Science and Technology Interest Group
Artificial Intelligence and Machine Learning Science and Technology Interest Group
The NASA Cosmic Origins Program AI/ML Science and Technology Interest Group (AI/ML STIG) addresses the critical need to upskill the astronomy community with AI literacy. We provide structured, domain-specific AI education through stackable, bite-sized modular training designed for astronomical research contexts.
About AI/ML STIG
Building AI Literacy for Astronomical Research
Astrophysics is an emerging technology for big-data science, and the use of Artificial Intelligence (AI) and Machine Learning (ML) technology will be inevitable in the coming decades.
The AI and ML Science and Technology Interest Group (AI/ML STIG) is motivated by the awareness that upskilling the scientific community could have a transformative impact to counter critical challenges facing astronomical research today.
By providing structured, domain-specific AI education, the AI/ML STIG aims to accelerate NASA's competitive advantage in AI-enabled space science, build the interdisciplinary workforce essential for next-generation astronomical discoveries, create a model for other NASA programs facing similar upskilling challenges, and establish NASA’s leadership in responsible AI adoption to maximize the science return from its missions by the community. The modular, community-driven approach ensures scalability while maintaining the rigor and domain relevance essential for meaningful scientific advancement. This STIG serves as a focal point for addressing these challenges through community townhalls for discussions and organizing short tutorials to address specific astronomical AI applications, modules, and foundational concepts.
Subscribe to the AI/ML STIG Email List
To join the list, send an email to AI-ML-STIG-join@lists.nasa.gov with Subject="join"
To unsubscribe, send an email to AI-ML-STIG-leave@lists.nasa.gov with Subject="leave"
Your email address will be used only for the purpose of subscription to the selected email distribution list. For further information, read the NASA Web Privacy Policy.
STIG Leadership
| Yuan-Sen Ting | OSU |
| Alex Gagliano | MIT |
| Siddharth Mishra-Sharma | Boston University |
| Digvijay Wadekar | Johns Hopkins |
| Andrew Saydjari | Princeton |
| Carol Cuesta-Lazaro | MIT |
| Georgios Valogiannis | UChicago |
News & Events
Meetings, conferences, seminars, workshops, and other news and events for the STIG
Build a decoder-only transformer (a small GPT-like language model) from scratch in PyTorch. Train it on the Tiny Shakespeare dataset for character-level language modeling and use it to generate text, understanding every component along the way.
Graph Neural Networks (GNNs) Speaker Tri Nguyen, Northwestern Learn how to build Graph Neural Networks (GNNs) to work with graph-structured data. Explore node classification on citation networks and apply GNNs to model dark matter subhalo interactions with stellar streams using…
Convolutional Neural Networks (CNNs) Speaker John Wu, STScI Build a convolutional neural network (CNN) to estimate physical properties of galaxies directly from images. Train a model to predict gas-phase metallicity from SDSS galaxy images, replicating the approach from Wu &…
Inductive Biases Speaker John Wu, STScI Understand how different neural network architectures encode different assumptions about data structure. Compare MLPs, CNNs, RNNs, and Transformers through the lens of inductive biases using synthetic exoplanet transit detection as a case study. Topics…
The 247th AAS meeting (joint with the Historical Astronomy Division) will be held 4-8 January in Phoenix, Arizona at the Phoenix Convention Center. Join us in the exhibit hall at the NASA booth and attend the NASA sessions.
JAX Speaker Philip Cargile (Harvard CfA) Dive into JAX, Google’s high-performance numerical computing library. Learn how JAX combines NumPy-like syntax with automatic differentiation, vectorization, and JIT compilation to accelerate scientific computing and machine learning workflows. Topics Covered: Meeting Connection Join…
News Straight to Your Inbox
Subscribe to your community email news list
We will never share your email address.
