Skip to ContentSkip to Navigation
About us Faculty of Science and Engineering Data Science & Systems Complexity (DSSC) About Data Science & Systems Complexity (DSSC)

Research profile B.C. (Bharath) Nagam

B.C. (Bharath) Nagam

Project: Searching for extremely rare objects in the Universe

Detecting rare objects of high scientific importance such as strong gravitational lenses in large astronomical datasets will increase dramatically within ten years. Detecting rare objects in large datasets resembling other more common objects can lead to very high rate of false positives. Hence, there is a key challenge to suppress the false positive rate while not suppressing the true positive rate.

To overcome this problem, this research project focuses on developing novel algorithms to create realistic synthetic image data of rare astronomical objects of interest and also developing deep learning based image classifiers such as Convolutional Neural Networks (CNNs) to be used in combination with other techniques such as Stacked Denoising Autoencoders (SDAe), Generative Adversarial Networks (GANs), colour-scale filter augmentation etc., for efficiently detecting rare objects such as strong gravitational lensing in large datasets such as ESO-VST KiDS (Kilo - Degree Survey). This algorithm will also be scalable to future missions such as ESA’s Euclid satellite mission.

Keywords: Gravitational Lensing, GAN, CNN.

Fields of Expertise: Data Science, Astronomy, Deep Learning.

Last modified:16 February 2021 09.40 a.m.