No Arabic abstract
Vetting of exoplanet candidates in transit surveys is a manual process, which suffers from a large number of false positives and a lack of consistency. Previous work has shown that Convolutional Neural Networks (CNN) provide an efficient solution to these problems. Here, we apply a CNN to classify planet candidates from the Next Generation Transit Survey (NGTS). For training datasets we compare both real data with injected planetary transits and fully-simulated data, as well as how their different compositions affect network performance. We show that fewer hand labelled lightcurves can be utilised, while still achieving competitive results. With our best model, we achieve an AUC (area under the curve) score of $(95.6pm{0.2})%$ and an accuracy of $(88.5pm{0.3})%$ on our unseen test data, as well as $(76.5pm{0.4})%$ and $(74.6pm{1.1})%$ in comparison to our existing manual classifications. The neural network recovers 13 out of 14 confirmed planets observed by NGTS, with high probability. We use simulated data to show that the overall network performance is resilient to mislabelling of the training dataset, a problem that might arise due to unidentified, low signal-to-noise transits. Using a CNN, the time required for vetting can be reduced by half, while still recovering the vast majority of manually flagged candidates. In addition, we identify many new candidates with high probabilities which were not flagged by human vetters.
We describe the Next Generation Transit Survey (NGTS), which is a ground-based project searching for transiting exoplanets orbiting bright stars. NGTS builds on the legacy of previous surveys, most notably WASP, and is designed to achieve higher phot
The Transiting Exoplanet Survey Satellite (TESS) mission measured light from stars in ~75% of the sky throughout its two year primary mission, resulting in millions of TESS 30-minute cadence light curves to analyze in the search for transiting exoplanets. To search this vast data trove for transit signals, we aim to provide an approach that is both computationally efficient and produces highly performant predictions. This approach minimizes the required human search effort. We present a convolutional neural network, which we train to identify planetary transit signals and dismiss false positives. To make a prediction for a given light curve, our network requires no prior transit parameters identified using other methods. Our network performs inference on a TESS 30-minute cadence light curve in ~5ms on a single GPU, enabling large scale archival searches. We present 181 new planet candidates identified by our network, which pass subsequent human vetting designed to rule out false positives. Our neural network model is additionally provided as open-source code for public use and extension.
The Next Generation Transit Survey (NGTS) is a new ground-based sky survey designed to find transiting Neptunes and super-Earths. By covering at least sixteen times the sky area of Kepler we will find small planets around stars that are sufficiently bright for radial velocity confirmation, mass determination and atmospheric characterisation. The NGTS instrument will consist of an array of twelve independently pointed 20cm telescopes fitted with red-sensitive CCD cameras. It will be constructed at the ESO Paranal Observatory, thereby benefiting from the very best photometric conditions as well as follow up synergy with the VLT and E-ELT. Our design has been verified through the operation of two prototype instruments, demonstrating white noise characteristics to sub-mmag photometric precision. Detailed simulations show that about thirty bright super-Earths and up to two hundred Neptunes could be discovered. Our science operations are due to begin in 2014.
A machine learning technique with two-dimension convolutional neural network is proposed for detecting exoplanet transits. To test this new method, five different types of deep learning models with or without folding are constructed and studied. The light curves of the Kepler Data Release 25 are employed as the input of these models. The accuracy, reliability, and completeness are determined and their performances are compared. These results indicate that a combination of two-dimension convolutional neural network with folding would be an excellent choice for the future transit analysis.
We present the results of a search for stellar flares in the first data release from the Next Generation Transit Survey (NGTS). We have found 610 flares from 339 stars, with spectral types between F8 and M6, the majority of which belong to the Galactic thin disc. We have used the 13 second cadence NGTS lightcurves to measure flare properties such as the flare amplitude, duration and bolometric energy. We have measured the average flare occurrence rates of K and early to mid M stars and present a generalised method to measure these rates while accounting for changing detection sensitivities. We find that field age K and early M stars show similar flare behaviour, while fully convective M stars exhibit increased white-light flaring activity, which we attribute to their increased spin down time. We have also studied the average flare rates of pre-main sequence K and M stars, showing they exhibit increased flare activity relative to their main sequence counterparts.