1993
DOI: 10.1029/93jc01815
|View full text |Cite
|
Sign up to set email alerts
|

A neural network approach for modeling nonlinear transfer functions: Application for wind retrieval from spaceborne scatterometer data

Abstract: The present paper shows that a wide class of complex transfer functions encountered in geophysics can be efficiently modeled using neural networks. Neural networks can approximate numerical and nonnumerical transfer functions. They provide an optimum basis of nonlinear functions allowing a uniform approximation of any continuous function. Neural networks can also realize classification tasks. It is shown that the classifier mode is related to Bayes discriminant functions, which give the minimum error risk clas… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
48
0
1

Year Published

1997
1997
2016
2016

Publication Types

Select...
5
4

Relationship

2
7

Authors

Journals

citations
Cited by 88 publications
(49 citation statements)
references
References 18 publications
0
48
0
1
Order By: Relevance
“…In the present study, we used water-leaving reflectances at five wavelengths (412, 443, 490, 510, and 555 nm). In order to extract the second-order effect due to specific water characteristics other than phytoplankton abundance, we computed a reflectance ratio, Ra(k), defined following Alvain et al [2012] SeaWiFS chlorophyll-a concentration values by using a specific class of neural networks, the so-called MLP (Multi-Layer Perceptron), which are well-suited estimators for nonlinear continuous regression [Bishop, 2006;Thiria et al, 1993]. As the function Chl-a !…”
Section: 1002/2015jc010738mentioning
confidence: 99%
“…In the present study, we used water-leaving reflectances at five wavelengths (412, 443, 490, 510, and 555 nm). In order to extract the second-order effect due to specific water characteristics other than phytoplankton abundance, we computed a reflectance ratio, Ra(k), defined following Alvain et al [2012] SeaWiFS chlorophyll-a concentration values by using a specific class of neural networks, the so-called MLP (Multi-Layer Perceptron), which are well-suited estimators for nonlinear continuous regression [Bishop, 2006;Thiria et al, 1993]. As the function Chl-a !…”
Section: 1002/2015jc010738mentioning
confidence: 99%
“…Neural networks provide a family of functions that can approximate a wide range of nonlinear continuous functions [Thiria et al, 1993;Bishop, 1995]. In section 3 we will justify and discuss the type of network selected for the study.…”
Section: Simulated Data Setsmentioning
confidence: 99%
“…NNs have been used in several applications in remote sensing, e.g., derivation of water properties from imaging spectrometers [13]. Furthermore, Thiria et al [14] and Richaume et al [15] applied NNs to wind retrieval from spaceborne SCAT data and ERS-1 SCAT data.…”
mentioning
confidence: 99%