International Conference on Machine Learning for Astrophysics 2nd Ed. - ML4ASTRO2

Session

FlashTalks

10 Jul 2024, 11:10

Aula Magna (Catania)

238. Enhancing X-ray Binary Analysis through Deep Learning

Antonio Tutone

10/07/2024, 11:10

X-ray binaries, systems composed of a star and a compact object, are pivotal to our understanding of astrophysical phenomena. However, the analysis of their X-ray spectra, critical for unlocking the secrets of these celestial bodies, is notoriously computationally intensive. Traditional approaches often struggle to keep pace with the voluminous data generated by observatories, a challenge set...

240. LightPred - a deep learning model for stellar properties predictions

Ilay Kamai

10/07/2024, 11:15

Stellar properties play an important role in understanding the evolution of stars, galaxies, and planetary systems. for example, stellar period is essential for understanding stars' age and stellar inclination is important for understanding planetary formation and dynamics. Despite their importance, it is not trivial to measure most of the stellar properties. On the other hand, since the...

242. Inferring stellar parameters and their uncertainties from high-resolution spectroscopy using conditional Invertible Neural Networks

Nils Candebat

10/07/2024, 11:20

Next generation instruments are prompting a revolutionary surge in collecting a wide variety of data, with an unprecedented advancement in our understanding of the Universe. The stellar community is actively adapting to this transformative era, trying to maximise the information obtainable from observational data, in particular stellar spectra. The next generation of multi-object spectrographs...

264. GWEEP: A Deep Learning Toolkit for Gravitational Waves Analysis

Daniel Tonoiu

10/07/2024, 11:25

As space exploration continues to expand, machine learning has proven many times to be an important item in our astrophysical data analysis toolbox, very elegantly navigating the challenges of high computational demands and the complexity of multi-dimensional parameter spaces that often occur when trying to process and understand the Universe's messages.
In this study, we have successfully...

243. Deep Learning-Based Visual-Binary Source Detection in Stamp Images from Multiple Surveys

Ilknur Gezer

10/07/2024, 11:35

We present a deep-learning approach for detecting visual-binary sources within 2.5 arcsecs in stamp images from various surveys. The aim is to develop a robust model that identifies the presence or absence of visual-binary sources. The process involves several stages including data preparation, model selection, training, evaluation, and deployment. Stamp images from multiple surveys are...

244. Early-stopping SOMs as a tool to classify SSOs in space surveys

Simone Sacquegna

10/07/2024, 11:40

Poster Presentation

Self-organizing maps (SOMs) are unsupervised machine learning techniques that reduce the dimensionality of the original dataset while preserving its topological structure. Their implementation can be represented as a transformation of n data points each with p variables as clusters of similar data on a two-dimensional map. This approach is widely used in astronomy due to the simplicity of the...

245. Inter-annotator consensus: optimizing machine learning for astrophysical feature segmentation and classification

Renaud Vancoellie

10/07/2024, 11:45

With the arrival of Euclid/LSST and other large-scale surveys we address the automatic detection and segmentation of galactic features from deep sky images. The training of machine learning and deep learning systems requires manual annotations, which tend to present a high variability between annotators.
For complex astrophysical features such as low surface brightness collision debris, even...

247. Automatic Modelling and Object Identification in Radio Astronomy

Richard Fuchs

10/07/2024, 11:50

Building appropriate models is crucial for imaging tasks in many fields, but often challenging due to the richness of the systems. In radio astronomy, for example, wide-field observations can contain various and superposed structures that require different descriptions, such as filaments, point sources or compact objects. This work presents an automatic pipeline that iteratively adapts models...

249. Morphological classification of radio sources in star-forming regions

Elena Díaz-Márquez

10/07/2024, 11:55

Radio continuum emission at centimeter wavelengths is found in association with young stellar objects (YSOs) throughout all stages of star formation, from deeply embedded Class 0 protostars to pre-main sequence Class III objects and thus, radio observations provide crucial insights into the formation and evolution of stars. In this work, we present a new approach implementing machine learning...

250. Target Selection for a redshift limited survey with Machine Learning

Gursharanjit Kaur

10/07/2024, 12:00

The WAVES survey of the upcoming multi object spectroscopy facility, 4MOST, has a key science goal of probing the halo mass function to fainter magnitudes as compared to previous surveys like GAMA. This objective, along with constraints on fibre-hour availability, shapes the criteria for selecting galaxies to be observed by WAVES, categorised into two sub-surveys: ""wide"" and ""deep"". The...

251. Spatially Variant Point Spread Functions for Bayesian Imaging

Vincent Eberle

10/07/2024, 12:10

When measuring photon counts from incoming sky fluxes, observatories imprint nuisance effects on the data that must be accurately removed. Some detector effects can be easily inverted, while others are not trivially invertible such as the point spread function and shot noise. Using information field theory and Bayes' theorem, we infer the posterior mean and uncertainty for the sky flux. This...

256. Predicting AGN Obscuration with Machine Learning

Ross Silver

10/07/2024, 12:15

I present a new method for predicting the line-of-sight column density (NH) values of Active Galactic Nuclei (AGN) based on mid-infrared (MIR), soft X-ray, and hard X-ray data.
We developed a multiple linear regression machine learning algorithm trained with WISE colors, Swift-BAT count rates, soft X-ray hardness ratios, and an MIR-soft X-ray flux ratio. The algorithm was trained off 451 AGN...

257. Galaxy stellar and total mass estimation using machine learning

Jiani Chu

10/07/2024, 12:20

I will talk about a successful proof of concept test on galaxy stellar and total mass estimation using machine learning. Conventional galaxy mass estimation methods suffer from model assumptions and degeneracies. Machine learning, which avoids many of assumption, can be a potential method to predict galaxy properties. In our work, we use a general sample of galaxies from the TNG100 simulation...

259. ULISSE: A tool for one-shot sky exploration and its application for detection of AGN and galaxy properties.

Lars Doorenbos

10/07/2024, 12:25

We present ULISSE (aUtomatic Lightweight Intelligent System for Sky Exploration), a deep learning tool capable of identifying objects that share morphological and photometric properties with a query prototype based on a single image, effectively creating a list of lookalikes. ULISSE performs a similarity search directly using features extracted from the ImageNet dataset and identifies a list...

261. Bayesian Generative Strong Lensing with LensCharm

Matteo Guardiani

10/07/2024, 12:30

Strong gravitational lensing offers a unique view into the distant cosmos by probing directly the distribution of dark matter and providing independent constraints on the Hubble constant.
These research objectives call for the utmost precision in the estimation of the distributions of the lens mass and the source surface brightness. Recent strides in telescope technology promise to provide...

279. Unmasking the Hidden: Anomaly Detection in ASKAP’s Monitoring

Zhuowei Wang

10/07/2024, 12:35

This study explores the intersection of astronomy and human-machine collaboration, focusing on their transformative role in our exploration of the universe. We examine the Australian Square Kilometre Array Pathfinder (ASKAP) and its monitoring data's crucial role in advancing astronomical discoveries. However, ASKAP's success in charting unprecedented numbers of galaxies presents the challenge...