-Dimensional Radiative Effects that Influence MODIS Cloud Optical Thickness Retrievals"}]},{"@id":"https://cir.nii.ac.jp/crid/1363388843782619520","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"3D Radiative Transfer in Cloudy Atmospheres"}]},{"@id":"https://cir.nii.ac.jp/crid/1363388845164922496","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Effects of cloud horizontal inhomogeneity and drizzle on remote sensing of cloud droplet effective radius: Case studies based on large‐eddy simulations"}]},{"@id":"https://cir.nii.ac.jp/crid/1363670320800471040","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"An assessment of differences between cloud effective particle radius retrievals for marine water clouds from three MODIS spectral bands"}]},{"@id":"https://cir.nii.ac.jp/crid/1363951794194086144","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"The MODIS cloud products: algorithms and examples from terra"}]},{"@id":"https://cir.nii.ac.jp/crid/1363951794265141760","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Droplet Growth in Warm Water Clouds Observed by the A-Train. Part I: Sensitivity Analysis of the MODIS-Derived Cloud Droplet Sizes"}]},{"@id":"https://cir.nii.ac.jp/crid/1363951796297091584","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"The Properties of Atmospheric Aerosol Particles as Functions of the Relative Humidity at Thermodynamic Equilibrium with the Surrounding Moist Air"}]},{"@id":"https://cir.nii.ac.jp/crid/1364233269463757568","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"The Potential for Improved Boundary Layer Cloud Optical Depth Retrievals from the Multiple Directions of MISR"}]},{"@id":"https://cir.nii.ac.jp/crid/1390001205221562624","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["references"],"jpcoar:relatedTitle":[{"@language":"en","@value":"Potential of Retrieving Shallow-Cloud Life Cycle from Future Generation Satellite Observations through Cloud Evolution Diagrams: A Suggestion from a Large Eddy Simulation"},{"@value":"Potential of retrieving shallow-cloud life cycle from future generation satellite observations through cloud evolution diagrams"}]},{"@id":"https://cir.nii.ac.jp/crid/2051996267026447488","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Impacts of cloud microphysics on trade wind cumulus : which cloud microphysics processes contribute to the diversity in a large eddy simulation？"}]}],"dataSourceIdentifier":[{"@type":"CROSSREF","@value":"10.5194/amt-10-4747-2017"},{"@type":"KAKEN","@value":"PRODUCT-21711461"},{"@type":"OPENAIRE","@value":"doi_dedup___::8de44c79c43e6121894b324625cdf01f"},{"@type":"CROSSREF","@value":"10.5194/amt-2017-154_isPreprintOf_DOI_XDIBXnURPGK0UMxSot0Zi3rhQgJ"},{"@type":"CROSSREF","@value":"10.3390/rs11171962_references_DOI_XDIBXnURPGK0UMxSot0Zi3rhQgJ"},{"@type":"CROSSREF","@value":"10.5194/amt-11-2501-2018_references_DOI_XDIBXnURPGK0UMxSot0Zi3rhQgJ"}]}