Gradient boosting and random forests outperform neural networks and stochastic gradient descent at classifying interstellar object tracklets in simulated LSST data, with Digest2 scores as the dominant features.
Palomar Optical Spectrum of Hyperbolic Near-Earth Object A/2017 U1
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We present optical spectroscopy of the recently discovered hyperbolic near-Earth object A/2017 U1, taken on 25 Oct 2017 at Palomar Observatory. Although our data are at a very low signal-to-noise, they indicate a very red surface at optical wavelengths without significant absorption features.
fields
astro-ph.EP 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Machine Learning Methods for Automated Interstellar Object Classification with LSST
Gradient boosting and random forests outperform neural networks and stochastic gradient descent at classifying interstellar object tracklets in simulated LSST data, with Digest2 scores as the dominant features.