Mapping Benthic Habitats by Extending Non-Negative Matrix Factorization to Address the Water Column and Seabed Adjacency Effects

Abstract

Monitoring of coastal areas by remote sensing is an important issue. The interest of using an unmixing method to determine the seabed composition from hyperspectral aerial images of coastal areas is investigated. Unmixing provides both seabed abundances and endmember reflectances. A sub-surface mixing model is presented, based on a recently proposed oceanic radiative transfer model that accounts for seabed adjacency effects in the water column. Two original non-negative matrix factorization ( N M F )-based unmixing algorithms, referred to as W A D J U M (Water ADJacency UnMixing) and W U M (Water UnMixing, no adjacency effects) are developed, assuming as known the water column bio-optical properties. Simulations show that W A D J U M algorithm achieves performance close to that of the N M F -based unmixing of the seabed without any water column, up to 10 m depth. W U M performance is lower and decreases with the depth. The robustness of the algorithms when using erroneous information about the water column bio-optical properties is evaluated. The results show that the abundance estimation is more reliable using W A D J U M approach. W A D J U M is applied to real data acquired along the French coast; the derived abundance maps of the benthic habitats are discussed and compared to the maps obtained using a fixed spectral library and a least-square ( L S ) estimation of the seabed mixing coefficients. The results show the relevance of the W A D J U M algorithm for the local analysis of the benthic habitats.

Mapping of Coral Reefs with Multispectral Satellites: A Review of Recent Papers

“…A high spectral resolution coupled with a low-spatial-resolution result in a problem known as "spectral unmixing", which is the process of decomposing a given mixed pixel into its component elements and their respective proportions. Some existing algorithms can tackle this issue with a high level of accuracy [42][43][44]. When unmixing pixels, algorithms may face errors due to the heterogeneity of seabed reflectance, disturbing the radiance with the light scattered on the neighboring elements [45].…”

Hyperspectral and Multispectral Image Fusion with Automated Extraction of Image-Based Endmember Bundles and Sparsity-Based Unmixing to Deal with Spectral Variability

“…The data provided by these sensors having a high spectral resolution deliver useful information that enable an accurate classification and precise detection of pure materials (also called endmembers) in the observed scene. This fine spectral resolution permits the use of hyperspectral images (HSI) in countless different fields [ 10 ] including monitoring of coastal areas [ 11 , 12 ], measuring gas flaring [ 13 , 14 ], estimation of the area of photovoltaic panels [ 15 ], mineral detection, and mapping [ 16 ].…”