Finding Environmental Measures Sensitive to Halo Properties Using Neural Networks

Explore the application of neural networks in identifying environmental measures sensitive to halo properties in this 27-minute conference talk by Haley Bowden from Steward Observatory. Delve into the intersection of astrostatistics, machine learning, and galaxy formation as part of the Kavli Institute for Theoretical Physics' conference on data-driven tools in galaxy formation physics. Gain insights into how advanced data science techniques can enhance our understanding of galaxy evolution, linking observations with theoretical models such as cosmological hydrodynamical simulations. Discover the potential of these tools in analyzing vast datasets from current and future surveys, including Integral Field Unit data and multi-wavelength imaging. Learn about the conference's focus on translating data-driven results into physical understanding and its aim to maximize the benefits of astrostatistics and machine learning for the galaxy formation field.