Our research contributions highlight a significant impact on the field of astrophysics, particularly through our innovative application of machine learning (ML) and deep learning (DL) techniques to complex astronomical phenomena. We've demonstrated how computational methods can address challenging problems in astrophysics, such as estimating dynamical parameters in interacting galaxies and detecting and analyzing gravitational waves.

In our paper "Estimating dynamical parameters of two interacting galaxies using Deep Learning" (Mahor et al., 2023), we pioneered the use of deep learning to model the dynamical behavior of galaxies. Accurately estimating parameters like mass distribution, relative velocity, and interaction dynamics between galaxies is crucial for understanding the universe's evolution. Traditional methods often require extensive computational resources and manual intervention, but we introduced a more efficient approach by training neural networks on simulated galaxy interactions. The impact of this work lies in its potential to significantly reduce computational costs while increasing the precision of models, thereby enabling more detailed and extensive studies of galactic interactions.

Similarly, our studies on gravitational waves, particularly "Deep Learning for estimating parameters of Gravitational Waves" (Singh et al., 2021), have critical implications for gravitational wave astronomy. Gravitational waves, which are ripples in spacetime caused by massive astrophysical events like black hole mergers, carry information about their sources that can provide insights into the fundamental nature of gravity and the universe. By applying deep learning in this context, we have enabled the rapid and accurate extraction of parameters from the gravitational wave signals detected by observatories such as LIGO and Virgo. This research enhances detection sensitivity and analysis speed, both of which are vital for real-time observations and could lead to the discovery of new astrophysical phenomena.

In addition to these contributions, our paper "Predicting future astronomical events using deep learning" (Singh, Prajapati, Pathak) introduces a novel approach to forecasting astronomical events using deep learning models. Predicting such events is crucial for proactive observation planning and resource allocation in observatories. By training models on historical data, we have demonstrated the potential for accurately predicting events like supernovae or gamma-ray bursts. The broader impact of this work is its potential to transform how observatories prepare for and conduct observations, leading to more timely and targeted studies of transient and rare astronomical phenomena.