Radial Basis Function and Multilayer Perceptron neural networks for sea water optically active parameter estimation in case II waters: a comparison

Corsini, G.; Diani, M.; Grasso, R.; De Martino, M.; Mantero, P.; Serpico, S. B.
October 2003
International Journal of Remote Sensing;10/20/2003, Vol. 24 Issue 20, p3917
Academic Journal
This paper deals with the problem of retrieving optically active parameters of the water from multispectral remotely sensed data. We analyse the neural networks approach applied to the estimation of chlorophyll concentration in coastal waters (Case II Waters) and discuss the use of two types of networks: the Radial Basis Function neural network and Multilayer Perceptron. We present a brief summary concerning their architectures and training methods. For proving the concept we analyse the procedures and the performances on a simulated data set reproducing the data acquired from the MERIS (Medium Resolution Imaging Spectrometer), the multispectral sensor on board the ENVISAT satellite. The multispectral subsurface reflectance data have been generated by means of a three component ocean colour direct model and statistically reproduce the case II waters. The neural networks performances have been analysed in terms of MSE (Mean Square Error), correlation coefficient and relative error. We provide a detailed discussion and comparison of the two types of networks and the obtained results confirm the effectiveness of the neural approach in such an application.


Related Articles

  • Model Updating Based on Radial Basis Function Neural Network. Fang Han; Dongwang Zhong; Jiyun Mo // International Review on Computers & Software;Dec2011, Vol. 6 Issue 7, p1218 

    Finite element model updating is a procedure to minimize the differences between analytical and experimental results so that a more refined model can be achieved. However, it still remains a difficult problem for model updating is an inverse process and often contains highly non-linear...

  • Hybrid state of charge estimation for lithium-ion batteries: design and implementation. Alfi, Alireza; Charkhgard, Mohammad; Zarif, Mohammad Haddad // IET Power Electronics;2014, Vol. 7 Issue 11, p2758 

    This study introduces a novel hybrid method for state of charge (SOC) estimation of lithium-ion battery types using extended H∞ filter and radial basis function (RBF) networks. The RBF network's parameters are adjusted off-line by acquired data from the battery in charging step. This kind...

  • Applying Radial Basis Function Neural Networks Based on Fuzzy Clustering to Estimate Web Applications Effort. Zakrani, Abdelali; Idri, Ali // International Review on Computers & Software;Sep2010, Vol. 5 Issue 5, p516 

    An important research issue in software project management is how to predict accurately an effort for the software project to develop at an early stage. Achieving high accuracy when estimating the effort of the software under development would supply effectively the project managers in leading...

  • A radial basis function artificial neural network test for neglected nonlinearity. Blake, Andrew P.; Kapetanios, George // Econometrics Journal;Dec2003, Vol. 6 Issue 2, p357 

    We propose a test for neglected nonlinearity that uses an alternative artificial neural network (ANN) specification to the one commonly used in the literature. We use radial basis functions for the ‘hidden layer’ with basis function centres and radii chosen from the sample data set...

  • Application of Generalized Radial Basis Function Networks to Recognition of Radar Targets. Huang, De-Shuang // International Journal of Pattern Recognition & Artificial Intell;Sep1999, Vol. 13 Issue 6, p945 

    This paper extends general radial basis function networks (RBFN) with Gaussian kernel functions to generalized radial basis function networks (GRBFN) with Parzen window functions, and discusses applying the GRBFNs to recognition of radar targets. The equivalence between the RBFN classifiers...

  • DESIGNING A SIMPLE RADIOMETRIC SYSTEM TO PREDICT VOID FRACTION PERCENTAGE INDEPENDENT OF FLOW PATTERN USING RADIAL BASIS FUNCTION. Roshani, Gholam H.; Nazemi, Ehsan; Shama, Farzin; Imani, Mohammad A.; Mohammadi, Salar // Metrology & Measurement Systems;2018, Vol. 25 Issue 2, p347 

    The void fraction is one of the most important parameters characterizing a multiphase flow. The prediction of the performance of any system operating with more than single phase relies on our knowledge and ability to measure the void fraction. In this work, a validated simulation study was...

  • Fuzzy System and CMAC Network with B-Spline Membership/Basis Functions can Approximate A Smooth Function and its Derivatives. Wang Shitong, Haiming; Lu Hongjun, Haiming // International Journal of Computational Intelligence & Applicatio;Sep2003, Vol. 3 Issue 3, p265 

    In control and other modeling applications, fuzzy system with B-spline membership functions and CMAC neural network with B-spline basis functions are sometimes desired to approximate not only the assigned smooth function as well as its derivatives. In this paper, by designing the fuzzy system...

  • On the effects of the radial basis function scale parameter on the numerical solution of partial differential equations. Hutchcraft, W. Elliott; Gordon, Richard K. // Microwave & Optical Technology Letters;Jun2009, Vol. 51 Issue 6, p1520 

    Radial Basis Functions have received significant attention in the scientific literature over the past several years. Specifically, they have been investigated extensively in the field of neural networks. They have been shown to have very good interpolation qualities and this property has led to...

  • RBF-PU Interpolation with Variable Subdomain Sizes and Shape Parameters. Cavoretto, Roberto; De Rossi, Alessandra; Perracchione, Emma // AIP Conference Proceedings;2016, Vol. 1776 Issue 1, p1 

    In this paper, we deal with the challenging computational issue of interpolating large data sets, with eventually nonhomogeneous densities. To such scope, the Radial Basis Function Partition of Unity (RBF-PU) method has been proved to be a reliable numerical tool. However, there are not...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics