arXiv subjects

Pooyan Goodarzi

Publications and source records attributed to Pooyan Goodarzi.

4 recordsLinked to original sources

arXiv2025

Graph Neural Networks for Interferometer Simulations

In recent years, graph neural networks (GNNs) have shown tremendous promise in solving problems in high energy physics, materials science, and fluid dynamics. In this work, we introduce a new application for GNNs in the physical sciences: instrumentation design. As a case study, we apply GNNs to simulate models of the Laser Interferometer Gravitational-Wave Observatory (LIGO) and show that they are capable of accurately capturing the complex optical physics at play, while achieving runtimes 815 times faster than state of the art simulation packages. We discuss the unique challenges this problem provides for machine learning models. In addition, we provide a dataset of high-fidelity optical physics simulations for three interferometer topologies, which can be used as a benchmarking suite for future work in this direction.

astro-ph.IM↗

arXiv2025

Error signals for overcoming the laser power limits of gravitational-wave detectors

A major barrier to improving the quantum-limited sensitivity of gravitational-wave observatories is the thermal distortions of the test masses which arise at megawatt laser power. Recent advances in a new form of higher-order wavefront correction, in which corrective heating profiles are applied to the test mass surfaces near their edges, together with other planned instrumental upgrades, have the potential to enable a tenfold reduction of the quantum noise floor of future detectors. However, realizing high levels of quantum noise reduction in practice hinges on identifying measurable error signals to finely control each wavefront actuator, in order to suppress wavefront errors to a few-nanometer precision across the full mirror apertures. No direct source of such an error signal exists in LIGO today. We demonstrate that thermally imaging the surface of each test mass can provide these critical error signals. We show that the surface temperature profiles obtained from thermal imaging can be uniquely mapped to a finite element model of the mirror whose complete thermal state is identified, enabling full-aperture wavefront reconstruction and direct error signals for real-time precision wavefront control. This new sensing capability can enable up to a 31% strain sensitivity improvement in LIGO A+ at 95% confidence, increasing the sky-averaged detection range for binary neutron star mergers by 10 Mpc, and will be integral to a next-generation 40-km gravitational-wave observatory in the U.S., Cosmic Explorer.

astro-ph.IM↗

arXiv2024

Multivariate Time Series Clustering for Environmental State Characterization of Ground-Based Gravitational-Wave Detectors

Gravitational-wave observatories like LIGO are large-scale, terrestrial instruments housed in infrastructure that spans a multi-kilometer geographic area and which must be actively controlled to maintain operational stability for long observation periods. Despite exquisite seismic isolation, they remain susceptible to seismic noise and other terrestrial disturbances that can couple undesirable vibrations into the instrumental infrastructure, potentially leading to control instabilities or noise artifacts in the detector output. It is, therefore, critical to characterize the seismic state of these observatories to identify a set of temporal patterns that can inform the detector operators in day-to-day monitoring and diagnostics. On a day-to-day basis, the operators monitor several seismically relevant data streams to diagnose operational instabilities and sources of noise using some simple empirically-determined thresholds. It can be untenable for a human operator to monitor multiple data streams in this manual fashion and thus a distillation of these data-streams into a more human-friendly format is sought. In this paper, we present an end-to-end machine learning pipeline for features-based multivariate time series clustering to achieve this goal and to provide actionable insights to the detector operators by correlating found clusters with events of interest in the detector.

cs.LG↗

arXiv2023

Applications of Deep Learning to physics workflows

Modern large-scale physics experiments create datasets with sizes and streaming rates that can exceed those from industry leaders such as Google Cloud and Netflix. Fully processing these datasets requires both sufficient compute power and efficient workflows. Recent advances in Machine Learning (ML) and Artificial Intelligence (AI) can either improve or replace existing domain-specific algorithms to increase workflow efficiency. Not only can these algorithms improve the physics performance of current algorithms, but they can often be executed more quickly, especially when run on coprocessors such as GPUs or FPGAs. In the winter of 2023, MIT hosted the Accelerating Physics with ML at MIT workshop, which brought together researchers from gravitational-wave physics, multi-messenger astrophysics, and particle physics to discuss and share current efforts to integrate ML tools into their workflows. The following white paper highlights examples of algorithms and computing frameworks discussed during this workshop and summarizes the expected computing needs for the immediate future of the involved fields.

hep-ex↗