Related papers: Understanding Molecular Abundances in Star-Forming…
Interpretability is a pressing issue for machine learning. Common approaches to interpretable machine learning constrain interactions between features of the input, rendering the effects of those features on a model's output comprehensible…
We study the metallicities and abundance ratios of early-type galaxies in cosmological semi-analytic models (SAMs) within the hierarchical galaxy formation paradigm. To achieve this we implemented a detailed galactic chemical evolution…
The widespread adoption of encrypted communication protocols such as HTTPS and TLS has enhanced data privacy but also rendered traditional anomaly detection techniques less effective, as they often rely on inspecting unencrypted payloads.…
While the best tracer of the molecular component and its dynamics in galaxies is the CO molecule, which excitation is revealed by its isotopic and (2-1)/(1-0) ratios, the denser gas is revealed by molecules such as HCN, HNC, HCO+ or CN,…
The combination of photometry, spectroscopy and spectropolarimetry of the chemically peculiar stars often aims to study the complex physical phenomena such as stellar pulsation, chemical inhomogeneity, magnetic field and their interplay…
Note that a newer expanded version of this paper is now available at: arXiv:1802.03888 It is critical in many applications to understand what features are important for a model, and why individual predictions were made. For tree ensemble…
Understanding the gas abundance distribution is essential when tracing star formation using molecular line observations. Changing density and temperature conditions cause gas to freeze-out onto dust grains, and this needs to be taken into…
An important technique to explore a black-box machine learning (ML) model is called SHAP (SHapley Additive exPlanation). SHAP values decompose predictions into contributions of the features in a fair way. We will show that for a boosted…
We applied machine learning to the entire data history of ESO's High Accuracy Radial Velocity Planet Searcher (HARPS) instrument. Our primary goal was to recover the physical properties of the observed objects, with a secondary emphasis on…
Feature attribution methods have become essential for explaining machine learning models. Many popular approaches, such as SHAP and Banzhaf values, are grounded in power indices from cooperative game theory, which measure the contribution…
We investigate the connection between galaxies, dark matter halos, and their large-scale environments at $z=0$ with Illustris TNG300 hydrodynamic simulation data. We predict stellar masses from subhalo properties to test two types of…
We simulate the formation and chemodynamical evolution of 128 elliptical galaxies using a GRAPE-SPH code that includes various physical processes that are associated with the formation of stellar systems: radiative cooling, star formation,…
We develop a new method to account for the finite lifetimes of stars and trace individual abundances within a semi-analytic model of galaxy formation. At variance with previous methods, based on the storage of the (binned) past star…
SHAP explanations are a popular feature-attribution mechanism for explainable AI. They use game-theoretic notions to measure the influence of individual features on the prediction of a machine learning model. Despite a lot of recent…
We investigate the response of outer radiation belt electron fluxes to different solar wind and geomagnetic indices using an interpretable machine learning method. We reconstruct the electron flux variation during 19 enhancement and 7…
We present a neural-network emulator for the thermal and chemical evolution in Population III star formation. The emulator accurately reproduces the thermochemical evolution over a wide density range spanning 21 orders of magnitude…
Fault detection and diagnosis is significant for reducing maintenance costs and improving health and safety in chemical processes. Convolution neural network (CNN) is a popular deep learning algorithm with many successful applications in…
Fully cosmological, high resolution N-Body + SPH simulations are used to investigate the chemical abundance trends of stars in simulated stellar halos as a function of their origin. These simulations employ a physically motivated supernova…
Astrochemical models are important tools to interpret observations of molecular and atomic species in different environments. However, these models are time-consuming, precluding a thorough exploration of the parameter space, leading to…
We propose a new method for determination of element abundances in stellar atmospheres aimed for the automatic processing of high-quality stellar spectra. The pan-spectral method is based on weighted cumulative line-widths Q of studied…