Investigating Machine Learning as a Basis for Asteroid Taxonomies in the 3-Micron Spectral Region
Abstract
As part of a larger study to elucidate the presence of hydrated minerals on the surfaces of asteroids, we seek to develop a robust taxonomic classification system for asteroids using spectroscopic infrared observations in the vicinity of 3 µm. Towards this endeavor, we have constructed a Python algorithm to identify band centers and band depths near 3 µm for a set of normalized, thermally-corrected asteroid spectra for use to serve as inputs to Python's Scikit-Learn library of Machine Learning (ML) algorithms. We anticipate a thorough investigation of both Principal Component Analysis and ML (supervised, unsupervised, and Artificial Neural Network) techniques to assess which technique is likely to be better suited to the task of classifying the 3-µm data. Thus far, we have evaluated the data using Python's Agglomerative and K-Means clustering ML algorithms for a suite of different parameterizations and have identified plausible clustering scenarios. Presented here are the preliminary results we have obtained.
- Publication:
-
AGU Fall Meeting Abstracts
- Pub Date:
- December 2020
- Bibcode:
- 2020AGUFMP004.0008R
- Keywords:
-
- 1906 Computational models;
- algorithms;
- INFORMATICS;
- 1914 Data mining;
- INFORMATICS;
- 1942 Machine learning;
- INFORMATICS;
- 1952 Modeling;
- INFORMATICS