An Application of Wavelet Based Dimension Reduction to AIRS Data

Hyperspectral sensors provide much richer information than comparable multispectral sensors. However currently we do not have sufficient recourses to compute results based on all the gathered information. One way to approach this problem is to perform dimension reduction [1] as pre-processing, i.e to apply a transformation that brings data from a high order dimension to a low order dimension. Wavelet spectral analysis of hyperspectral images has been proposed as a method for dimension reduction and has shown promising results over the traditional Principal Component Analysis (PCA) technique. The Atmospheric Infrared Sounder (AIRS) [2] instrument data, designed to measure the Earth’s atmospheric water vapor and temperature profiles on a global scale. AIRS has more than 2,000 channels and hence becomes a good candidate dimension reduction. The objective of this work is to extend and apply Wavelet based Dimension Reduction over AIRS data.