Search

Developing an effective automatic classifier to separate genuine sources from artifacts is essential for transient follow-ups in wide-field optical surveys. The identification of transient detections from the subtraction artifacts after the image differencing process is a key step in such classifiers, known as real-bogus classification problem. We apply a self-supervised machine learning model, the deep-embedded self-organizing map (DESOM) to this ‘real-bogus’ classification problem. DESOM combines an autoencoder and a self-organizing map to perform clustering in order to distinguish between real and bogus detections, based on their dimensionality-reduced representations. We use 32 × 32 normalized detection thumbnails as the input of DESOM. We demonstrate different model training approaches, and find that our best DESOM classifier shows a missed detection rate of $6.6{{\ \rm per\,cent}}$ with a false-positive rate of $1.5{{\ \rm per\,cent}}$. DESOM offers a more nuanced way to fine-tune the decision boundary identifying likely real detections when used in combination with other types of classifiers, e.g. built on neural networks or decision trees. We also discuss other potential usages of DESOM and its limitations.

Large-scale sky surveys have played a transformative role in our understanding of astrophysical transients, only made possible by increasingly powerful machine learning-based filtering to accurately sift through the vast quantities of incoming data generated. In this paper, we present a new real-bogus classifier based on a Bayesian convolutional neural network that provides nuanced, uncertainty-aware classification of transient candidates in difference imaging, and demonstrate its application to the datastream from the GOTO wide-field optical survey. Not only are candidates assigned a well-calibrated probability of being real, but also an associated confidence that can be used to prioritise human vetting efforts and inform future model optimisation via active learning. To fully realise the potential of this architecture, we present a fully-automated training set generation method which requires no human labelling, incorporating a novel data-driven augmentation method to significantly improve the recovery of faint and nuclear transient sources. We achieve competitive classification accuracy (FPR and FNR both below 1%) compared against classifiers trained with fully human-labelled datasets, whilst being significantly quicker and less labour-intensive to build. This data-driven approach is uniquely scalable to the upcoming challenges and data needs of next-generation transient surveys. We make our data generation and model training codes available to the community., 17 pages, 12 figures, resubmitted to MNRAS following reviewer comments

The Gravitational-wave Optical Transient Observer (GOTO) is an array of wide-field optical telescopes, designed to exploit new discoveries from the next generation of gravitational wave detectors (LIGO, Virgo, KAGRA), study rapidly evolving transients, and exploit multi-messenger opportunities arising from neutrino and very high energy gamma-ray triggers. In addition to a rapid response mode, the array will also perform a sensitive, all-sky transient survey with few day cadence. The facility features a novel, modular design with multiple 40-cm wide-field reflectors on a single mount. In June 2017 the GOTO collaboration deployed the initial project prototype, with 4 telescope units, at the Roque de los Muchachos Observatory (ORM), La Palma, Canary Islands. Here we describe the deployment, commissioning, and performance of the prototype hardware, and discuss the impact of these findings on the final GOTO design. We also offer an initial assessment of the science prospects for the full GOTO facility that employs 32 telescope units across two sites., 19 pages, 16 Figures, accepted for publication in Monthly Notices of the Royal Astronomical Society

The advent of wide-field sky surveys has led to the growth of transient and variable source discoveries. The data deluge produced by these surveys has necessitated the use of machine learning (ML) and deep learning (DL) algorithms to sift through the vast incoming data stream. A problem that arises in real-world applications of learning algorithms for classification is imbalanced data, where a class of objects within the data is underrepresented, leading to a bias for over-represented classes in the ML and DL classifiers. We present a recurrent neural network (RNN) classifier that takes in photometric time-series data and additional contextual information (such as distance to nearby galaxies and on-sky position) to produce real-time classification of objects observed by the Gravitational-wave Optical Transient Observer (GOTO), and use an algorithm-level approach for handling imbalance with a focal loss function. The classifier is able to achieve an Area Under the Curve (AUC) score of 0.972 when using all available photometric observations to classify variable stars, supernovae, and active galactic nuclei. The RNN architecture allows us to classify incomplete light curves, and measure how performance improves as more observations are included. We also investigate the role that contextual information plays in producing reliable object classification., Comment: 16 pages, 12 figures, to be published in Monthly Notices of the Royal Astronomical Society

The Gravitational-wave Optical Transient Observer (GOTO) is a wide-field telescope project focused on detecting optical counterparts to gravitational-wave sources. The GOTO Telescope Control System (G-TeCS) is a custom robotic control system which autonomously manages the GOTO telescope hardware and nightly operations. Since the commissioning the GOTO prototype on La Palma in 2017, development of the control system has focused on the alert handling and scheduling systems. These allow GOTO to receive and process transient alerts and then schedule and carry out observations, all without the need for human involvement. GOTO is ultimately anticipated to include multiple telescope arrays on independent mounts, both on La Palma and at a southern site in Australia. When complete these mounts will be linked to form a single multi-site observatory, requiring more advanced scheduling systems to best optimise survey and follow-up observations., 12 pages, 6 figures, 2 tables, submitted to SPIE Astronomical Telescopes + Instrumentation 2020

The amount of observational data produced by time-domain astronomy is exponentially in-creasing. Human inspection alone is not an effective way to identify genuine transients fromthe data. An automatic real-bogus classifier is needed and machine learning techniques are commonly used to achieve this goal. Building a training set with a sufficiently large number of verified transients is challenging, due to the requirement of human verification. We presentan approach for creating a training set by using all detections in the science images to be thesample of real detections and all detections in the difference images, which are generated by the process of difference imaging to detect transients, to be the samples of bogus detections. This strategy effectively minimizes the labour involved in the data labelling for supervised machine learning methods. We demonstrate the utility of the training set by using it to train several classifiers utilizing as the feature representation the normalized pixel values in 21-by-21pixel stamps centered at the detection position, observed with the Gravitational-wave Optical Transient Observer (GOTO) prototype. The real-bogus classifier trained with this strategy can provide up to 95% prediction accuracy on the real detections at a false alarm rate of 1%., 9 pages, 8 figures

We have adapted the Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST) Science Pipelines to process data from the Gravitational-Wave Optical Transient Observer (GOTO) prototype. In this paper, we describe how we used the Rubin Observatory LSST Science Pipelines to conduct forced photometry measurements on nightly GOTO data. By comparing the photometry measurements of sources taken on multiple nights, we find that the precision of our photometry is typically better than 20~mmag for sources brighter than 16 mag. We also compare our photometry measurements against colour-corrected PanSTARRS photometry, and find that the two agree to within 10~mmag (1$\sigma$) for bright (i.e., $\sim14^{\rm th}$~mag) sources to 200~mmag for faint (i.e., $\sim18^{\rm th}$~mag) sources. Additionally, we compare our results to those obtained by GOTO's own in-house pipeline, {\sc gotophoto}, and obtain similar results. Based on repeatability measurements, we measure a $5\sigma$ L-band survey depth of between 19 and 20 magnitudes, depending on observing conditions. We assess, using repeated observations of non-varying standard SDSS stars, the accuracy of our uncertainties, which we find are typically overestimated by roughly a factor of two for bright sources (i.e., $17^{\rm th}$~mag). Finally, we present lightcurves for a selection of variable sources, and compare them to those obtained with the Zwicky Transient Factory and GAIA. Despite the Rubin Observatory LSST Science Pipelines still undergoing active development, our results show that they are already delivering robust forced photometry measurements from GOTO data., Comment: Accepted for publication in PASA