Abstract
In image processing, it is commonly assumed that the model ruling spectral mixture in a given hyperspectral pixel is linear. However, in many real life cases, the different objects and materials determining the observed spectral signatures overlap in the same scene, resulting in nonlinear mixture. This is particularly evident in volcanoes-related imagery, where both airborne plumes of effluents and surface deposit of volcanic ejecta can be mixed in the same observation line of sight. To tackle this intrinsic complexity, in this paper, we perform a pilot test using Nonlinear Principal Component Analysis (NLPCA) as a nonlinear transformation, that projects a hyperspectral image onto a reduced-dimensionality feature space. The use of NLPCA is twofold: (1) it is used to reduce the dimensionality of the original spectral data and (2) it performs a linearization of the information, thus allowing the effective use of successive linear approaches for spectral unmixing. The proposed method has been tested on two different hyperspectral datasets, dealing with active volcanoes at the time of the observation. The dimensionality of the spectroscopic problem is reduced of up to 95% (ratio of the elements of compressed nonlinear vectors and initial spectral inputs), by the use of NLPCA. The selective use of an atmospheric correction pre-processing is applied, demonstrating how individual plume and volcanic surface deposit components can be discriminated, paving the way to future application of this method.
Highlights
Volcanoes can inject a great amount of gaseous and particulate effluents to the atmosphere, like water vapour, sulphur dioxide and ash, both at background degassing conditions and during explosive eruptions [1]
In this paper, we propose the use of the nonlinear Principal Component Analysis (NLPCA) for the projection of the hyper-spectral image into a feature space [32]
Two real measurements datasets have been considered to test the proposed technique. Both radiance and reflectance data, i.e., without and with atmospheric correction, are used in order to analyze the effect of these two options in our approach
Summary
Volcanoes can inject a great amount of gaseous and particulate effluents to the atmosphere, like water vapour, sulphur dioxide and ash, both at background degassing conditions and during explosive eruptions [1]. Approaches have been tried in order to quantify volcanic ash and SO2 using both multi-spectral and hyper-spectral data [15,16,17] In such cases, unmixing the volcanic cloud spectral signature from other spectral features, as those arising from other atmospheric components in the line of sight of the instruments or from the surface, is vital to rule out these different contributions [3,18]. Hyper-spectral imaging sensors normally record scenes in which numerous interacting objects and material substances, both at the surface and in the overlying atmosphere, contribute to the spectrum measured from a single pixel, by their interaction with the atmospheric radiation recorded by the sensor Given such mixed pixels, the process of identification of the individual constituent materials in the mixture (endmembers), as well as the proportions in which they appear (abundances), is commonly referred to as spectral unmixing.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
