The exploration of planetary bodies in our Solar system and beyond relies on the processing and interpretation of large, spatio-temporally inconsistent, and heterogeneous datasets.
autoencoder
Posted inAI - Data - Apps - Cybernetics, Imaging & Spectroscopy, Robotics/Rovers/UAVs, Status Report, Tricorders & Sensors
Novelty Detection In Rover-based Planetary Surface Images Using Autoencoders
In the domain of planetary science, novelty detection is gaining attention because of the operational opportunities it offers, including annotated data products and downlink prioritization.
Posted inAstronomy & Telescopes, Exoplanets, -moons, -comets, Imaging & Spectroscopy, Status Report, Stellar Cartography
Efficient Reduction Of Stellar Contamination And Noise In Planetary Transmission Spectra Using Neural Networks
Context: JWST has enabled transmission spectroscopy at unprecedented precision, but stellar heterogeneities (spots and faculae) remain a dominant contamination source that can bias atmospheric retrievals if uncorrected.
Posted inAI - Data - Apps - Cybernetics, Astronomy & Telescopes, Atmospheres, Climate, Weather, Biosignatures & Paleobiology, Exoplanets, -moons, -comets, Imaging & Spectroscopy, Press Release
Hunting for “Oddballs” With Machine Learning: Detecting Anomalous Exoplanets Using a Deep-Learned Low-Dimensional Representation of Transit Spectra with Autoencoders
This study explores the application of autoencoder-based machine learning techniques for anomaly detection to identify exoplanet atmospheres with unconventional chemical signatures using a low-dimensional data representation.
![Analysis of the stellar parameters derived with our methodology. The dots are colour-coded according to the estimated metallicity. The size of the dots is proportional to the estimated projected rotational velocity. The top left panel shows a Kiel diagram, with the red, black, and blue dashed lines corresponding to 5 Gyr PARSEC isochrones with [M/H] = −0.4, 0.0 and 0.1 dex, respectively. Empty squares represent the stars reported to have a behaviour akin to subdwarfs both in Mar21 and Schw19 (same for bottom left panel). Top right: black and grey dashed lines correspond to solar metallicity PARSEC isochrones for 5 and 0.1 Gyr, respectively. Black and grey dotted lines correspond to solar metallicity Baraffe et al. (2015) isochrones for 5 and 0.1 Gyr, respectively. Bottom left: triangles represent stars identified as Hα active in Schöfer et al. (2019). Empty stars depict members of the thick disc Galactic population (Cortés-Contreras et al., in prep.). Bottom right: plus symbols correspond to stars identified as members of the young disc Galactic population by Cortés-Contreras et al. (in prep.). Empty circles represent stars with a possible membership in a young stellar associaton, as explained in Section 4.1. -- astro-ph.SR](https://i0.wp.com/astrobiology.com/wp-content/uploads/2024/05/Using-Autoencoders-And-Deep.png?resize=1200%2C717&ssl=1)
Posted inAI - Data - Apps - Cybernetics, Astronomy & Telescopes, Imaging & Spectroscopy, Status Report, Stellar Cartography
Using Autoencoders And Deep Transfer Learning To Determine The Stellar Parameters Of 286 CARMENES M Dwarfs
Deep learning (DL) techniques are a promising approach among the set of methods used in the ever-challenging determination of stellar parameters in M dwarfs.