Combining colour parameters and geochemical tracers to improve sediment source discrimination in a mining catchment (New Caledonia, South Pacific Islands)

Tracing the origin of sediment is needed to improve our knowledge of hydro-sedimentary dynamics at the catchment scale. Several fingerprinting approaches have been developed to provide this crucial information. In particular, spectroscopy provides a rapid, inexpensive and non-destructive alternative technique to the conventional analysis of the geochemical properties. Here, we investigated the performance of four multi-proxy approaches based on (1) colour parameters, (2) geochemical properties, (3) colour parameters coupled with geochemical properties and (4) the entire visible spectrum to discriminate sediment source contributions in a mining catchment of New Caledonia. This French archipelago located in the south-west Pacific Ocean is the world's sixth largest producer of nickel. Open-cast nickel mining increases soil degradation and the downstream transfer of sediments in river systems, leading to the river system siltation. The sediment sources considered in the current research were therefore sediment eroded from mining sub-catchments and non-mining sub-catchments. To this end, sediment deposited during two cyclonic events (i.e. 2015 and 2017) was collected following a tributary design approach in one of the first areas exploited for nickel mining on the archipelago, the Thio River catchment (397 km2). Source (n=24) and river sediment (n=19) samples were analysed by X-ray fluorescence and spectroscopy in the visible spectra (i.e. 365–735 nm). The results demonstrated that the individual sediment tracing methods based on spectroscopy measurements (i.e. (1) and (4)) were not able to discriminate sources. In contrast, the geochemical approach (2) did discriminate sources, with 83.1 % of variance in sources explained. However, it is the inclusion of colour properties in addition to geochemical parameters (3) which provides the strongest discrimination between sources, with 92.6 % of source variance explained. For each of these approaches ((2) and (3)), the associated fingerprinting properties were used in an optimized mixing model. The predictive performance of the models was validated through tests with artificial mixture samples, i.e. where the proportions of the sources were known beforehand. Although with a slightly lower discrimination potential, the “geochemistry” model (2) provided similar predictions of sediment contributions to those obtained with the coupled “colour + geochemistry” model (3). Indeed, the geochemistry model (2) showed that mining