This Spring Astronomy Day, here’s a look at how AI and GPUs are helping astronomers work through unprecedented volumes of cosmic data.

The NVIDIA Developer Blog provides developers with a  knowledge on GPU computing, AI, and deep learning, offering tutorials, code samples, and real-world applications of NVIDIA technologies. From optimizing GPU-accelerated algorithms to implementing  AI models, developers can learn practical techniques and strategies for harnessing the power of NVIDIA GPUs in their projects. Moreover, the blog highlights advancements in GPU architectures, CUDA programming, and GPU-accelerated libraries, empowering developers to stay at the forefront of GPU computing innovation.

NVIDIA

Astronomer Brant Robertson at UC Santa Cruz is using NVIDIA GPUs and AI to process the massive datasets produced by the James Webb Space Telescope. His team built an AI pipeline including Morpheus, a semantic segmentation model that classifies galaxies pixel-by-pixel, and GalaxyFriends, a UMAP-based tool for organizing ~90,000 galaxies by similarity. Key findings include unexpectedly early disk galaxies that challenged existing cosmological models. The team also applies AI techniques similar to NVIDIA DLSS to remove atmospheric blur from ground-based telescope images, preparing for the Vera C. Rubin Observatory which will generate ~20TB of data nightly. All datasets covering nearly 500,000 galaxies are released publicly.

Making Sense of the Early Universe