Machine Learning Pipelines with Modern Big Data Tools for High Energy Physics

TL;DR

This paper presents a comprehensive solution for implementing scalable machine learning pipelines in high energy physics by integrating Big Data tools like Apache Spark, BigDL, and TensorFlow with HEP data formats and workflows.

Contribution

It introduces an end-to-end data pipeline framework that combines Spark, ROOT data formats, and distributed neural network training tools for HEP applications.

Findings

Successful integration of ROOT data with Spark for scalable data processing

Distributed training of neural networks on CPU and GPU resources

Enhanced efficiency of HEP data analysis workflows

Abstract

The effective utilization at scale of complex machine learning (ML) techniques for HEP use cases poses several technological challenges, most importantly on the actual implementation of dedicated end-to-end data pipelines. A solution to these challenges is presented, which allows training neural network classifiers using solutions from the Big Data and data science ecosystems, integrated with tools, software, and platforms common in the HEP environment. In particular, Apache Spark is exploited for data preparation and feature engineering, running the corresponding (Python) code interactively on Jupyter notebooks. Key integrations and libraries that make Spark capable of ingesting data stored using ROOT format and accessed via the XRootD protocol, are described and discussed. Training of the neural network models, defined using the Keras API, is performed in a distributed fashion on Spark clusters by using BigDL with Analytics Zoo and also by using TensorFlow, notably for distributed training on CPU and GPU resourcess. The implementation and the results of the distributed training are described in detail in this work.