Classifying Structures in the ISM with Machine Learning Techniques

Details Classifying Structures in the ISM with Machine Learning Techniques Classifying Structures in the ISM with Machine Learning Techniques

Jan 2011

adsabs.harvard.edu/cgi-bin/nph-data_query?bibcode=2011aas...21721701b&link_type=abstract

American Astronomical Society, AAS Meeting #217, #217.01; Bulletin of the American Astronomical Society, Vol. 43, 2011

Mathematics

Logic

Scientific paper

The processes which govern molecular cloud evolution and star formation often sculpt structures in the ISM: filaments, pillars, shells, outflows, etc. Because of their morphological complexity, these objects are often identified manually. Manual classification has several disadvantages; the process is subjective, not easily reproducible, and does not scale well to handle increasingly large datasets. We have explored to what extent machine learning algorithms can be trained to autonomously identify specific morphological features in molecular cloud datasets. We show that the Support Vector Machine algorithm can successfully locate filaments and outflows blended with other emission structures. When the objects of interest are morphologically distinct from the surrounding emission, this autonomous classification achieves >90% accuracy. We have developed a set of IDL-based tools to apply this technique to other datasets.

Affiliated with

Also associated with

No associations

Rating

Classifying Structures in the ISM with Machine Learning Techniques does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Classifying Structures in the ISM with Machine Learning Techniques, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Classifying Structures in the ISM with Machine Learning Techniques will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-1397681