I am a theoretical astrophysicist working on several aspects of cosmology. I investigate the properties of the large-scale structure of the Universe with the goal of using cosmological observations to learn about fundamental physics. The goal of my research is to develop the tools that will allow to extract every single bit of cosmological information from cosmic surveys. To achieve this, I combine machine/deep learning techniques with very large sets of state-of-the-art numerical simulations. I am particularly interested in understanding the impact of neutrino masses on cosmological observables, that I study combining analytic techniques and state-of-the-art numerical simulations. My research also involves investigating how cosmological and astrophysical information can be extracted from 21cm intensity mapping surveys. I have also worked on other topics such as the Lyman-alpha forest, modified gravity, BAO reconstruction, kSZ and galaxy formation and evolution. More recently, my research interests have been moving to machine learning, and its usage in cosmology.
I am the main architect of the Quijote simulations: a suite of more than 85,000 full N-body simulations containing trillions of particles over a combined cosmological volume larger than the volume of the entire observable Universe. I also developed its precursor, the HADES simulations. I am part of the core team who designed and developed the Cosmology and Astrophysics with MachinE Learning Simulations,
CAMELS, a suite of thousands of state-of-the-art cosmological (magneto-)hydrodynamic simulations designed to train machine learning algorithms. I am also the main developer of the Pylains libraries, a set of python, cython and C libraries designed to analyze numerical simulations.
I am one of the primary developers of the Denario project, a complex AI multi-agent system designed for scientific discovery. Denario can generate ideas, check literature, develop research plans, write and execute code, and write and review papers. I'm currently working with a large team of scientists from various fields, including astrophysics, biology, biophysics, chemistry, material science, neuroscience, planetary science, and quantum physics, as well as experts in machine learning, mathematics, and philosophy. Together, we are pushing the boundaries of what large-language models (LLMs) can achieve in scientific research.