Application of data fusion techniques to direct geographical traceability indicators

A hierarchical data fusion approach has been developed proposing multivariate curve resolution (MCR) as a variable reduction tool.The case study presented concerns the characterization of soil samples of the Modena District. It was performed in order to understand, at a pilot study stage, the geographical variability of the zone prior to planning a representative soils sampling to derive geographical traceability models for Lambrusco Wines. Soils samples were collected from four producers of Lambrusco Wines, located in in-plane and hill areas. Depending on the extension of the sampled fields the number of points collected varies from three to five and, for each point, five depth levels were considered.The different data blocks consisted of X-ray powder diffraction (XRDP) spectra, metals concentrations relative to thirty-four elements and the 87Sr/86Sr isotopic abundance ratio, a very promising geographical traceability marker.A multi steps data fusion strategy has been adopted. Firstly, the metals concentrations dataset was weighted and concatenated with the values of strontium isotopic ratio and compressed. The resolved components described common patterns of variation of metals content and strontium isotopic ratio. The X-ray powder spectra profiles were resolved in three main components that can be referred to calcite, quartz and clays contributions. Then, a high-level data fusion approach was applied by combining the components arising from the previous data sets.The results show interesting links among the different components arising from XRDP, the metals pattern and to which of these 87Sr/86Sr Isotopic Ratio variation is closer. The combined information allowed capturing the variability of the analyzed soil samples.

Figure optionsDownload as PowerPoint slideHighlights
► Data fusion is applied to XRPD profiles, metal contents and isotopic ratio 87Sr/86Sr data to characterize soils samples.
► Multivariate curve resolution is used as variable reduction tool for hierarchical data fusion.
► Soil samples differences and similarity were highlighted as well as the linking relations among data blocks.