Success of Machine Learning algorithms in Dynamical Mass Measurements of Galaxy Clusters
arXiv:1912.05316
Abstract
In recent years, machine learning (ML) algorithms have been successfully employed in Astronomy for analyzing and interpreting the data collected from various surveys. The need for new robust and efficient data analysis tools in Astronomy is imminently growing as we enter the new decade. Astronomical data sets are growing both in size and complexity at an exponential rate and ML methodologies can revolutionize our ability to interpret observations and provide new means of discovery. In this essay we focus on recent success of ML algorithms in predicting the dynamical mass of galaxy clusters. We discuss the results of the study performed by Ho et al. [1] and their implications, where it was found that ML algorithms outperform conventional statistical methods and can offer a robust and accurate tool for dynamical mass estimation.
arXiv comment14 pages, 3 figures
References in corpus (16)
- The Sloan Digital Sky Survey: Technical Summary
- The Gaia mission
- MultiDark simulations: the story of dark matter halo concentrations and density profiles
- LSST Science Book, Version 2.0
- Data Mining and Machine Learning in Astronomy
- Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
- Learning to Predict the Cosmological Structure Formation
- Probabilistic Random Forest: A machine learning algorithm for noisy datasets
- Finding strong lenses in CFHTLS using convolutional neural networks
- Non-Gaussian information from weak lensing data via deep learning
- Galaxy Cluster Mass Reconstruction Project: I. Methods and first results on galaxy-based techniques
- A Machine Learning Approach for Dynamical Mass Measurements of Galaxy Clusters
- Machine learning search for variable stars
- Dynamical Mass Measurements of Contaminated Galaxy Clusters Using Machine Learning
- Prediction of galaxy halo masses in SDSS DR7 via a machine learning approach
- An application of machine learning techniques to galaxy cluster mass estimation using the MACSIS simulations