A supervised multiclass framework for mineral classification of Iberian beads.

Research on personal adornments depends on the reliable characterisation of materials to trace provenance and model complex social networks. However, many analytical techniques require the transfer of materials from the museum to the laboratory, involving high insurance costs and limiting the number of items that can be analysed, making the process of empirical data collection a complicated, expensive and time-consuming routine. In this study, we compiled the largest geochemical dataset of Iberian personal adornments (n = 1243 samples) by coupling X-ray fluorescence compositional data with their respective X-ray diffraction mineral labels. This allowed us to develop a machine learning-based framework for the prediction of bead-forming minerals by training and benchmarking 13 of the most widely used supervised algorithms. As a proof of concept, we developed a multiclass model and evaluated its performance on two assemblages from different Portuguese sites with current mineralogical characterisation: Cova das Lapas (n = 15 samples) and Gruta da Marmota (n = 10 samples). Our results showed that decisión-tres based classifiers outperformed other classification logics given the discriminative importance of some chemical elements in determining the mineral phase, which fits particularly well with the decision-making process of this type of model. The comparison of results between the different validation sets and the proof-of-concept has highlighted the risk of using synthetic data to handle imbalance and the main limitation of the framework: its restrictive class system. We conclude that the presented approach can successfully assist in the mineral classification workflow when specific analyses are not available, saving time and allowing a transparent and straightforward assessment of model predictions. Furthermore, we propose a workflow for the interpretation of predictions using the model outputs as compound responses enabling an uncertainty reduction approach currently used by our team. The Python-based framework is packaged in a public repository and includes all the necessary resources for its reusability without the need for any installation.

Microbial plankton responses to multiple environmental drivers in marine ecosystems with different phosphorus limitation degrees.

Multiple drivers are threatening the functioning of the microbial food webs and trophic interactions. Our understanding about how temperature, CO2, nutrient inputs, and solar ultraviolet radiation (UVR) availability interact to alter ecosystem functioning is scarce because research has focused on single and double interactions. Moreover, the role that the degree of in situ nutrient limitation could play in the outcome of these interactions has been largely neglected, despite it is predominant in marine ecosystems. We address these uncertainties by combining remote-sensing analyses, and a collapsed experimental design with natural microbial communities from Mediterranean Sea and Atlantic Ocean exposed to temperature, nutrients, CO2, and UVR interactions. At the decade scale, we found that more intense and frequent (and longer lasting) Saharan dust inputs (and marine heatwaves) were only coupled with reduced phytoplankton biomass production. When microbial communities were concurrently exposed to future temperature, CO2, nutrient, and UVR conditions (i.e. the drivers studied over long-term scales), we found shifts from net autotrophy [primary production:respiration (PP:R) ratio > 1] towards a metabolic equilibrium (PP:R ratio ~ 1) or even a net heterotrophy (PP:R ratio < 1), as P-limitation degree was higher (i.e. Atlantic Ocean). These changes in the metabolic balance were coupled with a weakened phytoplankton-bacteria interaction (i.e. bacterial carbon demand exceeded phytoplankton carbon supply. Our work reveals that an accentuated in situ P limitation may promote reductions both in carbon uptake and fluxes between trophic levels in microbial plankton communities under global-change conditions. We show that considering long-term series can aid in identifying major local environmental drivers (i.e. temperature and nutrients in our case), easing the design of future global-change studies, but also that the abiotic environment to which microbial plankton communities are acclimated should be taken into account to avoid biased predictions concerning the effects of multiple interacting global-change drivers on marine ecosystems.