We apply a new deep learning technique to detect, classify, and deblend sources in multi-band astronomical images. We train and evaluate the performance of an artificial neural network built on the Mask R-CNN image processing framework, a general code for efficient object detection, classification, and instance segmentation. After evaluating the performance of our network against simulated ground truth images for star and galaxy classes, we find a precision of 92% at 80% recall for stars and a precision of 98% at 80% recall for galaxies in a typical field with $\sim30$ galaxies/arcmin$^2$. We investigate the deblending capability of our code, and find that clean deblends are handled robustly during object masking, even for significantly blended sources. This technique, or extensions using similar network architectures, may be applied to current and future deep imaging surveys such as LSST and WFIRST. Our code, Astro R-CNN, is publicly available at https://github.com/burke86/astro_rcnn.
Astronomical source deblending is the process of separating the contribution of individual stars or galaxies (sources) to an image comprised of multiple, possibly overlapping sources. Astronomical sources display a wide range of sizes and brightnesses and may show substantial overlap in images. Astronomical imaging data can further challenge off-the-shelf computer vision algorithms owing to its high dynamic range, low signal-to-noise ratio, and unconventional image format. These challenges make source deblending an open area of astronomical research, and in this work, we introduce a new approa…
We introduce a new algorithm for colour separation and deblending of multi-band astronomical images called MuSCADeT which is based on Morpho-spectral Component Analysis of multi-band images. The MuSCADeT algorithm takes advantage of the sparsity of astronomical objects in morphological dictionaries such as wavelets and their differences in spectral energy distribution (SED) across multi-band observations. This allows us to devise a model independent and automated approach to separate objects with different colours. We show with simulations that we are able to separate highly blended objects an…
Stacking analysis is a means of detecting faint sources using a priori position information to estimate an aggregate signal from individually undetected objects. Confusion severely limits the effectiveness of stacking in deep surveys with limited angular resolution, particularly at far infrared to submillimeter wavelengths, and causes a bias in stacking results. Deblending corrects measured fluxes for confusion from adjacent sources; however, we find that standard deblending methods only reduce the bias by roughly a factor of two while tripling the variance. We present an improved algorithm fo…
We present a new probabilistic method for detecting, deblending, and cataloging astronomical sources called the Bayesian Light Source Separator (BLISS). BLISS is based on deep generative models, which embed neural networks within a Bayesian model. For posterior inference, BLISS uses a new form of variational inference known as Forward Amortized Variational Inference. The BLISS inference routine is fast, requiring a single forward pass of the encoder networks on a GPU once the encoder networks are trained. BLISS can perform fully Bayesian inference on megapixel images in seconds, and produces h…
Fast and accurate astronomical source deblending with Density-Peak Clustering
INAF-Osservatorio Astronomico di Trieste（的里雅斯特天文台）；Dipartimento di Matematica, Sezione di Matematica e Geoscienze, Università di Trieste（的里雅斯特大学数学与地球科学系）
We present a new neural network approach for deblending galaxy images in astronomical data using Residual Dense Neural network (RDN) architecture. We train the network on synthetic galaxy images similar to the typical arrangements of field galaxies with a finite point spread function (PSF) and realistic noise levels. The main novelty of our approach is the usage of two distinct neural networks: i) a deblending network which isolates a single galaxy postage stamp from the composite and, ii) a classifier network which counts the remaining number of galaxies. The deblending proceeds by iterativel…
Simulation-Based Inference for Probabilistic Galaxy Detection and Deblending
University of Maryland, College Park（马里兰大学帕克分校）；University of Michigan（密歇根大学）；Leinweber Institute for Theoretical Physics, University of Michigan（密歇根大学莱因韦伯理论物理研究所）；The Voleon Group（Voleon集团）；Carnegie Mellon University（卡内基梅隆大学）
We present an extension of the multi-band galaxy fitting method scarlet which allows the joint modeling of astronomical images from different instruments, by performing simultaneous resampling and convolution. We introduce a fast and formally accurate linear projection operation that maps a pixelated model at a given resolution onto an observation frame with a different point spread function and pixel scale. We test our implementation against the well-tested resampling and convolution method in galsim on simulated images mimicking observations with the Euclid space telescope and the Vera C. Ru…
Detection, Instance Segmentation, and Classification for Astronomical Surveys with Deep Learning (DeepDISC): Detectron2 Implementation and Demonstration with Hyper Suprime-Cam Data
We present AstroVaDEr, a variational autoencoder designed to perform unsupervised clustering and synthetic image generation using astronomical imaging catalogues. The model is a convolutional neural network that learns to embed images into a low dimensional latent space, and simultaneously optimises a Gaussian Mixture Model (GMM) on the embedded vectors to cluster the training data. By utilising variational inference, we are able to use the learned GMM as a statistical prior on the latent space to facilitate random sampling and generation of synthetic images. We demonstrate AstroVaDEr's capabi…
Jet Propulsion Laboratory（喷气推进实验室）；California Institute of Technology（加州理工学院）；Graduate Institute of Astronomy, NCU（国立中央大学天文研究所）；St. Thomas College（圣托马斯学院）；Università degli Studi Federico II（费德里科二世大学）
The amount of collected data in many scientific fields is increasing, all of them requiring a common task: extract knowledge from massive, multi parametric data sets, as rapidly and efficiently possible. This is especially true in astronomy where synoptic sky surveys are enabling new research frontiers in the time domain astronomy and posing several new object classification challenges in multi dimensional spaces; given the high number of parameters available for each object, feature selection is quickly becoming a crucial task in analyzing astronomical data sets. Using data sets extracted fro…
Universidad de los Andes（洛斯安第斯大学）；Center for Research and Formation in Artificial Intelligence（人工智能研究与培训中心）；Systems and Computing Engineering Department（系统与计算工程系）；Departamento de Física（物理系）
Supervised classification of temporal sequences of astronomical images into meaningful transient astrophysical phenomena has been considered a hard problem because it requires the intervention of human experts. The classifier uses the expert's knowledge to find heuristic features to process the images, for instance, by performing image subtraction or by extracting sparse information such as flux time series, also known as light curves. We present a successful deep learning approach that learns directly from imaging data. Our method models explicitly the spatio-temporal patterns with Deep Convo…
Temporal Stamp Classifier: Classifying Short Sequences of Astronomical Alerts
Universidad de Chile（智利大学）；Millennium Institute of Astrophysics（千年天体物理学研究所）；Data and Artificial Intelligence Initiative (IDIA), Universidad de Chile（智利大学数据与人工智能计划（IDIA））；Center for Mathematical Modeling (CMM), Universidad de Chile（智利大学数学建模中心（CMM））
The Euclid telescope, due for launch in 2021, will perform an imaging and slitless spectroscopy survey over half the sky, to map baryon wiggles and weak lensing. During the survey Euclid is expected to resolve 100,000 strong gravitational lens systems. This is ideal to find rare lens configurations, provided they can be identified reliably and on a reasonable timescale. For this reason we have developed a Convolutional Neural Network (CNN) that can be used to identify images containing lensing systems. CNNs have already been used for image and digit classification as well as being used in astr…
We present a two-component Machine Learning (ML) based approach for classifying astronomical images by data-quality via an examination of sources detected in the images and image pixel values from representative sources within those images. The first component, which uses a clustering algorithm, creates a proper and small fraction of the image pixels to determine the quality of the observation. The representative images (and associated tables) are ~800 times smaller than the original images, significantly reducing the time required to train our algorithm. The useful information in the images i…
The Zwicky Transient Facility (ZTF), a state-of-the-art optical robotic sky survey, registers on the order of a million transient events - such as supernova explosions, changes in brightness of variable sources, or moving object detections - every clear night, and generates associated real-time alerts. We present Alert-Classifying Artificial Intelligence (ACAI), an open-source deep-learning framework for the phenomenological classification of ZTF alerts. ACAI uses a set of five binary classifiers to characterize objects which, in combination with the auxiliary/contextual event information avai…
Argonne National Laboratory（阿贡国家实验室）；National Astronomical Observatories of China（中国科学院国家天文台）；University of California, Berkeley（加州大学伯克利分校）
Upcoming large astronomical surveys are expected to capture an unprecedented number of strong gravitational lensing systems. Deep learning is emerging as a promising practical tool for the detection and quantification of these galaxy-scale image distortions. The absence of large quantities of representative data from current astronomical surveys motivates the development of a robust forward-modeling approach using synthetic lensing images. Using a mock sample of strong lenses created upon a state-of-the-art extragalactic catalogs, we train a modular deep learning pipeline for uncertainty-quant…
Source finding is one of the most challenging tasks in upcoming radio continuum surveys with SKA precursors, such as the Evolutionary Map of the Universe (EMU) survey of the Australian SKA Pathfinder (ASKAP) telescope. The resolution, sensitivity, and sky coverage of such surveys is unprecedented, requiring new features and improvements to be made in existing source finders. Among them, reducing the false detection rate, particularly in the Galactic plane, and the ability to associate multiple disjoint islands into physical objects. To bridge this gap, we developed a new source finder, based o…
Finding and classifying astronomical sources is key in the scientific exploitation of radio surveys. Source-finding usually involves identifying the parts of an image belonging to an astronomical source, against some estimated background. This can be problematic in the radio regime, owing to the presence of correlated noise, which can interfere with the signal from the source. In the current work, we present ConvoSource, a novel method based on a deep learning technique, to identify the positions of radio sources, and compare the results to a Gaussian-fitting method. Since the deep learning ap…
Astronomical image time series classification using CONVolutional attENTION (ConvEntion)
University of Montpellier（蒙彼利埃大学）；University of Nimes（尼姆大学）；Aix Marseille Univ（艾克斯-马赛大学）；Paul Valéry University Montpellier 3（蒙彼利埃第三大学（保罗·瓦莱里大学））；INRAE（法国国家农业、食品与环境研究院）；CIRAD（法国国际农业研究合作中心）；CNRS（法国国家科学研究中心）
INFN Section of Naples（意大利国家核物理研究所那不勒斯分部）；University of Naples "Federico II"（那不勒斯费德里科二世大学）；ESO（欧洲南方天文台）
We present a Deep-Learning (DL) pipeline developed for the detection and characterization of astronomical sources within simulated Atacama Large Millimeter/submillimeter Array (ALMA) data cubes. The pipeline is composed of six DL models: a Convolutional Autoencoder for source detection within the spatial domain of the integrated data cubes, a Recurrent Neural Network (RNN) for denoising and peak detection within the frequency domain, and four Residual Neural Networks (ResNets) for source characterization. The combination of spatial and frequency information improves completeness while decreasi…
Classification is a popular task in the field of Machine Learning (ML) and Artificial Intelligence (AI), and it happens when outputs are categorical variables. There are a wide variety of models that attempts to draw some conclusions from observed values, so classification algorithms predict categorical class labels and use them in classifying new data. Popular classification models including logistic regression, decision tree, random forest, Support Vector Machine (SVM), multilayer perceptron, Naive Bayes, and neural networks have proven to be efficient and accurate applied to many industrial…
Machine learning techniques have been increasingly useful in astronomical applications over the last few years, for example in the morphological classification of galaxies. Convolutional neural networks have proven to be highly effective in classifying objects in image data. The current work aims to establish when multiple components are present, in the astronomical context of synthesis imaging observations of radio sources. To this effect, we design a convolutional neural network to differentiate between different morphology classes using sources from the Radio Galaxy Zoo (RGZ) citizen scienc…
Fermi National Accelerator Laboratory（费米国家加速器实验室）；University of Chicago（芝加哥大学）；Argonne National Laboratory（阿贡国家实验室）；Oak Ridge National Laboratory（橡树岭国家实验室）；Space Telescope Science Institute（太空望远镜科学研究所）；Kavli Institute for Cosmological Physics（卡夫利宇宙物理研究所）
In astronomy, neural networks are often trained on simulation data with the prospect of being used on telescope observations. Unfortunately, training a model on simulation data and then applying it to instrument data leads to a substantial and potentially even detrimental decrease in model accuracy on the new target dataset. Simulated and instrument data represent different data domains, and for an algorithm to work in both, domain-invariant learning is necessary. Here we employ domain adaptation techniques$-$ Maximum Mean Discrepancy (MMD) as an additional transfer loss and Domain Adversarial…
Millennium Institute of Astrophysics（千年天体物理研究所）；Center for Mathematical Modeling, Universidad de Chile（智利大学数学建模中心）；AURA Observatory in Chile（智利AURA天文台）；Universidad de Chile（智利大学）
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 pe…
Identifying Light-curve Signals with a Deep Learning Based Object Detection Algorithm. II. A General Light Curve Classification Framework
Tsung-Dao Lee Institute, Shanghai Jiao Tong University（上海交通大学李政道研究所）；University of Warwick（华威大学）；School of Physics and Astronomy, Shanghai Jiao Tong University（上海交通大学物理与天文学院）
