Related papers: Understanding Molecular Abundances in Star-Forming…
While SHAP (SHapley Additive exPlanations) and other feature attribution methods are commonly employed to explain model predictions, their application within information retrieval (IR), particularly for complex outputs such as ranked lists,…
Understanding the connections between galaxy stellar mass, star formation rate, and dark matter halo mass represents a key goal of the theory of galaxy formation. Cosmological simulations that include hydrodynamics, physical treatments of…
Computational chemistry plays a relevant role in many astrochemical research fields, either by complementing experimental measurements or by deriving parameters difficult to be reproduced by laboratories. While the role of computational…
High quality archival spectra of interstellar absorption from C I toward 9 stars, taken with the Goddard High Resolution Spectrograph on the Hubble Space Telescope, were analyzed. Our sample was supplemented by two sight lines, 23 Ori and…
Nowadays, the interpretation of why a machine learning (ML) model makes certain inferences is as crucial as the accuracy of such inferences. Some ML models like the decision tree possess inherent interpretability that can be directly…
Massive stars play a key role in the evolution of the Universe. Our goal is to compare observed and predicted properties of single Galactic O stars to identify and constrain uncertain physical parameters and processes in stellar evolution…
Determining the physical parameters of pulsating variable stars such as RR Lyrae is essential for understanding their internal structure, pulsation mechanisms, and evolutionary state. In this study, we present a machine learning framework…
To fully harvest the rich library of stellar elemental abundance data available, we require reliable models that facilitate our interpretation of them. Galactic chemical evolution (GCE) models are one such set, and a key part of which are…
Attribution scores reflect how important the feature values in an input entity are for the output of a machine learning model. One of the most popular attribution scores is the SHAP score, which is an instantiation of the general Shapley…
The detailed chemical composition of stars is important in many astrophysical fields, among which the characterisation of exoplanetary systems. Previous studies seem to indicate an anomalous chemical pattern of the youngest stellar…
Atmospheric retrievals (AR) characterize exoplanets by estimating atmospheric parameters from observed light spectra, typically by framing the task as a Bayesian inference problem. However, traditional approaches such as nested sampling are…
Transparency of Machine Learning models used for decision support in various industries becomes essential for ensuring their ethical use. To that end, feature attribution methods such as SHAP (SHapley Additive exPlanations) are widely used…
Massive young stellar objects in the Magellanic Clouds show infrared absorption features corresponding to significant abundances of CO, CO$_2$ and H$_2$O ice along the line of sight, with the relative abundances of these ices differing…
The analysis of metal-rich HII regions has a profound impact on the calibration of abundance diagnostics widely used to measure the chemical content of star-forming galaxies, both locally and at high redshift. I review the main difficulties…
Machine Learning is an efficient method for analyzing and interpreting the increasing amount of astronomical data that is available. In this study, we show, a pedagogical approach that should benefit anyone willing to experiment with Deep…
A very popular model-agnostic technique for explaining predictive models is the SHapley Additive exPlanation (SHAP). The two most popular versions of SHAP are a conditional expectation version and an unconditional expectation version (the…
Missing data is a prevalent issue that can significantly impair model performance and explainability. This paper briefly summarizes the development of the field of missing data with respect to Explainable Artificial Intelligence and…
(Abridged) The abundance discrepancy problem in planetary nebulae (PNe) has long puzzled astronomers. NGC6153, with its high Abundance Discrepancy Factor (ADF~10), provides an opportunity to understand the chemical structure and ionisation…
Anomaly detection algorithms are often thought to be limited because they don't facilitate the process of validating results performed by domain experts. In Contrast, deep learning algorithms for anomaly detection, such as autoencoders,…
The interstellar medium of low-metallicity systems undergoing star formation will show chemical abundance inhomogeneities due to supernova events enriching the medium on a local scale. If the star formation time-scale is shorter than the…