The ultrahigh‐pressure pyrope whiteschists from the Brossasco‐Isasca Unit of the Southern Dora‐Maira Massif represent metasomatic rocks originated at the expense of post‐Variscan granitoids by the influx of fluids along shear zones. In this study, geochemical, petrological and fluid‐inclusion data, correlated with different generations of pyrope‐rich garnet (from medium, to very‐coarse‐grained in size) allow constraints to be placed on the relative timing of metasomatism and sources of the metasomatic fluid. Geochemical investigations reveal that whiteschists are strongly enriched in Mg and depleted in Na, K, Ca and LILE (Cs, Pb, Rb, Sr, Ba) with respect to the metagranite. Three generations of pyrope, with different composition and mineral inclusions, have been distinguished: (i) the prograde Prp I, which constitutes the large core of megablasts and the small core of porphyroblasts; (ii) the peak Prp II, which constitutes the inner rim of megablasts and porphyroblasts and the core of small neoblasts; and (iii) the early retrograde Prp III, which locally constitutes an outer rim. Two generations of fluid inclusions have been recognized: (i) primary fluid inclusions in prograde kyanite that represent a NaCl‐MgCl2‐rich brine (6–28 wt% NaCleq with Si and Al as other dissolved cations) trapped during growth of Prp I (type‐I fluid); (ii) primary multiphase‐solid inclusions in Prp II that are remnants of an alumino‐silicate aqueous solution, containing Mg, Fe, alkalies, Ca and subordinate P, Cl, S, CO32‐, LILE (Pb, Cs, Sr, Rb, K, LREE, Ba), U and Th (type‐II fluid), at the peak pressure stage. We propose a model that illustrates the prograde metasomatic and metamorphic evolution of the whiteschists and that could also explain the genesis of other Mg‐rich, alkali‐poor schists of the Alps. During Alpine metamorphism, the post‐Variscan metagranite of the Brossasco‐Isasca Unit experienced a prograde metamorphism at HP conditions (stage A: ∼1.6 GPa and ≤ 600 °C), as indicated by the growth of an almandine‐rich garnet in some xenoliths. At stage B (1.7–2.1 GPa and 560–590 °C), the influx of external fluids, originated from antigorite breakdown in subducting oceanic serpentinites, promoted the increase in Mg and the decrease of alkalies and Ca in the orthogneiss toward a whiteschist composition. During stage C (2.1 < P < 2.8 GPa and 590 < T < 650 °C), the metasomatic fluid influx coupled with internal dehydration reactions involving Mg‐chlorite promoted the growth of Prp I in the presence of the type‐I MgCl2‐brine. At the metamorphic peak (stage D: 4.0–4.3 GPa and 730 °C), Prp II growth occurred in the presence of a type–II alumino‐silicate aqueous solution, mostly generated by internal dehydration reactions involving phlogopite and talc. The contribution of metasomatic external brines at the metamorphic climax appears negligible. This fluid, showing enrichment in LILE and depletion in HFSE, could represent a metasomatic agent for the supra‐subduction mantle wedge.

We introduce a new approach, based on machine learning, to estimate pre-eruptive temperatures and storage depths using clinopyroxene-melt pairs and clinopyroxene-only chemistry. The model is calibrated for magmas of a wide compositional range, it complements existing models, and it can be applied independently of tectonic setting. Additionally, it allows the identification of the main chemical exchange mechanisms occurring in response to pressure and temperature variations on the base of experimental data without a priori assumptions. After the validation process, performances are assessed with test data never used during the training phase. We estimate the uncertainty using the root-mean-square error (RMSE) and the coefficient of determination (R 2). The application of the best performing algorithm (trained in the range 0-40 kbar and 952-1882 K) to clinopyroxene-melt pairs from primitive to extremely differentiated magmas of both subalkaline and alkaline systems returns a RMSE on the order of 2.6 kbar and 40 K for pressure and temperature, respectively. We additionally present a melt-and temperature-independent clinopyroxene barometer in the range 0-40 kbar, characterized by a RMSE of the order of 3 kbar. Tested for tholeiitic compositions in the range 0-10 kbar, the melt-and temperature-independent clinopyroxene barometer has a RMSE of 1.7 kbar. We finally apply the proposed approach to clinopyroxenes from Iceland, providing new, independent, insights about pre-eruptive storage depths of Icelandic volcanoes. The general applicability of this model will promote the comparison between the architecture of plumbing systems across tectonic settings and facilitate the comparison between petrologic and geophysical studies.

Thermobarometry is a fundamental tool to quantitatively interrogate magma plumbing systems and broaden our appreciation of volcanic processes. Developments in random forest‐based machine learning lend themselves to a data‐driven approach to clinopyroxene thermobarometry, allowing users to access large experimental data sets that can be tailored to individual applications in Earth Sciences. We present a methodological assessment of random forest thermobarometry using the R freeware package extraTrees. We investigate the model performance, the effect of hyperparameter tuning, and assess different methods for calculating uncertainties. Deviating from the default hyperparameters used in the extraTrees package results in little difference in overall model performance (<0.2 kbar and <3°C difference in standard error estimate, SEE). However, accuracy is greatly affected by how the final value from the distribution of trees in the random forest is selected (mean, median, or mode). Using the mean value leads to higher residuals between experimental and predicted P and T, whereas using median values produces smaller residuals. Additionally, this work provides two scripts for users to apply the methodology to natural data sets. The first script permits modification and filtering of the model calibration data set. The second script contains premade models, where users can rapidly input their data to recover PT estimates (SEE clinopyroxene‐only model: 3.2 kbar, 72.5°C and liquid‐clinopyroxene model: 2.7 kbar, 44.9°C). Additionally, the scripts allow the user to estimate the uncertainty for each analysis, which in some cases is significantly smaller than the reported SEE. These scripts are open source and can be accessed at https://github.com/corinjorgenson/RandomForest-cpx-thermobarometer.

Machine learning methods are evaluated to study the intriguing and debated topic of discrimination among different tectonic environments using geochemical and isotopic data. Volcanic rocks characterized by a whole geochemical signature of major elements (SiO have been extracted from open-access and comprehensive petrological databases (i.e. PetDB and GEOROC). The obtained dataset has been analyzed using support vector machines, a set of supervised machine learning methods, which are considered particularly powerful in classification problems.Results from the application of the machine learning methods show that the combined use of major, trace elements and isotopes allow associating the geochemical composition of rocks to the relative tectonic setting with high classification scores (93%, on average). The lowest scores are recorded from volcanic rocks deriving from back-arc basins (65%). All the other tectonic settings display higher classification scores, with oceanic islands reaching values up to 99%.Results of this study could have a significant impact in other petrological studies potentially opening new perspectives for petrologists and geochemists. Other examples of applications include the development of more robust geo-thermometers and geo-barometers and the recognition of volcanic sources for tephra layers in tephro-chronological studies.

[1] The 1739 A.D. Pietre Cotte lava flow is part of a sequence of low-explosive to weak effusion events occurred at La Fossa Cone, the active vent on Vulcano Island (Aeolian Arc, Italy). This lava is rhyolitic, texturally heterogeneous, and contains lati-trachytic enclaves. These compositions are recurrent in the La Fossa volcanic products and are representative of the recent Vulcano plumbing system. The host lava is vesicular, relatively phenocryst-free, and locally contains microlites and millimeter-sized spherulites. The enclaves are up to 10 cm in size, display angular to spherical shapes, and can form the core of spherulites. Enclaves mostly consist of plagioclase and augitic phenocrysts set in a weakly vesicular groundmass characterized by variable abundance of glass and feldspar microlites. Field, textural, and fractal data allow us to constrain the rheological features of the rhyolitic and lati-trachytic magmas. In situ major, trace, and volatile element analyses provide evidence for heterogeneities in the glassy matrix and zoning of phenocrysts. Processes of magma evolution have been quantitatively constrained by using the apparent distribution ratios of trace elements measured between mineral phases and glassy matrices. The collected data in combination with petrological and fluid inclusion data from the literature provides evidence for (1) a genetic relationship between the two magmas through assimilation fractional crystallization process; (2) a mingling mechanism between an uprising rhyolitic magma and a shallower partly crystallized lati-trachytic