Sedimentary structure discrimination with hyperspectral imaging in sediment cores.

Hyperspectral imaging (HSI) is a non-destructive, high-resolution imaging technique that is currently under significant development for analyzing geological areas with remote devices or natural samples in a laboratory. In both cases, the hyperspectral image provides several sedimentary structures that must be separated to temporally and spatially describe the sample. Sediment sequences are composed of successive deposits (strata, homogenite, flood) that are visible depending on sample properties. The classical methods to identify them are time-consuming, have a low spatial resolution (millimeters) and are generally based on naked-eye counting. In this study, we compare several supervised classification algorithms to discriminate sedimentological structures in lake sediments. Instantaneous events in lake sediments are generally linked to extreme geodynamical events (e.g., floods, earthquakes), so their identification and counting are essential to understand long-term fluctuations and improve hazard assessments. Identification and counting are done by reconstructing a chronicle of event layer occurrence, including estimation of deposit thicknesses. Here, we applied two hyperspectral imaging sensors (Visible Near-Infrared, VNIR, 60 µm, 400-1000 nm; Short Wave Infrared, SWIR, 200 µm, 1000-2500 nm) on three sediment cores from different lake systems. We highlight that the SWIR sensor is the optimal one for creating robust classification models with discriminant analyses (prediction accuracies of 0.87-0.98). Indeed, the VNIR sensor is impacted by the surface reliefs and structures that are not in the learning set, which causes mis-classification. These observations are also valid for the combined sensor (VNIR-SWIR) and the RGB images. Several spatial and spectral pre-processing were also compared and enabled one to highlight discriminant information specific to a sample and a sensor. These works show that the combined use of hyperspectral imaging and machine learning improves the characterization of sedimentary structures compared to conventional methods.

High-resolution prediction of organic matter concentration with hyperspectral imaging on a sediment core.

In the case of environmental samples, the use of a chemometrics-based prediction model is highly challenging because of the difficulty in experimentally creating a well-ranged reference sample set. In this study, we present a methodology using short wave infrared hyperspectral imaging to create a partial least squares regression model on a cored sediment sample. It was applied to a sediment core of the well-known Lake Bourget (Western Alps, France) to develop and validate a model for downcore high resolution LOI550 measurements used as a proxy of the organic matter. In lake and marine sediment, the organic matter content is widely used, for example, to reconstruct carbon flux variations through time. Organic matter analysis through routine analysis methods is time- and material-consuming, as well as not spatially resolved. A new instrument based on hyperspectral imaging allows high spatial and spectral resolutions to be acquired all along a sediment core. In this study, we obtain a model characterized by a 0.95 r prediction, with 0.77 wt% of model uncertainty based on 27 relevant wavelengths. The concentration map shows the variation inside each laminae and flood deposit. LOI550 reference values obtained with the loss on ignition are highly correlated to the inc/coh ratio used as a proxy of the organic matter in X-ray fluorescence with a correlation coefficient of 0.81. This ratio is also correlated with the averaged subsampled hyperspectral prediction with a r of 0.65.