Speaker
Description
DREAMS (DaRk mattEr with AI and siMulationS) is a state-of-the-art platform that combines thousands of high-resolution cosmological hydrodynamic simulations with machine learning to probe the nature of dark matter while marginalizing over uncertain baryonic physics. These simulations are run on the Flatiron Institute’s CCA cluster, supported by the Simons Foundation, anchoring DREAMS within an international ecosystem of large-scale computational astrophysics. It includes simulation suites at multiple scales — cosmological boxes, Milky Way zoom-ins, and dwarf galaxies — and spans a range of dark matter models (CDM, WDM, ETHOS-like, atomic DM). By coupling emulators and neural networks to these simulation datasets, DREAMS provides a powerful framework to disentangle dark matter physics from complex astrophysical processes and to forecast observational signatures in current and future surveys.
The goals of the present proposal are:
- Extend DREAMS by incorporating additional dark matter models—such as atomic DM, ETHOS-based acoustic oscillatory scenarios, SIDM variants—and apply advanced neural techniques akin to NeHOD, which uses diffusion models and Transformers trained on DREAMS' WDM zoom-ins.
- Deploy and adapt Denario agents to automate the research workflow using DREAMS data—e.g., generating hypotheses, designing ML architectures, running analyses, synthesizing results, and generating draft publications.
The timeline of the proposal is as follows:
Year 1
Extension of DREAMS: Incorporate new dark matter models beyond those already implemented (e.g. self-interacting DM, atomic DM variants, ETHOS-style oscillatory models).
Data preparation: Generate the relevant simulation outputs within the DREAMS framework and construct training datasets for AI models.
Neural architectures: Begin systematic tests with established methods (CNNs, emulators) as baselines.
Denario integration (early stage): Configure AI agents to suggest architectures and training protocols, adapting them to DREAMS datasets.
Year 2
Push beyond baseline methods by experimenting with diffusion models, Transformers, and graph neural networks (similar in spirit to NeHOD).
Perform large-scale benchmarking across DREAMS suites and dark matter models.
Advance Denario workflows to design experiments and automate analysis pipelines.
Year 3
Comprehensive comparison of AI methods across dark matter models.
Deploy Denario in full workflow mode (data → analysis → figures → draft manuscripts).
Expected Deliverables
-- New simulation analysis pipelines across extended dark matter models.
-- Published comparison of AI techniques (e.g. CNN vs Transformer vs diffusion-based emulators).
-- Fully Denario-generated draft(s) of research articles.
CERN group/ Experiment
CERN Theory Group
| Working area | Area 1" Cutting Edge AI for Offline Data Processing |
|---|---|
| If Other, please specify | Area 6. Large Language Models-based assistants |
| Project goals | The central goal of this project is to harness the power of modern artificial intelligence to accelerate discovery in dark matter physics, by extending the DREAMS (DaRk mattEr with AI and siMulationS) framework and integrating it with next-generation AI agents. DREAMS already provides an unprecedented platform of thousands of high-resolution cosmological simulations run on the Flatiron Institute’s CCA cluster (supported by the Simons Foundation), spanning multiple astrophysical scales and a variety of dark matter models. This project will also serve as a proof-of-concept for agent-based scientific discovery in high-energy physics and cosmology. The project will also be an amazing opportunity to create collaborations with CCA and Simons Foundation for AI research. |
| Timeline | Year 1 Extension of DREAMS: Incorporate new dark matter models beyond those already implemented (e.g. self-interacting DM, atomic DM variants, ETHOS-style oscillatory models). Data preparation: Generate the relevant simulation outputs within the DREAMS framework and construct training datasets for AI models. Neural architectures: Begin systematic tests with established methods (CNNs, emulators) as baselines. Denario integration (early stage): Configure AI agents to suggest architectures and training protocols, adapting them to DREAMS datasets. Year 2 Push beyond baseline methods by experimenting with diffusion models, Transformers, and graph neural networks (similar in spirit to NeHOD). Perform large-scale benchmarking across DREAMS suites and dark matter models. Advance Denario workflows to design experiments and automate analysis pipelines. Year 3 Comprehensive comparison of AI methods across dark matter models. Deploy Denario in full workflow mode (data → analysis → figures → draft manuscripts). |
| Available person power | 1. LD Staff at CERN. 2. Associate Professor at Princeton University 3. Senior Research Scientist at CCA. 4. Senior AI Researcher at Microsoft. |
| Additional person power request | Partial PI salary coverage (20%, what my ERC doesn’t cover) to ensure consistent leadership, coordination, and cross-institutional integration of DREAMS at CERN. 1 CERN Fellow (3 years) with expertise in both cosmology and AI/ML architectures. |