Accessible, Trustworthy, and Accelerated AI for Astronomy

Who are we?

CosmicAI aims to grow transformative AI advances with the overarching goal to increase the accessibility of astronomy data and knowledge for researchers, students, and the public. CosmicAI leverages partnerships between academia, national facilities, nonprofits, and industry to develop capabilities that enable astronomical researchers to conceptualize, define, and execute research projects via trustworthy, efficient, robust, and explainable AI methods.

By building next-generation AI tools the Institute aims to accelerate discoveries related to the most basic human question:

Where do we come from?

CosmicAI Driving Goals

CosmicAI is organized into four working groups - Explorable Universe, Observable Universe, Explainable Universe, and Accelerated Universe.

Each has a unique focus, but all are connected and integrated via common scientific interests or method applications.

Explorable Universe

Large astronomical datasets, which are by nature public and non-proprietary, provide unique opportunities to advance AI research in a “safe” public domain. Our Explorable Universe group aims to advance generative AI trustworthiness and reasoning to advance generative AI trustworthiness and reasoning by developing open AI foundation models for Astronomy.

Observable Universe

Astronomical data, which are inherently complex, noisy, and high-dimensional, provide challenging use cases to improve the automation of data preparation. The Observable Universe group aims to develop efficient techniques for the calibration and analysis of high-dimensional data, and to automate data pre-processing of interferometric spectral image cubes, which will increase by two orders of magnitude in size within a decade.

Explainable Universe

AI-enabled regression and inference techniques have unlocked massive discovery potential; however, constructing accurate predictions is inadequate without an understanding of the inference process itself. The Explainable Universe group aims to extend interpretable AI methods and unify them with causal reasoning, enabling explanation of the underlying mathematical relationships, while remaining robust to noise and uncertainty.

Accelerated Universe

AI advances in simulating the behavior of physical systems provide a means to significantly accelerate the speed of astrophysical calculations and gain new insights. The Accelerated Universe group aims to  extend the robustness of AI surrogates in order to model multi-physics, multiscale problems with the large dynamic ranges characteristic of astrophysical systems.