Inference-optimized AI and high performance computing for gravitational wave detection at scale

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 hours. 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 porcessed an entire month of advanced LIGO data (including Hanford and Livingston data streams) within 50 seconds. 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.

Interpreting a Machine Learning Model for Detecting Gravitational Waves

“…For instance, the first class of neural networks for gravitational wave detection [George and Huerta, 2018a, George and Huerta, 2017, George and Huerta, 2018b were tested using 4096 second long advanced LIGO data segments, reporting one misclassification for every 200 seconds of searched data. More sophisticated neural networks have been developed to test days-and weeks-long advanced LIGO data, reporting one misclassification for every 2.7 days of searched data [Wei et al, 2021], and one misclassification for every month of searched data [Chaturvedi et al, 2022]. In brief, the ML ensemble we used in this study represents a class of neural networks that are adequate for accelerated, data-driven gravitational wave detection st scale.…”