Wavelet transform-vector quantization compression of supercomputer ocean models

Abstract

A new procedure for efficient compression of digital information for storage and transmission purposes involves a discrete wavelet transform subband decomposition of the data set, followed by vector quantization of the wavelet transform coefficients using application-specific vector quantizers. The vector quantizer design optimizes the assignment of both memory resources and vector dimensions to the transform subbands by minimizing an exponential rate-distortion functional subject to constraints on both overall bit-rate and encoder complexity. The method is applicable to the compression of other multidimensional data sets possessing some degree of smoothness. The authors discuss the use of this technique for compressing the output of supercomputer simulations of global climate models. The data presented here comes from Semtner-Chervin global ocean models run at the National Center for Atmospheric Research.<>