Computationally Efficient Stochastic Realization for Internal Multiscale Autoregressive Models
Multidimensional Systems and Signal Processing
A Krylov Subspace Method for Covariance Approximation and Simulation of Random Processes and Fields
Multidimensional Systems and Signal Processing
ON SPECTRAL SIMULATION OF FRACTIONAL BROWNIAN MOTION
Probability in the Engineering and Informational Sciences
General methodology 2: an efficient method for simulating fractional stable motion
Proceedings of the 34th conference on Winter simulation: exploring new frontiers
Effective bandwidth for a single server queueing system with fractional Brownian input
Performance Evaluation - Long range dependence and heavy tail distributions
Fast simulation of overflow probabilities in a queue with Gaussian input
ACM Transactions on Modeling and Computer Simulation (TOMACS)
Wavelet-based synthesis of the Rosenblatt process
Signal Processing - Signal processing in UWB communications
Low-complexity coding and source-optimized clustering for large-scale sensor networks
ACM Transactions on Sensor Networks (TOSN)
Quasi-Monte Carlo methods for elliptic PDEs with random coefficients and applications
Journal of Computational Physics
Computing $f(A)b$ via Least Squares Polynomial Approximations
SIAM Journal on Scientific Computing
ISCIS'06 Proceedings of the 21st international conference on Computer and Information Sciences
A regularised estimator for long-range dependent processes
Automatica (Journal of IFAC)
HEAF: a novel estimator for long-range dependent self-similar network traffic
NEW2AN'06 Proceedings of the 6th international conference on Next Generation Teletraffic and Wired/Wireless Advanced Networking
Journal of Computational Physics
Hi-index | 0.02 |
Geostatistical simulations often require the generation of numerous realizations of a stationary Gaussian process over a regularly meshed sample grid $\Omega$. This paper shows that for many important correlation functions in geostatistics, realizations of the associated process over $m+1$ equispaced points on a line can be produced at the cost of an initial FFT of length $2m$ with each new realization requiring an additional FFT of the same length. In particular, the paper first notes that if an $(m+1)\times(m+1) $ Toeplitz correlation matrix $R$ can be embedded in a nonnegative definite $2M\times2M$ circulant matrix $S$, exact realizations of the normal multivariate $y \sim {\cal N}(0,R)$ can be generated via FFTs of length $2M$. Theoretical results are then presented to demonstrate that for many commonly used correlation structures the minimal embedding in which $M = m$ is nonnegative definite. Extensions to simulations of stationary fields in higher dimensions are also provided and illustrated.