Cosmological simulations of galaxy formation are limited by finite computational resources. We draw from the ongoing rapid advances in artificial intelligence (AI; specifically deep learning) to address this problem. Neural networks have been developed to learn from high-resolution (HR) image data and then make accurate superresolution (SR) versions of different low-resolution (LR) images. We apply such techniques to LR cosmological N-body simulations, generating SR versions. Specifically, we are able to enhance the simulation resolution by generating 512 times more particles and predicting their displacements from the initial positions. Therefore, our results can be viewed as simulation realizations themselves, rather than projections, e.g., to their density fields. Furthermore, the generation process is stochastic, enabling us to sample the small-scale modes conditioning on the large-scale environment. Our model learns from only 16 pairs of small-volume LR-HR simulations and is then able to generate SR simulations that successfully reproduce the HR matter power spectrum to percent level up to 16 h−1Mpc and the HR halo mass function to within 10% down to 1011 M⊙. We successfully deploy the model in a box 1,000 times larger than the training simulation box, showing that high-resolution mock surveys can be generated rapidly. We conclude that AI assistance has the potential to revolutionize modeling of small-scale galaxy-formation physics in large cosmological volumes.

星系形成的宇宙学模拟受到有限计算资源的限制。我们利用人工智能（AI；特别是深度学习）的持续快速发展来解决这个问题。已经开发出神经网络来从高分辨率 (HR) 图像数据中学习，然后制作不同低分辨率 (LR) 图像的准确超分辨率 (SR) 版本。我们将这些技术应用于 LR 宇宙学 N 体模拟，生成 SR 版本。具体来说，我们能够通过生成 512 倍多的粒子并预测它们从初始位置的位移来提高模拟分辨率。因此，我们的结果可以看作是模拟实现本身，而不是投影，例如，对它们的密度场。此外，生成过程是随机的，使我们能够对大规模环境下的小规模模式进行采样。我们的模型仅从 16 对小体积 LR-HR 模拟中学习，然后能够生成 SR 模拟，这些模拟成功地将 HR 物质功率谱复制到高达16 H-1多氯联苯 和 HR 晕质量函数到 10% 向下 1011 米⊙. 我们成功地将模型部署在比训练模拟盒大 1000 倍的盒子中，表明可以快速生成高分辨率模拟调查。我们得出的结论是，人工智能辅助有可能彻底改变大宇宙学体积中小尺度星系形成物理学的建模。