Accelerated, scalable and reproducible AI-driven gravitational wave detection

Abstract

Finding new ways to use artificial intelligence (AI) to accelerate the analysis of gravitational wave data, and ensuring the developed models are easily reusable promises to unlock new opportunities in multi-messenger astrophysics (MMA), and to enable wider use, rigorous validation, and sharing of developed models by the community. In this work, we demonstrate how connecting recently deployed DOE and NSF-sponsored cyberinfrastructure allows for new ways to publish models, and to subsequently deploy these models into applications using computing platforms ranging from laptops to high performance computing clusters. We develop a workflow that connects the Data and Learning Hub for Science (DLHub), a repository for publishing machine learning models, with the Hardware Accelerated Learning (HAL) deep learning computing cluster, using funcX as a universal distributed computing service. We then use this workflow to search for binary black hole gravitational wave signals in open source advanced LIGO data. We find that using this workflow, an ensemble of four openly available deep learning models can be run on HAL and process the entire month of August 2017 of advanced LIGO data in just seven minutes, identifying all four binary black hole mergers previously identified in this dataset, and reporting no misclassifications. This approach, which combines advances in AI, distributed computing, and scientific data infrastructure opens new pathways to conduct reproducible, accelerated, data-driven gravitational wave detection.

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

“…For instance, in Wei et al ( 2021b ), it was reported that an ensemble of 2 AI models reported 1 misclassification for every 2.7 days of searched data, and more basic AI architectures reported one misclassification for every 200 s of searched advanced LIGO data (George and Huerta, 2018a , b ). For completeness, it is worth mentioning that the results we present in Figure 6 differ from those we computed with traditional models in less than 0.01% (Huerta et al, 2021 ).…”

“…Figure 7 presents scaling results as we distributed AI inference in the ThetaGPU supercomputer using both traditional AI models, labeled as , and inference-optimized AI models, labeled as . These results show that our AI ensemble provides a 3 X speedup over traditional AI models (Huerta et al, 2021 ). These results also indicate that the environment setup we used in ThetaGPU optimally handled I/O and data distribution across nodes.…”

“…Our analysis indicates that with our proposed approach, we are able to process these datasets within 50 s using 20 nodes in the ThetaGPU supercomputer at Argonne Leadership Computing Facility. Most importantly, we find that these optimized models retain the same sensitivity of traditional AI models, since they are able to identify all binary black hole mergers in this month-long dataset, while also reporting no misclassifications, and reducing time-to-insight by up to 3 X compared to traditional AI models (Huerta et al, 2021 ).…”

“…In this article, we build upon our recent work developing AI frameworks for production scale gravitational wave detection (Huerta et al, 2021 ; Wei et al, 2021b ), and introduce an approach that consists of optimizing AI models for accelerated inference, levering (NVIDIA, 2021 ). We describe how we deployed our AI ensemble in the ThetaGPU supercomputer at Argonne Leadership Computing Facility, and developed the required software to optimally distribute inference using up to 20 nodes, which are equivalent to 160 NVIDIA A100 Tensor Core GPUs.…”

Precision dentistry—what it is, where it fails (yet), and how to get there

“…Data is considered a key resource for striving modern societies [ 17 ]. Many recent academic breakthroughs in astronomy [ 18 ], biology [ 19 ], and other disciplines are mostly and foremost driven by the analyses of huge data collections. Recently, we reflected on the transformational potential of rigorously applying data-centric principles in dentistry [ 20 ].…”