Inference-Optimized AI and High Performance Computing for Gravitational Wave Detection at Scale.

Pranshu Chaturvedi,E A Huerta,Minyang Tian,Huihuo Zheng,Asad Khan

doi:10.3389/frai.2022.828672

Abstract

We introduce an ensemble of artificial intelligence models for gravitational wave detection that we trained in the Summit supercomputer using 32 nodes, equivalent to 192 NVIDIA V100 GPUs, within 2 h. Once fully trained, we optimized these models for accelerated inference using NVIDIA TensorRT. We deployed our inference-optimized AI ensemble in the ThetaGPU supercomputer at Argonne Leadership Computer Facility to conduct distributed inference. Using the entire ThetaGPU supercomputer, consisting of 20 nodes each of which has 8 NVIDIA A100 Tensor Core GPUs and 2 AMD Rome CPUs, our NVIDIA TensorRT-optimized AI ensemble processed an entire month of advanced LIGO data (including Hanford and Livingston data streams) within 50 s. Our inference-optimized AI ensemble retains the same sensitivity of traditional AI models, namely, it identifies all known binary black hole mergers previously identified in this advanced LIGO dataset and reports no misclassifications, while also providing a 3X inference speedup compared to traditional artificial intelligence models. We used time slides to quantify the performance of our AI ensemble to process up to 5 years worth of advanced LIGO data. In this synthetically enhanced dataset, our AI ensemble reports an average of one misclassification for every month of searched advanced LIGO data. We also present the receiver operating characteristic curve of our AI ensemble using this 5 year long advanced LIGO dataset. This approach provides the required tools to conduct accelerated, AI-driven gravitational wave detection at scale.

Highlights

The international network of ground-based gravitational wave interferometers—advanced LIGO (Abbott et al, 2016a,b), advanced Virgo (Acernese et al, 2015; Acernese et al, 2020), and Kagra (Akutsu et al, 2020)—have completed three observing runs, reporting the detection of tens of gravitational wave sources (Abbott et al, 2021b)
We describe the procedure to optimize an ensemble of artificial intelligence (AI) models for accelerated AI inference, and the approach followed to deploy this AI ensemble in the ThetaGPU supercomputer to optimally search for gravitational waves in advanced LIGO data at scale
We used our inference-optimized AI ensemble to process hours, days, weeks, and a month-long advanced LIGO dataset. We found that this AI ensemble was able to identify all binary black hole mergers reported throughout the second observing run that covered the month of August 2017

Summary

Introduction

The international network of ground-based gravitational wave interferometers—advanced LIGO (Abbott et al, 2016a,b), advanced Virgo (Acernese et al, 2015; Acernese et al, 2020), and Kagra (Akutsu et al, 2020)—have completed three observing runs, reporting the detection of tens of gravitational wave sources (Abbott et al, 2021b). We have already witnessed the transformational power of gravitational wave astrophysics in fundamental physics, cosmology, chemistry and nuclear physics (Yunes et al, 2016; Abbottet al., 2017a,b; Abbott et al, 2017c, 2021a,c; Mooley et al, 2018; Miller and Yunes, 2019; Tan et al, 2020) These are only a few glimpses of the scientific revolution that may take place within the decade (Couvares et al, 2021; Kalogera et al, 2021; McClelland et al, 2021; Punturo et al, 2021; Reitze et al, 2021) if we translate the data deluge to be delivered by gravitational wave detectors into the required elements to enable scientific discovery at scale. Recent AI applications for gravitational wave astrophysics includes classification or signal detection (Gabbard et al, 2018; George and Huerta, 2018a,b; Dreissigacker et al, 2019; Fan et al, 2019; Miller et al, 2019; Rebei et al, 2019; Beheshtipour and Papa, 2020; Deighan et al, 2020; Dreissigacker and Prix, 2020; Krastev, 2020; Li et al, 2020a; Schäfer et al, 2020, 2021; Skliris et al, 2020; Wang et al, 2020; Gunny et al, 2021; Lin and Wu, 2021; Schäfer and Nitz, 2021), signal denoising and data cleaning (Shen et al, 2019; Ormiston et al, 2020; Wei and Huerta, 2020; Yu and Adhikari, 2021), regression or parameter estimation (Gabbard et al, 2019; Chua and Vallisneri, 2020; Green and Gair, 2020; Green et al, 2020; Dax et al, 2021a,b; Shen et al, 2022) Khan and Huerta, accelerated waveform production (Chua et al, 2019; Khan and Green, 2021), signal forecasting (Lee et al, 2021; Khan et al, 2022), and early warning systems for gravitational wave sources that include matter, such as binary neutron stars or black hole-neutron star systems (Wei and Huerta, 2021; Wei et al, 2021a; Yu et al, 2021)

Methods

Results

Conclusion