D. J. Armstrong

Kaiming Cui, D. J. Armstrong, Fabo Feng

Vast amounts of astronomical photometric data are generated from various projects, requiring significant effort to identify variable stars and other object classes. In light of this, a general, widely applicable classification framework would simplify the process of designing specific classifiers for various astronomical objects. We present a novel deep learning framework for classifying light curves using a weakly supervised object detection model. Our framework identifies the optimal windows for both light curves and power spectra automatically, and zooms in on their corresponding data. This allows for automatic feature extraction from both time and frequency domains, enabling our model to handle data across different scales and sampling intervals. We train our model on data sets obtained from Kepler, TESS, and Zwicky Transient Facility multiband observations of variable stars and transients. We achieve an accuracy of 87% for combined variables and transient events, which is comparable to the performance of previous feature-based models. Our trained model can be utilized directly for other missions, such as the All-sky Automated Survey for Supernovae, without requiring any retraining or fine-tuning. To address known issues with miscalibrated predictive probabilities, we apply conformal prediction to generate robust predictive sets that guarantee true-label coverage with a given probability. Additionally, we incorporate various anomaly detection algorithms to empower our model with the ability to identify out-of-distribution objects. Our framework is implemented in the Deep-LC toolkit, which is an open-source Python package hosted on Github (https://github.com/ckm3/Deep-LC) and PyPI.

Matthew P. Battley, David J. Armstrong, Don Pollacco

Young exoplanets and their corresponding host stars are fascinating laboratories for constraining the timescale of planetary evolution and planet-star interactions. However, because young stars are typically much more active than the older population, in order to discover more young exoplanets, greater knowledge of the wide array of young star variability is needed. Here Kohonen Self Organising Maps (SOMs) are used to explore young star variability present in the first year of observations from the Transiting Exoplanet Survey Satellite (TESS), with such knowledge valuable to perform targeted detrending of young stars in the future. This technique was found to be particularly effective at separating the signals of young eclipsing binaries and potential transiting objects from stellar variability, a list of which are provided in this paper. The effect of pre-training the Self-Organising Maps on known variability classes was tested, but found to be challenging without a significant training set from TESS. SOMs were also found to provide an intuitive and informative overview of leftover systematics in the TESS data, providing an important new way to characterise troublesome systematics in photometric data-sets. This paper represents the first stage of the wider YOUNGSTER program, which will use a machine-learning-based approach to classification and targeted detrending of young stars in order to improve the recovery of smaller young exoplanets.

David J. Armstrong, Jevgenij Gamper, Theodoros Damoulas

Over 30% of the ~4000 known exoplanets to date have been discovered using 'validation', where the statistical likelihood of a transit arising from a false positive (FP), non-planetary scenario is calculated. For the large majority of these validated planets calculations were performed using the vespa algorithm (Morton et al. 2016). Regardless of the strengths and weaknesses of vespa, it is highly desirable for the catalogue of known planets not to be dependent on a single method. We demonstrate the use of machine learning algorithms, specifically a gaussian process classifier (GPC) reinforced by other models, to perform probabilistic planet validation incorporating prior probabilities for possible FP scenarios. The GPC can attain a mean log-loss per sample of 0.54 when separating confirmed planets from FPs in the Kepler threshold crossing event (TCE) catalogue. Our models can validate thousands of unseen candidates in seconds once applicable vetting metrics are calculated, and can be adapted to work with the active TESS mission, where the large number of observed targets necessitates the use of automated algorithms. We discuss the limitations and caveats of this methodology, and after accounting for possible failure modes newly validate 50 Kepler candidates as planets, sanity checking the validations by confirming them with vespa using up to date stellar information. Concerning discrepancies with vespa arise for many other candidates, which typically resolve in favour of our models. Given such issues, we caution against using single-method planet validation with either method until the discrepancies are fully understood.