- Denoising galaxy images using deep learning techniques – testing the importance of incorporating image Point Spread Function in the network in various ways
- Stellar mass calculation of galaxy clusters from the Planck all sky survey
- Supernova and variable star detection and analysis using active anomaly detection
- Detection and morphological classification of dwarf galaxies from the MATLAS
- Detection and classification of tidal remnants around massive galaxies from the
Past research :
- Analysing the effect of including measurement errors in machine learning and how it improves astronomical applications using Probabilistic Random Forests.
- Supernova photometric classification using active learning.
- Comparison of machine learning techniques to classify galaxies according to their morphological types.
- Formulating a pre-processing technique for astronomical software such as Source Extractor using anisotropic diffusion filtering.
- Investigating merger remnants around and within early-type galaxies.
- Detection and analysis of dwarf galaxy environments from the MATLAS survey.