Applications of Deep Learning to physics workflows

TL;DR

This paper reviews how deep learning and AI are transforming physics workflows by enhancing efficiency and processing large datasets, with insights from a 2023 MIT workshop across multiple physics disciplines.

Contribution

It summarizes recent efforts and discusses the integration of ML tools into physics workflows, highlighting algorithms, frameworks, and future computing needs.

Findings

ML can improve physics algorithm performance

Deep learning accelerates data processing in physics

Workshop insights on future computational requirements

Abstract

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.