John Wu, Space Telescope Science Institute

Title: Astronomy Re-envisioned: Investigating the Physics of Galaxy Evolution with Machine Learning

Abstract: Interpretable machine learning (ML) techniques and artificial intelligence (AI) are revolutionizing our ability to study galaxy evolution and large-scale structure. Convolutional neural networks (CNNs) can now reliably predict galaxies' physical properties, including cold gas content and metallicity, directly from three-color optical images. 

These models can even reconstruct entire optical spectra from imaging alone. Highly optimized CNNs can also robustly identify nearby dwarf galaxies from wide-area surveys, expanding the sample of known low-redshift satellite systems by over 10-fold. Meanwhile, graph neural networks (GNNs) can encode simulated galaxies amid their surroundings, learning how the galaxy–halo connection varies with large-scale environment. These applications demonstrate how explainable ML models with strong inductive biases enables new scientific insights in galaxy evolution and cosmology. 

In the era of wide-area galaxy surveys by the Vera C. Rubin Observatory, Nancy Grace Roman Space Telescope and Euclid, advanced ML and interpretable AI methods will play an increasingly prominent role in extracting physical understanding from astronomical datasets.