Neural network retrieval of cloud parameters of inhomogeneous and fractional clouds

Faure, Thierry; Isaka, Harumi; Guillemet, B.

doi:10.1016/s0034-4257(01)00199-7

Cited by 43 publications

(37 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, a few studies have already applied such applications to the problem of 3-D clouds. Faure et al (2001) demonstrated the feasibility of NNs to retrieve mean optical thickness, mean effective radius, fractional cloud cover, and subpixelscale cloud inhomogeneity from multispectral radiance data at wavelengths of 0.64, 1.6, 2.2, and 3.7 µm for a pixel resolution of 0.8 km × 0.8 km. Faure et al (2002) improved NN cloud property retrievals of one-dimensional inhomogeneous clouds by considering multispectral radiance (at 0.64, 1.6, 2.2, and 3.7 µm) from a collection of pixels adjacent to the pixel of interest.…”

Section: Introductionmentioning

confidence: 95%

“…As NN inputs, we use the radiances at four wavelengths (0.86, 1.64, 2.13, and 3.75 µm) at the target pixel and eight adjacent pixels. As in Faure et al (2001), the outputs are COT and CDER, but with a pixel resolution of 280 m. Data for training and testing the NN are from the same original datasets used for DNNs. Figure 9 shows comparisons of the NN and our DNNs.…”

Section: Comparison With Previous Work Using a Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Feasibility study of multi-pixel retrieval of optical thickness and droplet effective radius of inhomogeneous clouds using deep learning

2017

View full text Add to dashboard Cite

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 socalled convolutional layers and retrieves cloud properties directly from the reflectances at four wavelengths. The DNN methods are trained and tested on cloud fields from largeeddy 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.

show abstract

Section: Introductionmentioning

confidence: 95%

Section: Comparison With Previous Work Using a Neural Networkmentioning

confidence: 99%

Feasibility study of multi-pixel retrieval of optical thickness and droplet effective radius of inhomogeneous clouds using deep learning

2017

View full text Add to dashboard Cite

show abstract

“…These authors simulated the columnar water vapour and columnar liquid water retrievals of the models using SSM/I measurements, closely reproducing its results, but improving the speed and thus allowing the use in forecast models such as the National Centers for Environmental Prediction (NCEP) numerical models. Cloud parameter retrieval models for inhomogeneous and fractional clouds have also been simulated (Faure et al 2001) with reasonable accuracy.…”

Section: Physically-based Methodsmentioning

confidence: 95%

Neural networks in satellite rainfall estimation

Tapiador

Kidd

Hsu

et al. 2004

Meteorological Applications

View full text Add to dashboard Cite

show abstract

“…The formulation and solution of direct and inverse radiative transfer problems are directly related to several relevant applications in a large number of areas of scientific and technological interest such as tomography (Kim and Charette, 2007;Carita Montero et al, 2004), remote sensing and environmental sciences (Spurr et al, 2007;Verhoef and Bach, 2003;Hanan, 2001;Fause et al, 2001), and radiative properties estimation (Sousa et al, 2007;Zhou et al, 2002), among many others.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of radiances generated by solving the radiative-transfer equation with different approaches

Chalhoub¹,

Velho²,

Neto³

2012

J. Braz. Soc. Mech. Sci. & Eng.

View full text Add to dashboard Cite

Neural network retrieval of cloud parameters of inhomogeneous and fractional clouds

Cited by 43 publications

References 29 publications

Feasibility study of multi-pixel retrieval of optical thickness and droplet effective radius of inhomogeneous clouds using deep learning

Feasibility study of multi-pixel retrieval of optical thickness and droplet effective radius of inhomogeneous clouds using deep learning

Neural networks in satellite rainfall estimation

Evaluation of radiances generated by solving the radiative-transfer equation with different approaches

Contact Info

Product

Resources

About