AI-Assisted Detector Design for the EIC (AID(2)E)

TL;DR

The paper addresses scalable AI-assisted design for large-scale EIC detectors by formulating a multi-objective optimization problem over detector design variables with objectives such as performance, physics reach, and cost. The approach centers on multi-objective Bayesian optimization (MOBO) and complementary multi-objective genetic algorithms (MOGA), with qNEHVI acquisition and SAASBO/TURBO variants to scale across many design points. The methodology is validated via two closure tests and applied to actual ePIC subsystems (dRICH and B0), achieving convergence to Pareto fronts within hundreds of evaluations and demonstrating potential improvements over nominal geometries. The work enables a distributed AI-assisted detector-design workflow using PanDA/iDDS, supports calibration and Detector-2 planning, and promises cost-efficient, physics-rich optimization for future large-scale nuclear and high-energy physics experiments.

Abstract

Artificial Intelligence is poised to transform the design of complex, large-scale detectors like the ePIC at the future Electron Ion Collider. Featuring a central detector with additional detecting systems in the far forward and far backward regions, the ePIC experiment incorporates numerous design parameters and objectives, including performance, physics reach, and cost, constrained by mechanical and geometric limits. This project aims to develop a scalable, distributed AI-assisted detector design for the EIC (AID(2)E), employing state-of-the-art multiobjective optimization to tackle complex designs. Supported by the ePIC software stack and using Geant4 simulations, our approach benefits from transparent parameterization and advanced AI features. The workflow leverages the PanDA and iDDS systems, used in major experiments such as ATLAS at CERN LHC, the Rubin Observatory, and sPHENIX at RHIC, to manage the compute intensive demands of ePIC detector simulations. Tailored enhancements to the PanDA system focus on usability, scalability, automation, and monitoring. Ultimately, this project aims to establish a robust design capability, apply a distributed AI-assisted workflow to the ePIC detector, and extend its applications to the design of the second detector (Detector-2) in the EIC, as well as to calibration and alignment tasks. Additionally, we are developing advanced data science tools to efficiently navigate the complex, multidimensional trade-offs identified through this optimization process.

Figures (4)

• Figure 1: Multi-objective optimization workflows: The left panel shows the Bayesian workflow MOBO, which is the primary choice in this project (generally capable of providing accurate determination Pareto fronts). The right panel shows MOGA (NSGA-II, based on genetic algorithms deb2002fast), which is an alternative approach (more suitable to handle, e.g., possible discontinuities or high-dimensional spaces).
• Figure 2: High-level workflow of AID(2)E: We first demonstrate an AI-assisted framework handling multiple test objectives ("simulations") with a known Pareto front (closure test 1). We also show the feasibility of distributing these simulations across various HPC/HTC clusters using the PanDA framework PanDA-CSBS (closure test 2). Following closure test 1, we replace the test functions with the ePIC software (compute-intensive simulations and reconstruction). The final step is a full integration, where the ePIC software is coupled with a distributed AI-assisted framework that asynchronously orchestrates the design points suggested by AI.
• Figure 3: Results from closure test (Left) The figure depicts the total explored points before DTLZ-2 convergence as a function of design parameters ($n$). Each trial was repeated for statistical robustness, with varying colors indicating a different number of objective. The process continued until either 1000 points were explored or convergence was reached, except for cases with $n=[50, 100]$ and $m=4$ where convergence was not achieved. A comparison with expected computational complexity is underway. (Right) The figure illustrates the time complexity of the qNEHVI acquisition function. According to daulton2021parallel, it is $\mathcal{O}(m\cdot(N+I)^m)$, where $N$ is the observed points and $I$ is partitions in the cached box decomposition. Further studies on varying design parameters and standard latency are in progress to elaborate on the problem's complexity.
• Figure 4: Sub-detector system in ePIC optimized with AID2E: (left) the dRICH design is characterized by two radiators (aerogel and gas) and 6 identical sectors with photosensors cisbani2020ai; (right) The B0 Tracker and the B0 ECAL detector. The magnetic field in the B0 Region is inhomogenous making the optimization more challenging.