Machine learning for exoplanet detection in high-contrast spectroscopy Combining cross correlation maps and deep learning on medium-resolution integral-field spectra

Abstract

The advent of high-contrast imaging instruments combined with medium-resolution spectrographs allows spectral and temporal dimensions to be combined with spatial dimensions to detect and potentially characterize exoplanets with higher sensitivity. We develop a new method to effectively leverage the spectral and spatial dimensions in integral-field spectroscopy (IFS) datasets using a supervised deep-learning algorithm to improve the detection sensitivity to high-contrast exoplanets. We begin by applying a data transform whereby the IFS datasets are replaced by cross-correlation coefficient tensors obtained by cross-correlating our data with young gas giant spectral template spectra. This transformed data is then used to train machine learning (ML) algorithms. We train a 2D CNN and 3D LSTM with our data. We compare the ML models with a non-ML algorithm, based on the STIM map of arXiv:1810.06895. We test our algorithms on simulated young gas giants in a dataset that contains no known exoplanet, and explore the sensitivity of algorithms to detect these exoplanets at contrasts ranging from 1e-3 to 1e-4 at different radial separations. We quantify the sensitivity using modified receiver operating characteristic curves (mROC). We discover that the ML algorithms produce fewer false positives and have a higher true positive rate than the STIM-based algorithm, and the true positive rate of ML algorithms is less impacted by changing radial separation. We discover that the velocity dimension is an important differentiating factor. Through this paper, we demonstrate that ML techniques have the potential to improve the detection limits and reduce false positives for directly imaged planets in IFS datasets, after transforming the spectral dimension into a radial velocity dimension through a cross-correlation operation.

Accepted for publication in A&A on 23/04/2024. Total 15 pages of text, 7 figures

References in corpus (19)

• The Gemini Planet Imager: First Light
• Two accreting protoplanets around the young star PDS 70
• Detection of Carbon Monoxide and Water Absorption Lines in an Exoplanet Atmosphere
• Fundamental limitations of high contrast imaging set by small sample statistics
• Combining high-dispersion spectroscopy (HDS) with high contrast imaging (HCI): Probing rocky planets around our nearest neighbors
• Retrieving scattering clouds and disequilibrium chemistry in the atmosphere of HR 8799e
• VIP: Vortex Image Processing package for high-contrast direct imaging
• The Near-Infrared Spectrograph (NIRSpec) on the James Webb Space Telescope III. Integral-field spectroscopy
• Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
• Searching for Exoplanets Using Artificial Intelligence
• Evidence for a circumplanetary disk around protoplanet PDS 70 b
• Radial Velocity Measurements of HR 8799 b and c with Medium Resolution Spectroscopy
• A Clear View of a Cloudy Brown Dwarf Companion from High-Resolution Spectroscopy
• In-depth study of moderately young but extremely red, very dusty substellar companion HD206893B
• Physical and orbital properties of Beta Pictoris b
• Retrieving the C and O Abundances of HR 7672~AB: a Solar-Type Primary Star with a Benchmark Brown Dwarf
• Molecular mapping of the PDS70 system: No molecular absorption signatures from the forming planet PDS70 b
• Imaging exoplanets with coronagraphic instruments
• Machine Learning for Exoplanet Detection in High-Contrast Spectroscopy: Revealing Exoplanets by Leveraging Hidden Molecular Signatures in Cross-Correlated Spectra with Convolutional Neural Networks

Cited by in corpus (1)

• Machine Learning for Exoplanet Detection in High-Contrast Spectroscopy: Revealing Exoplanets by Leveraging Hidden Molecular Signatures in Cross-Correlated Spectra with Convolutional Neural Networks