Unraveling particle dark matter with Physics-Informed Neural Networks
arXiv:2502.17597 · doi:10.1016/j.physletb.2025.139690
Abstract
We parametrically solve the Boltzmann equations governing freeze-in dark matter (DM) in alternative cosmologies with Physics-Informed Neural Networks (PINNs), a mesh-free method. Through inverse PINNs, using a single DM experimental point -- observed relic density -- we determine the physical attributes of the theory, namely power-law cosmologies, inspired by braneworld scenarios, and particle interaction cross sections. The expansion of the Universe in such alternative cosmologies has been parameterized through a switch-like function reproducing the Hubble law at later times. Without loss of generality, we model more realistically this transition with a smooth function. We predict a distinct pair-wise relationship between power-law exponent and particle interactions: for a given cosmology with negative (positive) exponent, smaller (larger) cross sections are required to reproduce the data. Lastly, via Bayesian methods, we quantify the epistemic uncertainty of theoretical parameters found in inverse problems.
26 LaTeX pages; 12 figures. Comments added in the main text, new Fig. 5 added and references added. Matches version published in PLB
References in corpus (26)
- Combined Measurement of the Higgs Boson Mass in Collisions at and 8 TeV with the ATLAS and CMS Experiments
- First Dark Matter Search Results from the LUX-ZEPLIN (LZ) Experiment
- The Dawn of FIMP Dark Matter: A Review of Models and Constraints
- Dark Matter Search Results from the PandaX-4T Commissioning Run
- A Physics-Informed Machine Learning Approach for Solving Heat Transfer Equation in Advanced Manufacturing and Engineering Applications
- micrOMEGAs4.1: two dark matter candidates
- Kolmogorov Arnold Informed neural network: A physics-informed deep learning framework for solving forward and inverse problems based on Kolmogorov Arnold Networks
- Extra-weakly Interacting Dark Matter
- Freezing-in hadrophilic dark matter at low reheating temperatures
- WIMPs during Reheating
- Higgs boson induced reheating and ultraviolet frozen-in dark matter
- Primordial black hole versus inflaton
- Long lived inert Higgs in fast expanding universe and its imprint on cosmic microwave background
- From WIMPs to FIMPs: Impact of Early Matter Domination
- Cosmology-informed neural networks to solve the background dynamics of the Universe
- Gauss-Bonnet braneworld cosmological effect on relic density of dark matter
- Using physics-informed neural networks to compute quasinormal modes
- Unitarity Bound on Dark Matter in Low-temperature Reheating Scenarios
- Superheavy WIMP dark matter from incomplete thermalization
- Solving the Pulsar Equation using Physics-Informed Neural Networks
- Exploring the flavor structure of quarks and leptons with reinforcement learning
- Thermal and nonthermal dark matters with gravitational neutrino reheating
- Analyzing the effect of higher dimensions on the black hole silhouette, deflection angles, and PINN approximated quasinormal modes
- WIMP dark matter in bulk viscous non-standard cosmologies
- Physics-informed neural networks for solving functional renormalization group on a lattice
- FIMP Dark Matter in bulk viscous non-standard cosmologies