The Feature Selection and Extraction of Hyperspectral Mineralization Information Based on Rough Sets Theory

Wall rock alteration is one of the major mineralization characteristics of hydrothermal deposits. In order to effectively extract information in hyperspectral remote sensing prospecting, it is necessary to objectively filter the spectral characteristics of altered rock and the closely correlative spectral characteristics in the mineralization forecast. Rough sets do not need the datapsilas additional information or prior knowledge, can make attribute reduction on the decision system. In the application of rough sets theory, this paper puts forward the believable method of spectrum curve feature selection and extraction, extracts the mineralization information which is closely related to the mineralization forecast, gets access to the best combination of variables and the interval, which are regarded as the parameter when establishing mineralization information identification model. Finally, this paper makes a example test based on this modes, and the results are basically consistent with the practical perambulation information, which shows that this method can be used as the hyperspectral mineralization information identification model to provide the basis for mineralization forecast.