Unmixing-Based Denoising as a Pre-Processing Step for Coral Reef Analysis

Abstract

ABSTRACT:Coral reefs, among the world's most biodiverse and productive submerged habitats, have faced several mass bleaching events due to climate change during the past 35 years. In the course of this century, global warming and ocean acidification are expected to cause corals to become increasingly rare on reef systems. This will result in a sharp decrease in the biodiversity of reef communities and carbonate reef structures. Coral reefs may be mapped, characterized and monitored through remote sensing. Hyperspectral images in particular excel in being used in coral monitoring, being characterized by very rich spectral information, which results in a strong discrimination power to characterize a target of interest, and separate healthy corals from bleached ones. Being submerged habitats, coral reef systems are difficult to analyse in airborne or satellite images, as relevant information is conveyed in bands in the blue range which exhibit lower signal-to-noise ratio (SNR) with respect to other spectral ranges; furthermore, water is absorbing most of the incident solar radiation, further decreasing the SNR. Derivative features, which are important in coral analysis, result greatly affected by the resulting noise present in relevant spectral bands, justifying the need of new denoising techniques able to keep local spatial and spectral features. In this paper, Unmixing-based Denoising (UBD) is used to enable analysis of a hyperspectral image acquired over a coral reef system in the Red Sea based on derivative features. UBD reconstructs pixelwise a dataset with reduced noise effects, by forcing each spectrum to a linear combination of other reference spectra, exploiting the high dimensionality of hyperspectral datasets. Results show clear enhancements with respect to traditional denoising methods based on spatial and spectral smoothing, facilitating the coral detection task.

Machine learning-based retrieval of benthic reflectance and Posidonia oceanica seagrass extent using a semi-analytical inversion of Sentinel-2 satellite data

“…This highlights the issue of SVM with noisy data, such as the Planet's CubeSat-derived imagery over coastal areas, as they are algorithms not optimised to deal with this problem (Mountrakis, Im, and Ogole 2011). SVM performance in Traganos, Cerra, and Reinartz (2017) increased by the use of the Unmixing-based Denoising (UBD) which has also shown remarkable improvements in hyperspectral scenes over coastal waters (Cerra et al 2013(Cerra et al , 2017. Elsewhere, Eugenio, Marcello, and Martin (2015) employed SVM algorithm with an RBF kernel in a similarly parameterised radiative transfer model to ours to map benthic habitats on a WorldView-2 with an overall accuracy of 73% in a depth range between 0-25m.…”