Identifying Exoplanets with Deep Learning. II. Two New Super-Earths Uncovered by a Neural Network in K2 Data

Abstract

For years, scientists have used data from NASA's Kepler Space Telescope to look for and discover thousands of transiting exoplanets. In its extended K2 mission, Kepler observed stars in various regions of sky all across the ecliptic plane, and therefore in different galactic environments. Astronomers want to learn how the population of exoplanets are different in these different environments. However, this requires an automatic and unbiased way to identify the exoplanets in these regions and rule out false positive signals that mimic transiting planet signals. We present a method for classifying these exoplanet signals using deep learning, a class of machine learning algorithms that have become popular in fields ranging from medical science to linguistics. We modified a neural network previously used to identify exoplanets in the Kepler field to be able to identify exoplanets in different K2 campaigns, which range in galactic environments. We train a convolutional neural network, called AstroNet-K2, to predict whether a given possible exoplanet signal is really caused by an exoplanet or a false positive. AstroNet-K2 is highly successful at classifying exoplanets and false positives, with accuracy of 98% on our test set. It is especially efficient at identifying and culling false positives, but for now, still needs human supervision to create a complete and reliable planet candidate sample. We use AstroNet-K2 to identify and validate two previously unknown exoplanets. Our method is a step towards automatically identifying new exoplanets in K2 data and learning how exoplanet populations depend on their galactic birthplace.

Classifying exoplanet candidates with convolutional neural networks: application to the Next Generation Transit Survey

“…The OFP model performs best in training with an AUC and accuracy of 99.3±0.2 % and 95.8 ± 0.5 respectively, compared with the remaining five models which likewise score approximately 96.0% and 90.0% respectively. These scores are broadly consistent with other studies (Shallue & Vanderburg 2018;Dattilo et al 2019). Models which contain ORION false positives have many high S/N candidates in the non-planet class, as these are preferentially selected by ORION.…”

“…These results highlight the main issue with training a neural network using simulated data. Previous works (Shallue & Vanderburg 2018;Dattilo et al 2019) have made efforts to remove data artefacts and systematic effects prior to passing the data through the network. The assumption being that this boosts performance.…”

Identifying Exoplanets with Deep Learning. III. Automated Triage and Vetting of TESS Candidates

“…Ansdell et al (2018) further improved upon the model by incorporating scientific domain knowledge. Since then, researchers have either modified the original AstroNet model or created their own CNNs to classify candidates from ground-based surveys (Schanche et al 2019) and K2 (Dattilo et al 2019). Osborn et al (2019) registered the first attempt to adapt AstroNet for TESS candidates, but the model was trained on simulated data, which are likely to have very different systematics from real TESS data.…”

Exoplanet validation with machine learning: 50 new validated Kepler planets

“…Past efforts to classify candidates in transit surveys with machine learning have been made, using primarily random forests (McCauliff et al 2015;Armstrong et al 2018;Schanche et al 2018;Caceres et al 2019) and convolutional neural nets (Shallue & Vanderburg 2018;Ansdell et al 2018;Dattilo et al 2019;Chaushev et al 2019;Yu et al 2019;Osborn et al 2019). To date these have all focused on identifying FPs or ranking candidates within a survey.…”