Orange-Volcanoes is an extension of the open-source Orange data mining platform specifically tailored for geochemical, petrological, and volcanological investigations. enhances original by incorporating specialized tools to enable interactive data-driven investigations in geochemistry, such as performing Compositional Data Analysis (CoDA). Applying CoDA transformations enables use many standard multivariate statistical methods like principal component analysis, discriminant hierarchical...

Plain Language Summary Clinopyroxene is a major mineral in Earth's upper mantle. Previous studies have attempted to discriminate between reactions modifying the mantle by plotting clinopyroxene and trace element compositions two‐dimensional (2‐D) diagrams. However, these 2‐D methods show poor accuracy when applied global datasets. Therefore, we suggest machine learning approach evaluate compositional data higher dimensions. Our results demonstrate that can significantly improve of...

Abstract Although machine learning (ML) has brought new insights into geochemistry research, its implementation is laborious and time‐consuming. Here, we announce Geochemistry π, an open‐source automated ML Python framework. Geochemists only need to provide tabulated data select the desired options clean run algorithms. The process operates in a question‐and‐answer format, thus does not require that users have coding experience. After either automatic or manual parameter tuning, framework...

Abstract Comprehending the temperature distribution within Earth's lithospheric mantle is of paramount importance for understanding dynamics interior. Traditional mineral‐based thermobarometers effectively constrain and pressure particular compositions, but their application limited at global scale. Here, we trained machine‐learning (ML) algorithms on 985 published high‐temperature high‐pressure experiments use as thermometers barometers to overcome limitations classic methods. We compared...

Abstract Subduction processes play a pivotal role in facilitating material exchange between the crust and mantle, contributing to growth of continents. However, onset evolution subduction remain hotly debated. Here, we developed high‐dimensional machine learning (ML) model use multiple compositional data (e.g., Nb/La, Nb, Ti, Nb/U, Pb/Nd, Nb/Th) distinguish arc‐type from non‐arc basalts worldwide, then applied this well‐trained ML identify delineate secular occurrence Archean basalts. Our...

Abstract Clinopyroxene ferric iron content is an important consideration for garnet-clinopyroxene geothermometry and estimations of water storage in the Earth’s interior but remains difficult expensive to measure. Here, we develop seven classic algorithms machine learning methods estimate Fe3+/ΣFe clinopyroxene using major element data from electron microprobe analyses. The models were first trained a large set values determined by Mössbauer spectroscopy spanning wide compositional range,...

Abstract The approach of estimating the H 2 O content basaltic magmas via clinopyroxene (cpx) phenocrysts is a potentially effective way to glimpse deep Earth water cycle. However, it difficult ascertain using traditional geochemical methods whether hydrogen (H) measured in cpx represents primary signature that can ultimately inform estimates mantle content. In this study, we conducted machine learning on major element compositions and (1904 samples total). Using support vector (SVM),...

Abstract Li-rich micas are crucial in the exploration for and exploitation of Li resources. The determination mica using classical bulk chemical methods or situ microanalytical techniques is expensive time-consuming has stringent requirements quality reference materials. Although simple linear nonlinear empirical equations have been proposed, they inconsistent with complex physicochemical mechanisms incorporation commonly lead to large errors. In this study, we introduce a refined method...

Abstract The three main serpentine minerals, chrysotile, lizardite, and antigorite, form in various geological settings have different chemical compositions rheological properties. accurate identification of minerals is thus fundamental importance to understanding global geochemical cycles the tectonic evolution serpentine-bearing rocks. However, it challenging distinguish specific species solely based on data obtained by traditional analytical techniques. Here, we apply machine learning...

The Tibetan Plateau, Earth's largest and highest plateau, boasts an extraordinarily thick continental crust (60-80 kilometers) average elevation exceeding 4000 meters. Unraveling the plateau's uplift history, vital for comprehending Cenozoic history its environmental impacts, has long been a subject of debate. While prior studies predominantly attribute formation to India-Asia collision, 45-59 million years ago, timing underlying mechanisms remain contentious. Airy isostasy as response...

Machine learning has significantly advanced geochemistry research, but its implementation can be arduous and time-consuming. In response to this challenge, we introduce Geochemistry π, an open-source automated machine Python framework. With geochemists effortlessly process tabulated data execute algorithms by selecting preferred options. This streamlined operates in a user-friendly question-and-answer format, eliminating the need for coding expertise. Following automatic or manual...

The sulfur content at sulfide saturation (SCSS) in silicate melts plays a pivotal role governing the behavior of chalcophile elements planetary magma oceans. Numerous high-pressure experiments have been conducted to determine SCSS, employing various regression methods capture thermodynamic characteristics system. However, existing empirical equations shown limited predictive accuracy when applied laboratory measurements. In this study, we compiled and analyzed 542 experimental datasets...

Understanding the temperature and pressure within Earth's lithospheric mantle is crucial for comprehending dynamics of interior, its geochemical geophysical properties, as well their influence on magma formation stability cratons. While traditional mineral-based thermobarometers have provided valuable insights in estimating pressure, reliance specific mineral pairs reactions limits global applicability. Furthermore, a type high-dimensional data, compositions complex relationships that are...

Research on sampling and analysis of fluids rocks within both continental oceanic crusts has revealed a significant portion Earth's prokaryotic biomass residing in the rock-hosted biosphere, extending to depths several kilometers. This deep subsurface life lithosphere may host substantial amount biomass. However, more constrained estimates this are still lacking. In study, we first determine habitable volume lithospheric biosphere then estimate its potential Temperature, critical factor...

Abstract The subaerial exposure of the modern continental crust through time remains intensely debated, with estimates first ranging from late Archean to Neoproterozoic. To constrain when and how much was exposed subaerially during Earth's history, we trained a supervised machine learning model on compositions submerged basalts. Then, applied this well‐trained refined worldwide data set basaltic calculated mean proportions basalts erupted since 3.8 billion years ago (Ga). Our results suggest...