Department of Physics & Astronomy
University of New Mexico

Center for Astrophysics Research and Technologies Seminar Series

Applications of Machine Learning Algorithms on astronomical datasets

Presented by Rajorshi Bhattacharya, UNM

The application of machine learning (ML) techniques to astronomical datasets has been increasingly popular. From image classification and object detection in large-scale sky surveys to obtaining different stellar parameters, ML algorithms have been quite successful. We here discuss that how by using ML algorithms (specifically Supervised ML) on large astronomical datasets, we can successfully regress/classify different parameters, for example, distances. To test the accuracy of our machine learning models we show results from their application on the BAaDE survey, which consists of 28,062 infrared color-selected red giant stars, the majority of which are of Mira-type and lie on the Asymptotic Giant Branch (AGB). By using this dataset, we have explored classification of the sample into typical AGB subgroups, for instance C-rich vs O-rich, and estimation of properties such as stellar periods. We also discuss different types of ML algorithms and their accuracy, along with some optimization techniques to enhance the efficiency of the ML models.

2:00 pm, Thursday, November 30, 2023

Disability NoticeIndividuals with disabilities who need an auxiliary aid or service to attend or participate in P&A events should contact the Physics Department (phone: 505-277-2616, email: well in advance to ensure your needs are accomodated. Event handouts can be provided in alternative accessible formats upon request. Please contact the Physics front office if you need written information in an alternative format.

A schedule of talks within the Department of Physics and Astronomy is available on the P&A web site at