Classifying Non-Gaussian Transient Noise in LIGO

Using computer vision to analyse gravitational waves can provide valuable information about previously obscured information.

Space exploration methods have never been as diverse and thorough as it is in today’s time. New techniques that span far beyond the conventional method of using electromagnetic radiation to identify and study astronomical evidence have been discovered and are now amplified using machine learning technology. One such technique is using interferometers to record gravitational waves released from astronomical events. Using computer vision to analyse gravitational waves can provide valuable information about previously obscured information. Also, gravitational waves are fundamentally unrelated to electromagnetic radiation thereby providing us with information that is entirely different from what we previously could access. This has consequentially opened an altogether new avenue for research and further exploration. The contrastive model for machine learning-based detection and classification performed the best.

Explore More!

Predictive Dynamics of Solar Cycles: An Analysis of Sunspot Patterns, Granger Causal Relationships, and Terrestrial and Space Weather Phenomena

This paper attempts to understand the complex nature of solar cycles, primarily through the lens of sunspot data analysis, to predict future solar activity and explore its causality with Earth and Space phenomena such as global temperatures and CO2 Emissions.

Mariah D.

Mentored by

Vibration Analysis

This paper covers differences in accuracies of an artificial intelligence model that classifies different sets of sensor outputs (in this case, machinery shaft vibrations) collected by sensors into varying levels of weight on the shaft.