EarthGAN: Can we visualize the Earth's mantle convection using a surrogate model?
This work addresses visualization challenges for geoscientists by providing an incremental method to access complex simulation data on standard hardware.
The researchers tackled the problem of visualizing Earth's mantle convection data without powerful computers by building a surrogate model using a generative adversarial network, with preliminary results showing it can generate useful outputs compared to ground-truth data.
Scientific simulations are often used to gain insight into foundational questions. However, many potentially useful simulation results are difficult to visualize without powerful computers. In this research, we seek to build a surrogate model, using a generative adversarial network, to allow for the visualization of the Earth's Mantle Convection data set on readily accessible hardware. We present our preliminary method and results, and all code is made publicly available. The preliminary results show that a surrogate model of the Earth's Mantle Convection data set can generate useful results. A comparison to the "ground-truth" is provided.