# EarthGAN: Can we visualize the Earth's mantle convection using a surrogate model?

arXiv: https://arxiv.org/abs/2110.13315 · HTML: https://mlsanity.com/paper/2110.13315/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 10 references that are in the map.
- First posted on arXiv 25 Oct 2021.

## Builds on (most cited first, 6 of 6)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges](https://mlsanity.com/paper/2104.13478/) (2021)
- [AI-assisted super-resolution cosmological simulations](https://mlsanity.com/paper/2010.06608/) (2020)

## Abstract (arXiv)

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.