Protostellar classification using supervised machine learning algorithms
arXiv:1808.08371 · doi:10.1007/s10509-018-3418-7
Abstract
Classification of young stellar objects (YSOs) into different evolutionary stages helps us to understand the formation process of new stars and planetary systems. Such classification has traditionally been based on spectral energy distributions (SEDs). An alternative approach is provided by supervised machine learning algorithms. We attempt to classify a sample of Orion YSOs into different classes, where each source has already been classified using multiwavelength SED analysis. We used 8 different learning algorithms to classify the target YSOs, namely a decision tree, random forest, gradient boosting machine (GBM), logistic regression, naïve Bayes classifier, -nearest neighbour classifier, support vector machine, and neural network. The classifiers were trained and tested by using a 10-fold cross-validation procedure. As the learning features, we employed ten continuum flux densities spanning from the near-IR to submm. With a classification accuracy of 82% (with respect to the SED-based classes), a GBM algorithm was found to exhibit the best performance. The lowest accuracy of 47% was obtained with a naïve Bayes classifier. Our analysis suggests that the inclusion of the 3.6 m and 24 m flux densities is useful to maximise the YSO classification accuracy. Although machine learning has the potential to provide a rapid and fairly reliable way to classify YSOs, an SED analysis is still needed to derive the physical properties of the sources, and to create the labelled training data. The classification accuracies can be improved with respect to the present results by using larger data sets, more detailed missing value imputation, and advanced ensemble methods. Overall, the application of machine learning is expected to be very useful in the era of big astronomical data, for example to quickly assemble interesting target source samples for follow-up studies.
arXiv comment17 pages, 6 figures, 2 tables, accepted for publication in Astrophysics and Space Science, abstract abridged for arXiv
References in corpus (37)
- The Infrared Array Camera (IRAC) for the Spitzer Space Telescope
- Herschel Space Observatory - An ESA facility for far-infrared and submillimetre astronomy
- Interstellar Dust Grains
- The Photodetector Array Camera and Spectrometer (PACS) on the Herschel Space Observatory
- The Spitzer c2d Legacy Results: Star Formation Rates and Efficiencies; Evolution and Lifetimes
- The Infrared Spectrograph on the Spitzer Space Telescope
- From filamentary clouds to prestellar cores to the stellar IMF: Initial highlights from the Herschel Gould Belt survey
- The Spitzer Space Telescope Survey of the Orion A & B Molecular Clouds - Part I: A Census of Dusty Young Stellar Objects and a Study of their Mid-IR Variability
- Data Mining and Machine Learning in Astronomy
- Young Stellar Objects in the Gould Belt
- The Large APEX Bolometer Camera LABOCA
- The Herschel Orion Protostar Survey: Spectral Energy Distributions and Fits Using a Grid of Protostellar Models
- The Effect of Line of Sight Temperature Variation and Noise on Dust Continuum Observations
- Photometric Supernova Classification With Machine Learning
- A Herschel and APEX Census of the Reddest Sources in Orion: Searching for the Youngest Protostars
- An all-sky Support Vector Machine selection of WISE YSO Candidates
- Classifying Radio Galaxies with Convolutional Neural Network
- Searching for Exoplanets Using Artificial Intelligence
- The early stages of star formation in Infrared Dark Clouds: characterizing the core dust properties
- The Herschel Orion Protostar Survey: Luminosity and Envelope Evolution
- Transfer learning for galaxy morphology from one survey to another
- An automatic taxonomy of galaxy morphology using unsupervised machine learning
- Radio Galaxy Zoo: Compact and extended radio source classification with deep learning
- Integrating human and machine intelligence in galaxy morphology classification tasks
- Machine learning search for variable stars
- Spitzer IRAC Detection and Analysis of Shocked Molecular Hydrogen Emission
- Machine-learning identification of galaxies in the WISExSuperCOSMOS all-sky catalogue
- A machine-learning method for identifying multi-wavelength counterparts of submillimeter galaxies: training and testing using AS2UDS and ALESS
- Feature Selection based on Machine Learning in MRIs for Hippocampal Segmentation
- Galaxy And Mass Assembly: Automatic Morphological Classification of Galaxies Using Statistical Learning
- The VISTA Orion mini-survey: star formation in the Lynds 1630 North cloud
- Prestellar and protostellar cores in Ori B9
- Improved Selection Criteria for HII Regions, based on IRAS Sources
- A Machine Learning Approach to Galaxy-LSS Classification I: Imprints on Halo Merger Trees
- Operations and Performance of the PACS Instrument 3He Sorption Cooler on board of the Herschel Space Observatory
- Characterising the physical and chemical properties of a young Class 0 protostellar core embedded in the Orion B9 filament
- The Science Case for an Extended Spitzer Mission
Cited by in corpus (9)
- Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
- A Naive Bayes Classifier for identifying Class II YSOs
- A neural network-based methodology to select young stellar object candidates from IR surveys
- A Random Forest Approach to Identifying Young Stellar Object Candidates in the Lupus Star-Forming Region
- A Classifier to Detect Elusive Astronomical Objects through Photometry
- Probabilistic Classification of Infrared-selected targets for SPHEREx mission: In search of YSOs
- A Possible Converter to Denoise the Images of Exoplanet Candidates through Machine Learning Techniques
- Machine Learning Classification of Young Stellar Objects and Evolved Stars in the Magellanic Clouds Using the Probabilistic Random Forest Classifier
- The viewing angle in AGN SED models, a data-driven analysis