Conveners
Simulation & inference: constrained simulation
- Hong Guo (Shanghai Astronomical Observatory)
Simulation & inference: Machine learning
- Yin Li
I will present a review on how to use targets provided by galaxies, galaxy groups and reconstructed density field to study the cosmic web, galaxy formation and evolution.
Machine learning techniques are widely implemented to predict galaxy properties based on halo or subhalo properties in semi-analytic models (SAM) and hydrodynamic simulations. The multivariate relation between galaxy and halo or subhalo can be captured and reproduced efficiently. However, the galaxy formation and evolution in galaxy formation models may deviate from those in the real Universe,...
I will discuss our work on the reconstruction of the cosmic velocity field from the redshift-space distribution of dark matter halos using the state-of-the-art deep learning technique. We were able to accurately recover the magnitude, divergence and vorticity of the velocity field, with the power spectra recovered at 80% accuracy at $k < 1.1\ h$/Mpc. This approach is very promising and...
We develop a deep learning technique to reconstruct the dark matter density field from the redshift-space distribution of dark matter halos. We implement a UNet-architecture neural network and successfully trained it using the COLA fast simulation, which is an approximation of the N-body simulation with $512^3$ particles in a box size of $500 \mpch$. We evaluate the resulting UNet model not...
Obtaining well-calibrated probability density functions (PDFs) of photometric redshift (photo-z) for galaxies without using spectroscopy remains a challenge for many science goals. Deep learning tools have proven to be powerful for this task and gained growing popularity. These include, in particular, state-of-the-art deep neural networks that are typically fed with multi-band galaxy images or...
