High Energy Physics Data Analysis Research Articles

PASCL: supervised contrastive learning with perturbative augmentation for particle decay reconstruction

Abstract In high-energy physics, particles produced in collision events decay in a format of a hierarchical tree structure, where only the final decay products can be observed using detectors. However, the large combinatorial space of possible tree structures makes it challenging to recover the actual decay process given a set of final particles. To better analyse the hierarchical tree structure, we propose a graph-based deep learning model to infer the tree structure to reconstruct collision events. In particular, we use a compact matrix representation termed as lowest common ancestor generations matrix, to encode the particle decay tree structure. Then, we introduce a perturbative augmentation technique applied to node features, aiming to mimic experimental uncertainties and increase data diversity. We further propose a supervised graph contrastive learning algorithm to utilize the information of inter-particle relations from multiple decay processes. Extensive experiments show that our proposed supervised graph contrastive learning with perturbative augmentation method outperforms state-of-the-art baseline models on an existing physics-based dataset, significantly improving the reconstruction accuracy. This method provides a more effective training strategy for models with the same parameters and makes way for more accurate and efficient high-energy particle physics data analysis.

Machine Learning for Columnar High Energy Physics Analysis

Machine learning (ML) has become an integral component of high energy physics data analyses and is likely to continue to grow in prevalence. Physicists are incorporating ML into many aspects of analysis, from using boosted decision trees to classify particle jets to using unsupervised learning to search for physics beyond the Standard Model. Since ML methods have become so widespread in analysis and these analyses need to be scaled up for HL-LHC data, neatly integrating ML training and inference into scalable analysis workflows will improve the user experience of analysis in the HL-LHC era.We present the integration of ML training and inference into the IRISHEP Analysis Grand Challenge pipeline to provide an example of how this integration can look like in a realistic analysis environment. We also utilize Open Data to ensure the project’s reach to the broader community. Different approaches for performing ML inference at analysis facilities are investigated and compared, including performing inference through external servers. Since ML techniques are applied for many different types of tasks in physics analyses, we showcase options for ML integration that can be applied to various inference needs.

Evaluating query languages and systems for high-energy physics data

In the domain of high-energy physics (HEP), general-purpose query languages have found little adoption in analysis. This is surprising regarding SQL-based systems, as HEP data analysis matches SQL’s processing model well: the data is fully structured and makes use of predominantly standard operators. To better understand the situation, we select six general-purpose query engines, from both the SQL and NoSQL domain, and analyze their performance, scalability, and usability in HEP analysis, employing standard HEP tools as baseline. We also identify a set of core language features needed to support HEP data analysis. Our results reveal an interesting and complex picture: several query languages provide a rich and natural query development experience, while others fall short. In terms of performance, our results reveal that many of the database systems are one or two orders of magnitude slower than the standard HEP analysis tools, while others manage to scale and perform well. These conclusions suggest that while the existing data processing systems are viable candidates for HEP analysis, there is still work to be done to improve their performance and ability to succinctly express HEP queries.

Leveraging an open source serverless framework for high energy physics computing

CERN (Centre Europeen pour la Recherce Nucleaire) is the largest research centre for high energy physics (HEP). It offers unique computational challenges as a result of the large amount of data generated by the large hadron collider. CERN has developed and supports a software called ROOT, which is the de facto standard for HEP data analysis. This framework offers a high-level and easy-to-use interface called RDataFrame, which allows managing and processing large data sets. In recent years, its functionality has been extended to take advantage of distributed computing capabilities. Thanks to its declarative programming model, the user-facing API can be decoupled from the actual execution backend. This decoupling allows physical analysis to scale automatically to thousands of computational cores over various types of distributed resources. In fact, the distributed RDataFrame module already supports the use of established general industry engines such as Apache Spark or Dask. Notwithstanding the foregoing, these current solutions will not be sufficient to meet future requirements in terms of the amount of data that the new projected accelerators will generate. It is of interest, for this reason, to investigate a different approach, the one offered by serverless computing. Based on a first prototype using AWS Lambda, this work presents the creation of a new backend for RDataFrame distributed over the OSCAR tool, an open source framework that supports serverless computing. The implementation introduces new ways, relative to the AWS Lambda-based prototype, to synchronize the work of functions.

Quantum convolutional neural networks for high energy physics data analysis

This paper presents a quantum convolutional neural network (QCNN) for the classification of high energy physics events. The proposed model is tested using a simulated dataset from the Deep Underground Neutrino Experiment. The proposed quantum architecture demonstrates an advantage of learning faster than the classical convolutional neural networks (CNNs) under a similar number of parameters. In addition to the faster convergence, the QCNN achieves a greater test accuracy compared to CNNs. Based on our results from numerical simulations, it is a promising direction to apply QCNN and other quantum machine learning models to high energy physics and other scientific fields.

Challenges and opportunities in quantum machine learning for high-energy physics

Quantum machine learning may provide powerful tools for data analysis in high-energy physics. Sau Lan Wu and Shinjae Yoo describe how the potential of these tools is starting to be tested and what has been understood thus far.

Evaluating query languages and systems for high-energy physics data

In the domain of high-energy physics (HEP), query languages in general and SQL in particular have found limited acceptance. This is surprising since HEP data analysis matches the SQL model well: the data is fully structured and queried using mostly standard operators. To gain insights on why this is the case, we perform a comprehensive analysis of six diverse, general-purpose data processing platforms using an HEP benchmark. The result of the evaluation is an interesting and rather complex picture of existing solutions: Their query languages vary greatly in how natural and concise HEP query patterns can be expressed. Furthermore, most of them are also between one and two orders of magnitude slower than the domain-specific system used by particle physicists today. These observations suggest that, while database systems and their query languages are in principle viable tools for HEP, significant work remains to make them relevant to HEP researchers.

Scalable Declarative HEP Analysis Workflows for Containerised Compute Clouds.

We describe a novel approach for experimental High-Energy Physics (HEP) data analyses that is centred around the declarative rather than imperative paradigm when describing analysis computational tasks. The analysis process can be structured in the form of a Directed Acyclic Graph (DAG), where each graph vertex represents a unit of computation with its inputs and outputs, and the graph edges describe the interconnection of various computational steps. We have developed REANA, a platform for reproducible data analyses, that supports several such DAG workflow specifications. The REANA platform parses the analysis workflow and dispatches its computational steps to various supported computing backends (Kubernetes, HTCondor, Slurm). The focus on declarative rather than imperative programming enables researchers to concentrate on the problem domain at hand without having to think about implementation details such as scalable job orchestration. The declarative programming approach is further exemplified by a multi-level job cascading paradigm that was implemented in the Yadage workflow specification language. We present two recent LHC particle physics analyses, ATLAS searches for dark matter and CMS jet energy correction pipelines, where the declarative approach was successfully applied. We argue that the declarative approach to data analyses, combined with recent advancements in container technology, facilitates the portability of computational data analyses to various compute backends, enhancing the reproducibility and the knowledge preservation behind particle physics data analyses.

Striped Data Analysis Framework

A columnar data representation is known to be an efficient way for data storage, specifically in cases when the analysis is often done based only on a small fragment of the available data structures. A data representation like Apache Parquet is a step forward from a columnar representation, which splits data horizontally to allow for easy parallelization of data analysis. Based on the general idea of columnar data storage, working on the [LDRD Project], we have developed a striped data representation, which, we believe, is better suited to the needs of High Energy Physics data analysis. A traditional columnar approach allows for efficient data analysis of complex structures. While keeping all the benefits of columnar data representations, the striped mechanism goes further by enabling easy parallelization of computations without requiring special hardware. We will present an implementation and some performance characteristics of such a data representation mechanism using a distributed no-SQL database or a local file system, unified under the same API and data representation model. The representation is efficient and at the same time simple so that it allows for a common data model and APIs for wide range of underlying storage mechanisms such as distributed no-SQL databases and local file systems. Striped storage adopts Numpy arrays as its basic data representation format, which makes it easy and efficient to use in Python applications. The Striped Data Server is a web service, which allows to hide the server implementation details from the end user, easily exposes data to WAN users, and allows to utilize well known and developed data caching solutions to further increase data access efficiency. We are considering the Striped Data Server as the core of an enterprise scale data analysis platform for High Energy Physics and similar areas of data processing. We have been testing this architecture with a 2TB dataset from a CMS dark matter search and plan to expand it to multiple 100 TB or even PB scale. We will present the striped format, Striped Data Server architecture and performance test results.

Machine learning classification: Case of Higgs boson CP state in H→ττ decay at the LHC

Machine Learning (ML) techniques are rapidly finding a place among the methods of High Energy Physics data analysis. Different approaches are explored concerning how much effort should be put into building high-level variables based on physics insight into the problem, and when it is enough to rely on low-level ones, allowing ML methods to find patterns without explicit physics model. In this paper we continue the discussion of previous publications on the CP state of the Higgs boson measurement of the H to tau tau decay channel with the consecutive tau^pm to rho^pm nu; rho^pm to pi^pm pi^0 and tau^pm to a_1^pm nu; a_1^pm to rho^0 pi^pm to 3 pi^pm cascade decays. The discrimination of the Higgs boson CP state is studied as a binary classification problem between CP-even (scalar) and CP-odd (pseudoscalar), using Deep Neural Network (DNN). Improvements on the classification from the constraints on directly non-measurable outgoing neutrinos are discussed. We find, that once added, they enhance the sensitivity sizably, even if only imperfect information is provided. In addition to DNN we also evaluate and compare other ML methods: Boosted Trees (BT), Random Forest (RF) and Support Vector Machine (SVN).

Application of pivoting adversarial networks in search for four top quark production in CMS

One burden of high energy physics data analysis is uncertainty within the measurement, both systematically and statistically. Even with sophisticated neural network techniques that are used to assist in high energy physics measurements, the resulting measurement may suffer from both types of uncertainties. Fortunately, most types of systematic uncertainties are based on knowledge from information such as theoretical assumptions, for which the range and behaviour are known. It has been proposed to mitigate such systematic uncertainties by using a new type of neural network called adversarial neural network (ANN) that would make the discriminator less sensitive to these uncertainties, but this has not yet been demonstrated in a real-life LHC analysis. This work investigates ANNs using as a benchmark the search for the production of four top quarks, an extremely rare physics process at the LHC and one of the important processes that can prove or disprove the Standard Model. The search for four top quarks in some cases is sensitive to large systematic uncertainties. The expected cross section upper limit for four top quark production is calculated using traditional neural networks and adversarial neural networks based on simulated proton-proton collisions within the Compact Muon Solenoid detector within Large Hadron Collider, and are compared to existing results. The improvement and further considerations to the search for rare processes at the LHC will be discussed.

Striped Data Server for Scalable Parallel Data Analysis

A columnar data representation is known to be an efficient way for data storage, specifically in cases when the analysis is often done based only on a small fragment of the available data structures. A data representation like Apache Parquet is a step forward from a columnar representation, which splits data horizontally to allow for easy parallelization of data analysis. Based on the general idea of columnar data storage, working on the FNAL LDRD Project FNAL-LDRD-2016-032, we have developed a striped data representation, which, we believe, is better suited to the needs of High Energy Physics data analysis. A traditional columnar approach allows for efficient data analysis of complex structures. While keeping all the benefits of columnar data representations, the striped mechanism goes further by enabling easy parallelization of computations without requiring special hardware. We will present an implementation and some performance characteristics of such a data representation mechanism using a distributed no-SQL database or a local file system, unified under the same API and data representation model. The representation is efficient and at the same time simple so that it allows for a common data model and APIs for wide range of underlying storage mechanisms such as distributed no-SQL databases and local file systems. Striped storage adopts Numpy arrays as its basic data representation format, which makes it easy and efficient to use in Python applications. The Striped Data Server is a web service, which allows to hide the server implementation details from the end user, easily exposes data to WAN users, and allows to utilize well known and developed data caching solutions to further increase data access efficiency. We are considering the Striped Data Server as the core of an enterprise scale data analysis platform for High Energy Physics and similar areas of data processing. We have been testing this architecture with a 2TB dataset from a CMS dark matter search and plan to expand it to multiple 100 TB or even PB scale. We will present the striped format, Striped Data Server architecture and performance test results.

On the notion “significance of the difference”

The concept of the significance of a signal in presence of background in experiment is widely used in data analysis in high-energy physics. It is shown that when comparing pairs independent samples obtained from one population (Poisson flow of events), the distribution of estimates of the significance is asymptotically standard normal distribution.

Deep Learning and Its Application to LHC Physics

Machine learning has played an important role in the analysis of high-energy physics data for decades. The emergence of deep learning in 2012 allowed for machine learning tools which could adeptly handle higher-dimensional and more complex problems than previously feasible. This review is aimed at the reader who is familiar with high-energy physics but not machine learning. The connections between machine learning and high-energy physics data analysis are explored, followed by an introduction to the core concepts of neural networks, examples of the key results demonstrating the power of deep learning for analysis of LHC data, and discussion of future prospects and concerns.

The use of multivariate analysis of the radon variability in the underground laboratory and indoor environment

Abstract The paper presents results of multivariate analysis of variations of radon concentrations in the shallow underground laboratory and a family house, depending on meteorological variables only. All available multivariate classification and regression methods, developed for data analysis in high-energy physics and implemented in the toolkit for multivariate analysis (TMVA) software package in ROOT, are used in the analysis. The result of multivariate regression analysis is a mapped functional behaviour of variations of radon concentration depending on meteorological variables only, which can be used for the evaluation of radon concentration, as well as to help with modelling of variation of radon concentration. The results of analysis of the radon concentration variations in the underground laboratory and real indoor environment, using multivariate methods, demonstrated the potential usefulness of these methods. Multivariate analysis showed that there is a potentially considerable prediction power of variations of indoor radon concentrations based on the knowledge of meteorological variables only. In addition, the online system using the resulting mapped functional behaviour for underground laboratory in the Institute of Physics Belgrade is implemented, and the resulting evaluation of radon concentrations are presented in this paper.

Successes, Challenges and Future Outlook of Multivariate Analysis In HEP

Multivariate techniques using machine learning algorithms have become an integral part in many High Energy Physics data analyses. This article is intended to sketch how this development took place by pointing out a few analyses that pushed forward the exploitation of these powerful analysis techniques. This article does not focus on controversial issues like for example how systematic uncertainties can be dealt with when using such techniques, which have been widely discussed previously by other authors. The main purpose here is to point to the gain in physics reach of the physics experiments due to the adaptation of machine learning techniques and to the challenges the HEP community faces in the light a rapid development in the field of machine learning if we want to make successful use of these powerful selection and reconstruction techniques.

Correlative and multivariate analysis of increased radon concentration in underground laboratory.

The results of analysis using correlative and multivariate methods, as developed for data analysis in high-energy physics and implemented in the Toolkit for Multivariate Analysis software package, of the relations of the variation of increased radon concentration with climate variables in shallow underground laboratory is presented. Multivariate regression analysis identified a number of multivariate methods which can give a good evaluation of increased radon concentrations based on climate variables. The use of the multivariate regression methods will enable the investigation of the relations of specific climate variable with increased radon concentrations by analysis of regression methods resulting in 'mapped' underlying functional behaviour of radon concentrations depending on a wide spectrum of climate variables.

Comparison of multivariate classification and regression methods for the indoor radon measurements

We present the results of a test usage of multivariate methods, as developed for data analysis in high-energy physics and implemented in the toolkit for multivariate analysis software package, in our analysis of the dependence of the variation of indoor radon concentration on climate variables. The method enables the investigation of the connections of the wide spectrum of climate variables with radon concentrations. We find that multivariate classification and regression methods work well, giving new information and indications, which may be helpful in further research of the variation of radon concentration in indoor spaces. The method may also lead to considerable prediction power of the variations of indoor radon concentrations based on the knowledge of climate variables only.

Computational particle physics for event generators and data analysis

High-energy physics data analysis relies heavily on the comparison between experimental and simulated data as stressed lately by the Higgs search at LHC and the recent identification of a Higgs-like new boson. The first link in the full simulation chain is the event generation both for background and for expected signals. Nowadays event generators are based on the automatic computation of matrix element or amplitude for each process of interest.Moreover, recent analysis techniques based on the matrix element likelihood method assign probabilities for every event to belong to any of a given set of possible processes. This method originally used for the top mass measurement, although computing intensive, has shown its efficiency at LHC to extract the new boson signal from the background.Serving both needs, the automatic calculation of matrix element is therefore more than ever of prime importance for particle physics. Initiated in the 80's, the techniques have matured for the lowest order calculations (tree-level), but become complex and CPU time consuming when higher order calculations involving loop diagrams are necessary like for QCD processes at LHC. New calculation techniques for next-to-leading order (NLO) have surfaced making possible the generation of processes with many final state particles (up to 6). If NLO calculations are in many cases under control, although not yet fully automatic, even higher precision calculations involving processes at 2-loops or more remain a big challenge.After a short introduction to particle physics and to the related theoretical framework, we will review some of the computing techniques that have been developed to make these calculations automatic. The main available packages and some of the most important applications for simulation and data analysis, in particular at LHC will also be summarized (see CCP2012 slides [1]).

PROOF-Lite running experience in High Energy Physics data analysis

Solid-State-Drives are currently introduced in storage facilities for High Energy Physics (HEP) experiments and their performances are measured and compared to standard magnetic disks. For this paper a typical HEP data analysis is performed and used as a test to measure computing performances. The tests exploit the features provided by PROOF-Lite which allows to distribute a huge number of events among different CPU cores, thus reducing the overall time needed to complete the analysis task. These tests are carried on few computational devices typically hosted at a current Tier-2/Tier-3 facility. The performance results are provided in terms of figures of merit and the main issue is scalability described in terms of speed up factor and processing event rate. The obtained results can be used as guideline for both the typical HEP analyst and the Tier-2/Tier-3 manager: the former in the configuration of his own analysis task while dealing with increasing data sizes, the latter in the implementation of an interactive data analysis facility for HEP experiments while facing solutions that concern both technological and economical aspects.