arXiv subjects

Massimo Brescia

Publications and source records attributed to Massimo Brescia.

At least 37 records · Page 2Linked to original sources

arXiv2024

Identification of problematic epochs in astronomical time series through transfer learning

We present a novel method for detecting outliers in astronomical time series based on the combination of a deep neural network and a k-nearest neighbor algorithm with the aim of identifying and removing problematic epochs in the light curves of astronomical objects. We use an EfficientNet network pre-trained on ImageNet as a feature extractor and perform a k-nearest neighbor search in the resulting feature space to measure the distance from the first neighbor for each image. If the distance is above the one obtained for a stacked image, we flag the image as a potential outlier. We apply our method to time series obtained from the VLT Survey Telescope (VST) monitoring campaign of the Deep Drilling Fields of the Vera C. Rubin Legacy Survey of Space and Time (LSST). We show that our method can effectively identify and remove artifacts from the VST time series and improve the quality and reliability of the data. This approach may prove very useful in sight of the amount of data that will be provided by the LSST, which will prevent the inspection of individual light curves. We also discuss the advantages and limitations of our method and suggest possible directions for future work.

astro-ph.IM↗

arXiv2023

VST-GAME: Galaxy Assembly as a function of Mass and Environment with VST. Photometric assessment and density field of MACSJ0416

Observational studies have widely demonstrated that galaxy physical properties are strongly affected by the surrounding environment. On one side, gas inflows provide galaxies with new fuel for star formation. On the other side, the high temperatures and densities of the medium are expected to induce quenching in the star formation. Observations of large structures, in particular filaments at the cluster outskirts (r>2r$_{200}$), are currently limited to the low redshift Universe. We present a multi-band dataset for the cluster MACS J0416.1-2403 (z=0.397), observed in the context of the Galaxy Assembly as a function of Mass and Environment with VST (VST-GAME) survey. The project aims at gathering deep ($r$<24.4) and wide (20x20Mpc$^2$) observations at optical wavelengths for six massive galaxy clusters at 0.2<z<0.6, complemented with near infrared data. This work describes the photometric analysis of the cluster, defines a density field and studies galaxy properties in the cluster outskirts. We extract sources paying particular attention to recover the faintest ones. We combine all the extractions in a multi-band catalog and compute photometric redshifts. We then define cluster memberships up to 5r$_{200}$ from the cluster core and measure the density field, comparing galaxy properties in different environments. We found that the $g-r$ colors show bimodal behaviours in all the environments, but the peak of the distribution of red galaxies shifts toward redder colors with increasing density and the fraction of galaxies in the blue cloud increases with decreasing density. We also found 3 overdense regions in the cluster outskirts at r$\sim$5r$_{200}$. The color of galaxies suggests the presence of evolved galaxy populations, an insight for pre-processing phenomena over these substructures. We release the multi-band catalog, down to the completeness limit $r$<24.4 mag.

astro-ph.GA↗

arXiv2022

Generating astronomical spectra from photometry with conditional diffusion models

A trade-off between speed and information controls our understanding of astronomical objects. Fast-to-acquire photometric observations provide global properties, while costly and time-consuming spectroscopic measurements enable a better understanding of the physics governing their evolution. Here, we tackle this problem by generating spectra directly from photometry, through which we obtain an estimate of their intricacies from easily acquired images. This is done by using multi-modal conditional diffusion models, where the best out of the generated spectra is selected with a contrastive network. Initial experiments on minimally processed SDSS galaxy data show promising results.

astro-ph.IM↗

arXiv2022

ULISSE: A Tool for One-shot Sky Exploration and its Application to Active Galactic Nuclei Detection

Modern sky surveys are producing ever larger amounts of observational data, which makes the application of classical approaches for the classification and analysis of objects challenging and time-consuming. However, this issue may be significantly mitigated by the application of automatic machine and deep learning methods. We propose ULISSE, a new deep learning tool that, starting from a single prototype object, is capable of identifying objects sharing the same morphological and photometric properties, and hence of creating a list of candidate sosia. In this work, we focus on applying our method to the detection of AGN candidates in a Sloan Digital Sky Survey galaxy sample, since the identification and classification of Active Galactic Nuclei (AGN) in the optical band still remains a challenging task in extragalactic astronomy. Intended for the initial exploration of large sky surveys, ULISSE directly uses features extracted from the ImageNet dataset to perform a similarity search. The method is capable of rapidly identifying a list of candidates, starting from only a single image of a given prototype, without the need for any time-consuming neural network training. Our experiments show ULISSE is able to identify AGN candidates based on a combination of host galaxy morphology, color and the presence of a central nuclear source, with a retrieval efficiency ranging from 21% to 65% (including composite sources) depending on the prototype, where the random guess baseline is 12%. We find ULISSE to be most effective in retrieving AGN in early-type host galaxies, as opposed to prototypes with spiral- or late-type properties. Based on the results described in this work, ULISSE can be a promising tool for selecting different types of astrophysical objects in current and future wide-field surveys (e.g. Euclid, LSST etc.) that target millions of sources every single night.

astro-ph.IM↗

arXiv2022

Galaxy morphoto-Z with neural Networks (GaZNets). I. Optimized accuracy and outlier fraction from Imaging and Photometry

In the era of large sky surveys, photometric redshifts (photo-z) represent crucial information for galaxy evolution and cosmology studies. In this work, we propose a new Machine Learning (ML) tool called Galaxy morphoto-Z with neural Networks (GaZNet-1), which uses both images and multi-band photometry measurements to predict galaxy redshifts, with accuracy, precision and outlier fraction superior to standard methods based on photometry only. As a first application of this tool, we estimate photo-z of a sample of galaxies in the Kilo-Degree Survey (KiDS). GaZNet-1 is trained and tested on $\sim140 000$ galaxies collected from KiDS Data Release 4 (DR4), for which spectroscopic redshifts are available from different surveys. This sample is dominated by bright (MAG$\_$AUTO$<21$) and low redshift ($z < 0.8$) systems, however, we could use $\sim$ 6500 galaxies in the range $0.8 < z < 3$ to effectively extend the training to higher redshift. The inputs are the r-band galaxy images plus the 9-band magnitudes and colours, from the combined catalogs of optical photometry from KiDS and near-infrared photometry from the VISTA Kilo-degree Infrared survey. By combining the images and catalogs, GaZNet-1 can achieve extremely high precision in normalized median absolute deviation (NMAD=0.014 for lower redshift and NMAD=0.041 for higher redshift galaxies) and low fraction of outliers ($0.4$\% for lower and $1.27$\% for higher redshift galaxies). Compared to ML codes using only photometry as input, GaZNet-1 also shows a $\sim 10-35$% improvement in precision at different redshifts and a $\sim$ 45% reduction in the fraction of outliers. We finally discuss that, by correctly separating galaxies from stars and active galactic nuclei, the overall photo-z outlier fraction of galaxies can be cut down to $0.3$\%.

astro-ph.GA↗

arXiv2021

The LSST-DESC 3x2pt Tomography Optimization Challenge

This paper presents the results of the Rubin Observatory Dark Energy Science Collaboration (DESC) 3x2pt tomography challenge, which served as a first step toward optimizing the tomographic binning strategy for the main DESC analysis. The task of choosing an optimal tomographic binning scheme for a photometric survey is made particularly delicate in the context of a metacalibrated lensing catalogue, as only the photometry from the bands included in the metacalibration process (usually riz and potentially g) can be used in sample definition. The goal of the challenge was to collect and compare bin assignment strategies under various metrics of a standard 3x2pt cosmology analysis in a highly idealized setting to establish a baseline for realistically complex follow-up studies; in this preliminary study, we used two sets of cosmological simulations of galaxy redshifts and photometry under a simple noise model neglecting photometric outliers and variation in observing conditions, and contributed algorithms were provided with a representative and complete training set. We review and evaluate the entries to the challenge, finding that even from this limited photometry information, multiple algorithms can separate tomographic bins reasonably well, reaching figures-of-merit scores close to the attainable maximum. We further find that adding the g band to riz photometry improves metric performance by ~15% and that the optimal bin assignment strategy depends strongly on the science case: which figure-of-merit is to be optimized, and which observables (clustering, lensing, or both) are included.

astro-ph.IM↗

arXiv2021

Improving the reliability of photometric redshift with machine learning

In order to answer the open questions of modern cosmology and galaxy evolution theory, robust algorithms for calculating photometric redshifts (photo-z) for very large samples of galaxies are needed. Correct estimation of the various photo-z algorithms' performance requires attention to both the performance metrics and the data used for the estimation. In this work, we use the supervised machine learning algorithm MLPQNA to calculate photometric redshifts for the galaxies in the COSMOS2015 catalogue and the unsupervised Self-Organizing Maps (SOM) to determine the reliability of the resulting estimates. We find that for spec-z<1.2, photo-z predictions are on the same level of quality as SED fitting photo-z. We show that the SOM successfully detects unreliable spec-z that cause biases in the estimation of the photo-z algorithms' performance. Additionally, we use SOM to select the objects with reliable photo-z predictions. Our cleaning procedures allow to extract the subset of objects for which the quality of the final photo-z catalogs is improved by a factor of two, compared to the overall statistics.

astro-ph.IM↗

arXiv2021

Photometric redshifts with machine learning, lights and shadows on a complex data science use case

The current role of data-driven science is constantly increasing its importance within Astrophysics, due to the huge amount of multi-wavelength data collected every day, characterized by complex and high-volume information requiring efficient and as much as possible automated exploration tools. Furthermore, to accomplish main and legacy science objectives of future or incoming large and deep survey projects, such as JWST, LSST and Euclid, a crucial role is played by an accurate estimation of photometric redshifts, whose knowledge would permit the detection and analysis of extended and peculiar sources by disentangling low-z from high-z sources and would contribute to solve the modern cosmological discrepancies. The recent photometric redshift data challenges, organized within several survey projects, like LSST and Euclid, pushed the exploitation of multi-wavelength and multi-dimensional data observed or ad hoc simulated to improve and optimize the photometric redshifts prediction and statistical characterization based on both SED template fitting and machine learning methodologies. But they also provided a new impetus in the investigation on hybrid and deep learning techniques, aimed at conjugating the positive peculiarities of different methodologies, thus optimizing the estimation accuracy and maximizing the photometric range coverage, particularly important in the high-z regime, where the spectroscopic ground truth is poorly available. In such a context we summarize what learned and proposed in more than a decade of research.

astro-ph.IM↗

arXiv2021

A novel approach to the classification of terrestrial drainage networks based on deep learning and preliminary results on Solar System bodies

Several approaches were proposed to describe the geomorphology of drainage networks and the abiotic/biotic factors determining their morphology. There is an intrinsic complexity of the explicit qualification of the morphological variations in response to various types of control factors and the difficulty of expressing the cause-effect links. Traditional methods of drainage network classification are based on the manual extraction of key characteristics, then applied as pattern recognition schemes. These approaches, however, have low predictive and uniform ability. We present a different approach, based on the data-driven supervised learning by images, extended also to extraterrestrial cases. With deep learning models, the extraction and classification phase is integrated within a more objective, analytical, and automatic framework. Despite the initial difficulties, due to the small number of training images available, and the similarity between the different shapes of the drainage samples, we obtained successful results, concluding that deep learning is a valid way for data exploration in geomorphology and related fields.

physics.geo-ph↗

arXiv2020

Rejection criteria based on outliers in the KiDS photometric redshifts and PDF distributions derived by machine learning

The Probability Density Function (PDF) provides an estimate of the photometric redshift (zphot) prediction error. It is crucial for current and future sky surveys, characterized by strict requirements on the zphot precision, reliability and completeness. The present work stands on the assumption that properly defined rejection criteria, capable of identifying and rejecting potential outliers, can increase the precision of zphot estimates and of their cumulative PDF, without sacrificing much in terms of completeness of the sample. We provide a way to assess rejection through proper cuts on the shape descriptors of a PDF, such as the width and the height of the maximum PDF's peak. In this work we tested these rejection criteria to galaxies with photometry extracted from the Kilo Degree Survey (KiDS) ESO Data Release 4, proving that such approach could lead to significant improvements to the zphot quality: e.g., for the clipped sample showing the best trade-off between precision and completeness, we achieve a reduction in outliers fraction of $\simeq 75\%$ and an improvement of $\simeq 6\%$ for NMAD, with respect to the original data set, preserving the $\simeq 93\%$ of its content.

astro-ph.IM↗

arXiv2020

Periodic Astrometric Signal Recovery through Convolutional Autoencoders

Astrometric detection involves a precise measurement of stellar positions, and is widely regarded as the leading concept presently ready to find earth-mass planets in temperate orbits around nearby sun-like stars. The TOLIMAN space telescope[39] is a low-cost, agile mission concept dedicated to narrow-angle astrometric monitoring of bright binary stars. In particular the mission will be optimised to search for habitable-zone planets around Alpha Centauri AB. If the separation between these two stars can be monitored with sufficient precision, tiny perturbations due to the gravitational tug from an unseen planet can be witnessed and, given the configuration of the optical system, the scale of the shifts in the image plane are about one millionth of a pixel. Image registration at this level of precision has never been demonstrated (to our knowledge) in any setting within science. In this paper we demonstrate that a Deep Convolutional Auto-Encoder is able to retrieve such a signal from simplified simulations of the TOLIMAN data and we present the full experimental pipeline to recreate out experiments from the simulations to the signal analysis. In future works, all the more realistic sources of noise and systematic effects present in the real-world system will be injected into the simulations.

astro-ph.IM↗

arXiv2020

Anomaly detection in Astrophysics: a comparison between unsupervised Deep and Machine Learning on KiDS data

Every field of Science is undergoing unprecedented changes in the discovery process, and Astronomy has been a main player in this transition since the beginning. The ongoing and future large and complex multi-messenger sky surveys impose a wide exploiting of robust and efficient automated methods to classify the observed structures and to detect and characterize peculiar and unexpected sources. We performed a preliminary experiment on KiDS DR4 data, by applying to the problem of anomaly detection two different unsupervised machine learning algorithms, considered as potentially promising methods to detect peculiar sources, a Disentangled Convolutional Autoencoder and an Unsupervised Random Forest. The former method, working directly on images, is considered potentially able to identify peculiar objects like interacting galaxies and gravitational lenses. The latter instead, working on catalogue data, could identify objects with unusual values of magnitudes and colours, which in turn could indicate the presence of singularities.

astro-ph.IM↗

arXiv2020

Comparison of outlier detection methods on astronomical image data

Among the many challenges posed by the huge data volumes produced by the new generation of astronomical instruments there is also the search for rare and peculiar objects. Unsupervised outlier detection algorithms may provide a viable solution. In this work we compare the performances of six methods: the Local Outlier Factor, Isolation Forest, k-means clustering, a measure of novelty, and both a normal and a convolutional autoencoder. These methods were applied to data extracted from SDSS stripe 82. After discussing the sensitivity of each method to its own set of hyperparameters, we combine the results from each method to rank the objects and produce a final list of outliers.

astro-ph.IM↗

arXiv2020

Building the largest spectroscopic sample of ultra-compact massive galaxies with the Kilo Degree Survey

Ultra-compact massive galaxies UCMGs, i.e. galaxies with stellar masses $M_{*} > 8 \times 10^{10} M_{\odot}$ and effective radii $R_{e} < 1.5$ kpc, are very rare systems, in particular at low and intermediate redshifts. Their origin as well as their number density across cosmic time are still under scrutiny, especially because of the paucity of spectroscopically confirmed samples. We have started a systematic census of UCMG candidates within the ESO Kilo Degree Survey, together with a large spectroscopic follow-up campaign to build the largest possible sample of confirmed UCMGs. This is the third paper of the series and the second based on the spectroscopic follow-up program. Here, we present photometrical and structural parameters of 33 new candidates at redshifts $0.15 \lesssim z \lesssim 0.5$ and confirm 19 of them as UCMGs, based on their nominal spectroscopically inferred $M_{*}$ and $R_{e}$. This corresponds to a success rate of $\sim 58\%$, nicely consistent with our previous findings. The addition of these 19 newly confirmed objects, allows us to fully assess the systematics on the system selection, and finally reduce the number density uncertainties. Moreover, putting together the results from our current and past observational campaigns and some literature data, we build the largest sample of UCMGs ever collected, comprising 92 spectroscopically confirmed objects at $0.1 \lesssim z \lesssim 0.5$. This number raises to 116, allowing for a $3σ$ tolerance on the $M_{*}$ and $R_{e}$ thresholds for the UCMG definition. For all these galaxies we have estimated the velocity dispersion values at the effective radii which have been used to derive a preliminary mass-velocity dispersion correlation.

astro-ph.GA↗

arXiv2019

Astroinformatics based search for globular clusters in the Fornax Deep Survey

In the last years, Astroinformatics has become a well defined paradigm for many fields of Astronomy. In this work we demonstrate the potential of a multidisciplinary approach to identify globular clusters (GCs) in the Fornax cluster of galaxies taking advantage of multi-band photometry produced by the VLT Survey Telescope using automatic self-adaptive methodologies. The data analyzed in this work consist of deep, multi-band, partially overlapping images centered on the core of the Fornax cluster. In this work we use a Neural-Gas model, a pure clustering machine learning methodology, to approach the GC detection, while a novel feature selection method ($Φ$LAB) is exploited to perform the parameter space analysis and optimization. We demonstrate that the use of an Astroinformatics based methodology is able to provide GC samples that are comparable, in terms of purity and completeness with those obtained using single band HST data (Brescia et al. 2012) and two approaches based respectively on a morpho-photometric (Cantiello et al. 2018b) and a PCA analysis (D'Abrusco et al. 2015) using the same data discussed in this work.

astro-ph.IM↗

arXiv2019

Stellar formation rates in galaxies using Machine Learning models

Global Stellar Formation Rates or SFRs are crucial to constrain theories of galaxy formation and evolution. SFR's are usually estimated via spectroscopic observations which require too much previous telescope time and therefore cannot match the needs of modern precision cosmology. We therefore propose a novel method to estimate SFRs for large samples of galaxies using a variety of supervised ML models.

astro-ph.IM↗

arXiv2018

Statistical analysis of probability density functions for photometric redshifts through the KiDS-ESO-DR3 galaxies

Despite the high accuracy of photometric redshifts (zphot) derived using Machine Learning (ML) methods, the quantification of errors through reliable and accurate Probability Density Functions (PDFs) is still an open problem. First, because it is difficult to accurately assess the contribution from different sources of errors, namely internal to the method itself and from the photometric features defining the available parameter space. Second, because the problem of defining a robust statistical method, always able to quantify and qualify the PDF estimation validity, is still an open issue. We present a comparison among PDFs obtained using three different methods on the same data set: two ML techniques, METAPHOR (Machine-learning Estimation Tool for Accurate PHOtometric Redshifts) and ANNz2, plus the spectral energy distribution template fitting method, BPZ. The photometric data were extracted from the KiDS (Kilo Degree Survey) ESO Data Release 3, while the spectroscopy was obtained from the GAMA (Galaxy and Mass Assembly) Data Release 2. The statistical evaluation of both individual and stacked PDFs was done through quantitative and qualitative estimators, including a dummy PDF, useful to verify whether different statistical estimators can correctly assess PDF quality. We conclude that, in order to quantify the reliability and accuracy of any zphot PDF method, a combined set of statistical estimators is required.

astro-ph.IM↗

arXiv2018

Data Deluge in Astrophysics: Photometric Redshifts as a Template Use Case

Astronomy has entered the big data era and Machine Learning based methods have found widespread use in a large variety of astronomical applications. This is demonstrated by the recent huge increase in the number of publications making use of this new approach. The usage of machine learning methods, however is still far from trivial and many problems still need to be solved. Using the evaluation of photometric redshifts as a case study, we outline the main problems and some ongoing efforts to solve them.

astro-ph.IM↗