Code covered by the BSD License  

Download apps, toolboxes, and other File Exchange content using Add-On Explorer in MATLAB.

» Watch video

Highlights from
Circulant Embedding method for generating stationary Gaussian field

5.0
5.0 | 1 rating Rate this file 8 Downloads (last 30 days) File Size: 2.24 KB File ID: #38880 Version: 2.0
image thumbnail

Circulant Embedding method for generating stationary Gaussian field

by

Zdravko Botev (view profile)

 

02 Nov 2012 (Updated )

Fast simulation of Gaussian random fields via the Fast Fourier Transform

| Watch this File

File Information
Description

simulating stationary Gaussian field over an 'm' times 'n' grid
 INPUT:
          - 'm' and 'n' for evaluating the field over the m*n grid;
             note that size of covariance matrix is m^2*n^2;
          - scalar function rho(h), where 'h' is a two dimensional vector
            input and cov(X_t,Y_s)=rho(t-s) is the cov. function of a
            2-dimensional stationary Gaussian field; see reference below;
 OUTPUT:
          - two statistically independent fields 'field1' and 'field2'
            over the m*n grid;
          - vectors 'tx' and 'ty' so that the field is plotted via
                    imagesc(tx,ty,field1)
 Example:
 rho=@(h)((1-h(1)^2/50^2-h(1)*h(2)/(15*50)-h(2)^2/15^2)...
  *exp(-(h(1)^2/50^2+h(2)^2/15^2))); % define covariance function
  stationary_Gaussian_process(512,384,rho); % plot when no output wanted
Reference:
 Kroese, D. P., & Botev, Z. I. (2015). Spatial Process Simulation.
 In Stochastic Geometry, Spatial Statistics and Random Fields(pp. 369-404)
 Springer International Publishing, DOI: 10.1007/978-3-319-10064-7_12

Acknowledgements

This file inspired Fractional Brownian Field Or Surface Generator.

Required Products MATLAB
MATLAB release MATLAB 8.6 (R2015b)
MATLAB Search Path
/
Tags for This File   Please login to tag files.
Please login to add a comment or rating.
Comments and Ratings (2)
01 Mar 2016 ARVINDER KAUR

Please help me to understand what does it mean and tell me how to do it-
Realistic spatially correlated speckle noise in ultrasound images can be simulated by low-pass filtering a complex Gaussian random field and taking the magnitude of filtered output.The speckle noise with different covariance functions are introduced under different noise cases.These are-Matern covariance function,Spherical covariance function,Exponential covariance function and Rational quadratic covariance function.
Mean of Gaussian random field=0

Comment only
06 Jun 2014 Knight Short

Very helpful code.

I am interested in How to use this circulant embedding method to generate a 3 dimensional stationary processes. The book does not describe that case in detail. Could we have a further communication?

Thank you for your consideration.

Best regards.

Updates
22 Jan 2016 2.0

- rewritten as an m-file
- reference updated

Contact us