Data-driven learning techniques like deep learning (DL) are becoming ubiquitous in various scientific disciplines like computational fluid dynamics, materials science, biological sciences, cyber-physical systems and other science and engineering disciplines. Most often DL techniques, (due to their ability to capture highly non-linear relationships) are employed as `cheap' surrogates to expensive computational simulations or real-world experiments. However, certain characteristic behaviors of DL models like their data-hungry nature, spectral bias, rollout error and lack of explainable decision-making often limit their effectiveness in scientific disciplines. This social will serve as a forum to highlight these technical challenges while also discussing a few potential solutions to better leverage data-driven techniques to further accelerate scientific discovery.