No Arabic abstract
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.
We analysed 68 candidate planetary systems first identified during Campaigns 5 and 6 (C5 and C6) of the NASA textit{K2} mission. We set out to validate these systems by using a suite of follow-up observations, including adaptive optics, speckle imaging, and reconnaissance spectroscopy. The overlap between C5 with C16 and C18, and C6 with C17, yields lightcurves with long baselines that allow us to measure the transit ephemeris very precisely, revisit single transit candidates identified in earlier campaigns, and search for additional transiting planets with longer periods not detectable in previous works. Using texttt{vespa}, we compute false positive probabilities of less than 1% for 37 candidates orbiting 29 unique host stars and hence statistically validate them as planets. These planets have a typical size of $2.2R_{oplus}$ and orbital periods between 1.99 and 52.71 days. We highlight interesting systems including a sub-Neptune with the longest period detected by textit{K2}, sub-Saturns around F stars, several multi-planetary systems in a variety of architectures. These results show that a wealth of planetary systems still remains in the textit{K2} data, some of which can be validated using minimal follow-up observations and taking advantage of analyses presented in previous catalogs.
We present an investigation of twelve candidate transiting planets from Kepler with orbital periods ranging from 34 to 207 days, selected from initial indications that they are small and potentially in the habitable zone (HZ) of their parent stars. Few of these objects are known. The expected Doppler signals are too small to confirm them by demonstrating that their masses are in the planetary regime. Here we verify their planetary nature by validating them statistically using the BLENDER technique, which simulates large numbers of false positives and compares the resulting light curves with the Kepler photometry. This analysis was supplemented with new follow-up observations (high-resolution optical and near-infrared spectroscopy, adaptive optics imaging, and speckle interferometry), as well as an analysis of the flux centroids. For eleven of them (KOI-0571.05, 1422.04, 1422.05, 2529.02, 3255.01, 3284.01, 4005.01, 4087.01, 4622.01, 4742.01, and 4745.01) we show that the likelihood they are true planets is far greater than that of a false positive, to a confidence level of 99.73% (3 sigma) or higher. For KOI-4427.01 the confidence level is about 99.2% (2.6 sigma). With our accurate characterization of the GKM host stars, the derived planetary radii range from 1.1 to 2.7 R_Earth. All twelve objects are confirmed to be in the HZ, and nine are small enough to be rocky. Excluding three of them that have been previously validated by others, our study doubles the number of known rocky planets in the HZ. KOI-3284.01 (Kepler-438b) and KOI-4742.01 (Kepler-442b) are the planets most similar to the Earth discovered to date when considering their size and incident flux jointly.
We introduce a new machine learning based technique to detect exoplanets using the transit method. Machine learning and deep learning techniques have proven to be broadly applicable in various scientific research areas. We aim to exploit some of these methods to improve the conventional algorithm based approaches presently used in astrophysics to detect exoplanets. Using the time-series analysis library TSFresh to analyse light curves, we extracted 789 features from each curve, which capture the information about the characteristics of a light curve. We then used these features to train a gradient boosting classifier using the machine learning tool lightgbm. This approach was tested on simulated data, which showed that is more effective than the conventional box least squares fitting (BLS) method. We further found that our method produced comparable results to existing state-of-the-art deep learning models, while being much more computationally efficient and without needing folded and secondary views of the light curves. For Kepler data, the method is able to predict a planet with an AUC of 0.948, so that 94.8 per cent of the true planet signals are ranked higher than non-planet signals. The resulting recall is 0.96, so that 96 per cent of real planets are classified as planets. For the Transiting Exoplanet Survey Satellite (TESS) data, we found our method can classify light curves with an accuracy of 0.98, and is able to identify planets with a recall of 0.82 at a precision of 0.63.
Since the start of the Wide Angle Search for Planets (WASP) program, more than 160 transiting exoplanets have been discovered in the WASP data. In the past, possible transit-like events identified by the WASP pipeline have been vetted by human inspection to eliminate false alarms and obvious false positives. The goal of the present paper is to assess the effectiveness of machine learning as a fast, automated, and reliable means of performing the same functions on ground-based wide-field transit-survey data without human intervention. To this end, we have created training and test datasets made up of stellar light curves showing a variety of signal types including planetary transits, eclipsing binaries, variable stars, and non-periodic signals. We use a combination of machine learning methods including Random Forest Classifiers (RFCs) and Convolutional Neural Networks (CNNs) to distinguish between the different types of signals. The final algorithms correctly identify planets in the test data ~90% of the time, although each method on its own has a significant fraction of false positives. We find that in practice, a combination of different methods offers the best approach to identifying the most promising exoplanet transit candidates in data from WASP, and by extension similar transit surveys.
Exoplanet detection in the past decade by efforts including NASAs Kepler and TESS missions has discovered many worlds that differ substantially from planets in our own Solar system, including more than 400 exoplanets orbiting binary or multi-star systems. This not only broadens our understanding of the diversity of exoplanets, but also promotes our study of exoplanets in the complex binary and multi-star systems and provides motivation to explore their habitability. In this study, we analyze orbital stability of exoplanets in non-coplanar circumbinary systems using a numerical simulation method, with which a large number of circumbinary planet samples are generated in order to quantify the effects of various orbital parameters on orbital stability. We also train a machine learning model that can quickly determine the stability of the circumbinary planetary systems. Our results indicate that larger inclinations of the planet tend to increase the stability of its orbit, but change in the planets mass range between Earth and Jupiter has little effect on the stability of the system. In addition, we find that Deep Neural Networks (DNNs) have higher accuracy and precision than other machine learning algorithms.