Exploring the efficacy of hyperspectral data analysis using support vector machines

Abstract EN

Remote sensing hyper spectral data has matured over the past ten years especially in the field of earth science.

Utilization of this technology has shown a rapid increase in many areas of economic and scientific significance.

Hyper spectral sensors capture the detailed spectral signatures that uniquely characterize a great number of diverse surface materials.

Classification, clustering, and visualization of these very high-dimensional signatures need untraditional methods.

Different approaches for spectral image interpretation are studied using Artificial Neural Networks (ANNs) namely Support Vector Machines (SVM) to meet the challenge of high-dimensionality.

Precisely the study used SVM for geological mapping of hyper spectral imagery at Abu Zenima area, western Sinai, Egypt, the hyper spectral data has been captured in 2003 by Hyperion instrument on the United States Geological Survey (USGS) Earth Observing 1 (EO-1) satellite.

The hyper spectral imagery contains 224 bands ; the study used 174 bands excluding overlapped and not calibrated bands.

More than 10 different geological units were well classified and recognized by the proposed SVM using different data sets with different sizes for training as well as for testing.