We argue that at the confluence of scientific simulation and modern machine learning, particularly recently-proposed Generative Adversarial Networks (GANs), there exists an opportunity to develop a ``middle path'' that leverages the strengths of both approaches to build machine-learning emulators of PDE-based models. From the perspective of machine learning, incorporating simulation data may significantly reduce the need of expensive observational data for training, as well as conditions the model on real-time observations for inference; from the perspective of scientific simulation, a streamlined, end-to-end process naturally leveraging observational data may reduce the reliance on closures and parameterizations to resolve finer scales that models purely based on solving partial differential equation (PDE) systems cannot address. Running on modern machine learning frameworks and acceleration hardware such as graphical processing units (GPUs), such a hybrid emulator would allow fast inference, easy sensitivity/what-if analysis of simulation output variables with respect to input observational data, and scenario analysis via the generative capabilities of GANs. We present initial work in developing a GAN-based emulator for the specific case of snowpack modeling, which has important ramifications in a variety of applications, e.g., hydropower forecasting, agriculture, and water supply management.