There has been a significant increase in the amount and accuracy of mineral data (from resources like Mindat, MED or the GEMI) and the improvements in technological resources make it possible to explore and answer large, outstanding scientific questions, such as, understanding the mineral assemblages on Earth and how they compare to assemblages and localities on other planets. In the last couple of years, affinity analysis methods have been used to:1) Predict unreported minerals at an existing locality, 2) Predict localities for a set of known minerals[1]. We’ve chosen to call this application “Mineral Association Analysis”[2]. Affinity analysis is an unsupervised machine learning method that uses mined association rules to find interesting patterns in the data. Most of the metrics used to evaluate market basket analysis methods focus on either the ability of the model to ingest large amounts of data[3], or using a metric based comparison of various algorithms used for association rule mining[4], or on evaluating the rules mined to more efficiently generate association rules[5]. However, when patterns generated in an unsupervised method are used to predict the occurrences of entities such as minerals, there needs to be a way to evaluate the predictions made by the model. It’s in such an area that there has been very little work. In this abstract, we explore the development of a new method to evaluate the results of association rule mining algorithms specifically when used when the association rules generated are utilized in a predictive setting. [1] Prabhu et. al (2019). In AGU Fall Meeting Abstracts (EP23D-2286). [2] Morrison et al. Nat. Geo. (2021) In Prep. [3] Agrawal et al. (1993) SIGMOD’93. [4] Sharma et al. (2012) IJERT 1(06). [5] Üstündağ and Bal (2014) Proc. in Comp.

Subduction zones are the interface between Earth’s interior (crust and mantle) and exterior (atmosphere and oceans), where carbon and other volatiles are actively cycled between Earth reservoirs by plate tectonics. Helium is highly sensitive to mantle inputs and can be used to deconvolute mantle and crustal volatile pathways in arcs. We report He isotope and abundance data for 18 deeply-sourced gas seep samples in the Central Volcanic Zone (CVZ) of Argentina and the Southern Volcanic Zone (SVZ) of Chile. We use 4He/20Ne values to assess the extent of air contributions, as well as He concentrations. Air-corrected He isotopes from the CVZ range from 0.21 to 2.58 RA (n=7), with the highest value in the Puna and the lowest in the Sub-Andean foreland fold-and-thrust belt. 4He/20Ne values range from 1.7 to 546 and He contents range from 1.0 to 31 x 106 cm3STP/cm3. Air-corrected He isotopes from the SVZ range from 1.27 to 5.03 RA (n=7), 4He/20Ne values range from 0.3 to 69 and He contents range from 0.5 to 175 x 106 cm3STP/cm3). Taken together, these data reveal a clear southeastward increase in 3He/4He, with the highest values (in the SVZ) plotting below the nominal range of values associated with pure upper mantle He (8 ± 1 RA1), but approaching the mean He isotope value for arc gases of ~5.4 RA2. Notably, the lowest values are found in the CVZ, suggesting more significant crustal contributions to the He budget. The crustal thickness in the CVZ is up to 70 km, significantly more than in the SVZ, where it is just 35-45 km3. It thus appears that crustal thickness exerts a primary control on the extent of fluid-crust interaction, as helium and other volatiles rise through the upper plate in the Andean Convergent Margin. These data agree well with the findings of several previous studies4-14 conducted on the volatile geochemistry along the Andean Convergent Margin, which suggest a much smaller mantle influence, presumably associated with thicker crust masking the signal in the CVZ. [1] Graham, 2002 [2] Hilton et al., 2002 [3] Tassara and Echaurren, 2012 [4] Hilton et al., 1993 [5] Varekamp et al., 2006 [6] Ray et al., 2009 [7] Aguilera et al., 2012 [8] Tardani et al., 2016 [9] Tassi et al., 2016 [10] Tassi et al., 2017 [11] Peralta-Arnold et al., 2017 [12] Chiodi et al., 2019 [13] Inostroza et al., 2020 [14] Robidoux et al., 2020