The detection of exoplanets with the radial velocity (RV) method consists in detecting variations of the stellar velocity caused by an unseen substellar companion. Instrumental errors, irregular time sampling, and different noise sources originating in the intrinsic variability of the star can hinder interpretation of the data, and even lead to spurious detections. Machine learning algorithms are being increasingly employed in the field of extrasolar planets, some with results that exceed those obtained with traditional techniques in terms of precision. We seek to explore the scope of neural networks in conjunction with the RV method, in particular for exoplanet detection in the presence of correlated noise of stellar origin. In this work, a neural network is proposed to replace the computation of the significance of the signal detected with the RV method and to classify it as of planetary origin or not. The algorithm is trained using synthetic data for systems with and without planetary companions. We injected realistic correlated noise into the simulations based on previous studies of the behaviour of stellar activity. The performance of the network is compared to the traditional method based on null-hypothesis significance testing. The network achieves 28% fewer false positives. This improvement is observed mainly in the detection of small-amplitude signals associated with low-mass planets. In addition, its execution time is five orders of magnitude faster than the traditional method. The superior performance of our algorithm has only been showcased with simulated RV data so far. Although in principle it should be straightforward to adapt it for use in real time series, its performance remains to be thoroughly tested. Future work should allow us to evaluate its potential for adoption as a valuable tool for exoplanet detection.

No abstract