| |
 |
| Paper: |
Machine Learning Approaches for Detection and Classification of Astrochemical Spectral Lines |
| Volume: |
521, Astronomical Data Analysis Software and Systems XXVI |
| Page: |
189 |
| Authors: |
Barrientos, A.; Solar, M. |
| Abstract: |
Astronomical spectroscopy is a field that has been growing for a number of years. Analyzing the features of molecular spectral lines from astronomical data cubes provides insight into the composition and dynamics of our universe. With the arrival of state-of-the-art high spectral resolution radiotelescopes like ALMA, the size of the data cubes will be constantly growing in time. This is why we believe that some automatic analysis methods will be helpful assisting the astrochemists work. We generated a method to analyze astronomical data cubes, detect their regions of interest, by using a non supervised clustering algorithm, and then, creating a spectrum for each region of interest, and classifying the molecular species found in the spectra, by using a supervised training algorithm. The training for the learner is done using synthetic spectra, and the validation is done using radio astronomical data cubes from ALMA data. A summary of related works is presented, and also a list of the astronomical complexities surrounding the nature of a molecular spectrum. Initial experiments contemplated a basic physical model that was considered to start the problem and two popular Machine Learning methods were tested for the task of classifying molecular spectra: Support Vector Machines and Neural Networks. Results for SVM resulted in accuracy of over 90 percent with the basic model, later, a more complex model provided a slightly lower accuracy due to the lack of proper validation data. The Neural Network approach provided similar results to the initial SVM approach.
A parallelization test was also performed, obtaining a speedup of 2x in the processing of real world data files. |
|
|
|
|
|
