arXiv subjects

Guillermo Cabrera-Vives

Publications and source records attributed to Guillermo Cabrera-Vives.

28 records · Page 2Linked to original sources

arXiv2022

DELIGHT: Deep Learning Identification of Galaxy Hosts of Transients using Multi-resolution Images

We present DELIGHT, or Deep Learning Identification of Galaxy Hosts of Transients, a new algorithm designed to automatically and in real-time identify the host galaxies of extragalactic transients. The proposed algorithm receives as input compact, multi-resolution images centered at the position of a transient candidate and outputs two-dimensional offset vectors that connect the transient with the center of its predicted host. The multi-resolution input consists of a set of images with the same number of pixels, but with progressively larger pixel sizes and fields of view. A sample of \nSample galaxies visually identified by the ALeRCE broker team was used to train a convolutional neural network regression model. We show that this method is able to correctly identify both relatively large ($10\arcsec < r < 60\arcsec$) and small ($r \le 10\arcsec$) apparent size host galaxies using much less information (32 kB) than with a large, single-resolution image (920 kB). The proposed method has fewer catastrophic errors in recovering the position and is more complete and has less contamination ($< 0.86\%$) recovering the cross-matched redshift than other state-of-the-art methods. The more efficient representation provided by multi-resolution input images could allow for the identification of transient host galaxies in real-time, if adopted in alert streams from new generation of large etendue telescopes such as the Vera C. Rubin Observatory.

astro-ph.IM↗

arXiv2021

Alert Classification for the ALeRCE Broker System: The Real-time Stamp Classifier

We present a real-time stamp classifier of astronomical events for the ALeRCE (Automatic Learning for the Rapid Classification of Events) broker. The classifier is based on a convolutional neural network, trained on alerts ingested from the Zwicky Transient Facility (ZTF). Using only the \textit{science, reference} and \textit{difference} images of the first detection as inputs, along with the metadata of the alert as features, the classifier is able to correctly classify alerts from active galactic nuclei, supernovae (SNe), variable stars, asteroids and bogus classes, with high accuracy ($\sim$94\%) in a balanced test set. In order to find and analyze SN candidates selected by our classifier from the ZTF alert stream, we designed and deployed a visualization tool called SN Hunter, where relevant information about each possible SN is displayed for the experts to choose among candidates to report to the Transient Name Server database. From June 26th 2019 to February 28th 2021, we have reported 6846 SN candidates to date (11.8 candidates per day on average), of which 971 have been confirmed spectroscopically. Our ability to report objects using only a single detection means that 70\% of the reported SNe occurred within one day after the first detection. ALeRCE has only reported candidates not otherwise detected or selected by other groups, therefore adding new early transients to the bulk of objects available for early follow-up. Our work represents an important milestone toward rapid alert classifications with the next generation of large etendue telescopes, such as the Vera C. Rubin Observatory.

astro-ph.IM↗

arXiv2021

Matching Embeddings for Domain Adaptation

In this work we address the problem of transferring knowledge obtained from a vast annotated source domain to a low labeled target domain. We propose Adversarial Variational Domain Adaptation (AVDA), a semi-supervised domain adaptation method based on deep variational embedded representations. We use approximate inference and domain adversarial methods to map samples from source and target domains into an aligned class-dependent embedding defined as a Gaussian Mixture Model. AVDA works as a classifier and considers a generative model that helps this classification. We used digits dataset for experimentation. Our results show that on a semi-supervised few-shot scenario our model outperforms previous methods in most of the adaptation tasks, even using a fewer number of labeled samples per class on target domain.

cs.LG↗

arXiv2018

Labeling Bias in Galaxy Morphologies

We present a metric to quantify systematic labeling bias in galaxy morphology data sets stemming from the quality of the labeled data. This labeling bias is independent from labeling errors and requires knowledge about the intrinsic properties of the data with respect to the observed properties. We conduct a relative comparison of label bias for different low redshift galaxy morphology data sets. We show our metric is able to recover previous de-biasing procedures based on redshift as biasing parameter. By using the image resolution instead, we find biases that have not been addressed. We find that the morphologies based on supervised machine-learning trained over features such as colors, shape, and concentration show significantly less bias than morphologies based on expert or citizen-science classifiers. This result holds even when there is underlying bias present in the training sets used in the supervised machine learning process. We use catalog simulations to validate our bias metric, and show how to bin the multidimensional intrinsic and observed galaxy properties used in the bias quantification. Our approach is designed to work on any other labeled multidimensional data sets and the code is publicly available.

astro-ph.GA↗

arXiv2018

Deep Learning for Image Sequence Classification of Astronomical Events

We propose a new sequential classification model for astronomical objects based on a recurrent convolutional neural network (RCNN) which uses sequences of images as inputs. This approach avoids the computation of light curves or difference images. This is the first time that sequences of images are used directly for the classification of variable objects in astronomy. The second contribution of this work is the image simulation process. We generate synthetic image sequences that take into account the instrumental and observing conditions, obtaining a realistic, set of movies for each astronomical object. The simulated dataset is used to train our RCNN classifier. This approach allows us to generate datasets to train and test our RCNN model for different astronomical surveys and telescopes. We aim at building a simulated dataset whose distribution is close enough to the real dataset, so that a fine tuning could match the distributions between real and simulated dataset. To test the RCNN classifier trained with the synthetic dataset, we used real-world data from the High cadence Transient Survey (HiTS) obtaining an average recall of 85%, improved to 94% after performing fine tuning with 10 real samples per class. We compare the results of our model with those of a light curve random forest classifier. The proposed RCNN with fine tuning has a similar performance on the HiTS dataset compared to the light curve classifier, trained on an augmented training set with 10 real samples per class. The RCNN approach presents several advantages in an alert stream classification scenario, such as a reduction of the data pre-processing, faster online evaluation and easier performance improvement using a few real data samples. These results encourage us to use this method for alert brokers systems that will process alert streams generated by new telescopes such as the Large Synoptic Survey Telescope.

astro-ph.IM↗

arXiv2018

Multiband galaxy morphologies for CLASH: a convolutional neural network transferred from CANDELS

We present visual-like morphologies over 16 photometric bands, from ultra-violet to near infrared, for 8,412 galaxies in the Cluster Lensing And Supernova survey with Hubble (CLASH) obtained by a convolutional neural network (CNN) model. Our model follows the CANDELS main morphological classification scheme, obtaining the probability for each galaxy at each CLASH band of being spheroid, disk, irregular, point source, or unclassifiable. Our catalog contains morphologies for each galaxy with Hmag < 24.5 in every filter where the galaxy is observed. We trained an initial CNN model using approximately 7,500 expert eyeball labels from The Cosmic Assembly Near-IR Deep Extragalactic Legacy Survey (CANDELS). We created eyeball labels for 100 randomly selected galaxies per each of the 16-filters set of CLASH (1,600 galaxy images in total), where each image was classified by at least five of us. We use these labels to fine-tune the network in order to accurately predict labels for the CLASH data and to evaluate the performance of our model. We achieve a root-mean-square error of 0.0991 on the test set. We show that our proposed fine-tuning technique reduces the number of labeled images needed for training, as compared to directly training over the CLASH data, and achieves a better performance. This approach is very useful to minimize eyeball labeling efforts when classifying unlabeled data from new surveys. This will become particularly useful for massive datasets such as the ones coming from near future surveys such as EUCLID or the LSST. Our catalog consists of prediction of probabilities for each galaxy by morphology in their different bands and is made publicly available at http://www.inf.udec.cl/~guille/data/Deep-CLASH.csv.

astro-ph.IM↗

arXiv2018

The High Cadence Transient Survey (HITS): Compilation and characterization of light-curve catalogs

The High Cadence Transient Survey (HiTS) aims to discover and study transient objects with characteristic timescales between hours and days, such as pulsating, eclipsing and exploding stars. This survey represents a unique laboratory to explore large etendue observations from cadences of about 0.1 days and to test new computational tools for the analysis of large data. This work follows a fully \textit{Data Science} approach: from the raw data to the analysis and classification of variable sources. We compile a catalog of ${\sim}15$ million object detections and a catalog of ${\sim}2.5$ million light-curves classified by variability. The typical depth of the survey is $24.2$, $24.3$, $24.1$ and $23.8$ in $u$, $g$, $r$ and $i$ bands, respectively. We classified all point-like non-moving sources by first extracting features from their light-curves and then applying a Random Forest classifier. For the classification, we used a training set constructed using a combination of cross-matched catalogs, visual inspection, transfer/active learning and data augmentation. The classification model consists of several Random Forest classifiers organized in a hierarchical scheme. The classifier accuracy estimated on a test set is approximately $97\%$. In the unlabeled data, $3\,485$ sources were classified as variables, of which $1\,321$ were classified as periodic. Among the periodic classes we discovered with high confidence, 1 $δ$-scutti, 39 eclipsing binaries, 48 rotational variables and 90 RR-Lyrae and for the non-periodic classes we discovered 1 cataclysmic variables, 630 QSO, and 1 supernova candidates. The first data release can be accessed in the project archive of HiTS.

astro-ph.IM↗

arXiv2018

Enhanced Rotational Invariant Convolutional Neural Network for Supernovae Detection

In this paper, we propose an enhanced CNN model for detecting supernovae (SNe). This is done by applying a new method for obtaining rotational invariance that exploits cyclic symmetry. In addition, we use a visualization approach, the layer-wise relevance propagation (LRP) method, which allows finding the relevant pixels in each image that contribute to discriminate between SN candidates and artifacts. We introduce a measure to assess quantitatively the effect of the rotational invariant methods on the LRP relevance heatmaps. This allows comparing the proposed method, CAP, with the original Deep-HiTS model. The results show that the enhanced method presents an augmented capacity for achieving rotational invariance with respect to the original model. An ensemble of CAP models obtained the best results so far on the HiTS dataset, reaching an average accuracy of 99.53%. The improvement over Deep-HiTS is significant both statistically and in practice.

astro-ph.IM↗

arXiv2017

Deep-HiTS: Rotation Invariant Convolutional Neural Network for Transient Detection

We introduce Deep-HiTS, a rotation invariant convolutional neural network (CNN) model for classifying images of transients candidates into artifacts or real sources for the High cadence Transient Survey (HiTS). CNNs have the advantage of learning the features automatically from the data while achieving high performance. We compare our CNN model against a feature engineering approach using random forests (RF). We show that our CNN significantly outperforms the RF model reducing the error by almost half. Furthermore, for a fixed number of approximately 2,000 allowed false transient candidates per night we are able to reduce the miss-classified real transients by approximately 1/5. To the best of our knowledge, this is the first time CNNs have been used to detect astronomical transient events. Our approach will be very useful when processing images from next generation instruments such as the Large Synoptic Survey Telescope (LSST). We have made all our code and data available to the community for the sake of allowing further developments and comparisons at https://github.com/guille-c/Deep-HiTS.

astro-ph.IM↗

arXiv2015

The morphologies of massive galaxies from z~3 - Witnessing the 2 channels of bulge growth

[abridged] We quantify the morphological evolution of z~0 massive galaxies ($M*/M_\odot\sim10^{11}$) from z~3 in the 5 CANDELS fields. The progenitors are selected using abundance matching techniques to account for the mass growth. The morphologies strongly evolve from z~3. At z<1, the population matches the massive end of the Hubble sequence, with 30% of spheroids, 50% of galaxies with equally dominant disk and bulge components and 20% of disks. At z~2-3 there is a majority of irregular systems (~60-70%) with still 30% of spheroids. We then analyze the SFRs, gas fractions and structural properties for the different morphologies independently. Our results suggest two distinct channels for the growth of bulges in massive galaxies. Around 30-40% were already bulges at z~2.5, with low average SFRs and gas-fractions (10-15%), high Sersic indices (n>3-4) and small effective radii ($R_e$~1 kpc) pointing towards an early formation through gas-rich mergers or VDI. Between z~ 2.5 and z~0, they rapidly increase their size by a factor of ~4-5, become all passive but their global morphology remains unaltered. The structural evolution is independent of the gas fractions, suggesting that it is driven by ex-situ events. The remaining 60% experience a gradual morphological transformation, from clumpy disks to more regular bulge+disks systems, essentially happening at z>1. It results in the growth of a significant bulge component (n~3) for 2/3 of the systems possibly through the migration of clumps while the remaining 1/3 keeps a rather small bulge (n~1.5-2). The transition phase between disturbed and relaxed systems and the emergence of the bulge is correlated with a decrease of the star formation activity and the gas fractions. The growth of the effective radii scales roughly with $H(z)^{-1}$ and it is therefore consistent with the expected growth of disks in galaxy haloes.

astro-ph.GA↗