CAII Receives $1 Million NASA Funding to Enhance Euclid Mission’s Dark Matter and Dark Energy Research with AI Innovation

The Center for Artificial Intelligence Innovation (CAII) at the National Center for Supercomputing Applications has received $1 million in funding from NASA to support the Euclid space mission, which aims to study dark matter and dark energy. CAII will develop an open-source deep learning framework using the DeepDISC AI tool to address challenges in analyzing blended or overlapping galaxy images captured by Euclid, improving accuracy in critical areas such as photometry and weak gravitational lensing. This initiative also supports broader applications in space exploration, including work with the Vera C. Rubin Observatory, demonstrating CAII’s interdisciplinary approach to advancing astrophysics through machine learning.

CAII Receives NASA Funding for Euclid Mission

The Center for Artificial Intelligence Innovation (CAII) at the National Center for Supercomputing Applications has received $1 million from NASA to support the Euclid space mission. This mission aims to explore dark matter and dark energy by utilizing a deep learning framework called DeepDISC, developed by CAII and Principal Investigator Xin Liu.

A key challenge in analyzing data from the Euclid mission is identifying blended galaxies or overlapping sources, which can lead to inaccuracies in measurements such as photometry and redshift estimation. To address this, DeepDISC employs machine learning to enhance the detection of stars and galaxies, improving analysis efficiency and accuracy while quantifying prediction uncertainties.

The project benefits from a team of experts including co-principal investigators Vlad Kindratenko, Yue Shen, and Yuxiong Wang. Their expertise in computational infrastructure, data analysis, and machine learning ensures robust methodologies and advanced techniques, strengthening the mission’s interdisciplinary foundation.

DeepDISC’s adaptability extends beyond Euclid to other space missions like the Vera C. Rubin Observatory, underscoring its potential impact in advancing AI applications in space exploration. CAII’s role is pivotal in fostering collaborations across disciplines, leveraging cutting-edge technology to drive innovation and understanding of the universe.

DeepDISC Framework Enhances Galaxy Detection

The DeepDISC framework, developed by the Center for Artificial Intelligence Innovation (CAII) with NASA funding, addresses a critical challenge in astrophysical imaging: the detection of blended galaxies or overlapping sources. These overlaps complicate accurate measurements in key areas such as photometry, redshift estimation, and weak gravitational lensing. By leveraging machine learning, DeepDISC enhances galaxy detection by distinguishing individual celestial objects within complex images captured by the Euclid space mission.

DeepDISC’s ability to quantify uncertainty in its predictions is a significant advancement for ensuring reliable scientific outputs. This capability allows researchers to better understand the limitations of their data and refine their analyses accordingly. The framework’s application extends beyond the Euclid mission, with potential uses in other space exploration projects like the Vera C. Rubin Observatory.

The development of DeepDISC reflects CAII’s commitment to advancing AI applications in astrophysics. By integrating cutting-edge computational methods, the framework not only improves data analysis accuracy but also sets a foundation for future innovations in space-based research.

DeepDISC’s adaptability extends beyond the Euclid mission, with potential applications in other space exploration projects such as the Vera C. Rubin Observatory. This versatility underscores CAII’s commitment to fostering innovation in astrophysics through cutting-edge computational methods. By integrating diverse expertise and leveraging AI technologies, CAII is driving advancements that enhance our understanding of the universe while setting a foundation for future research initiatives.