Bjorn Burkle

We describe the construction of end-to-end jet image classifiers based on simulated low-level detector data to discriminate quark- vs. gluon-initiated jets with high-fidelity simulated CMS Open Data. We highlight the importance of precise spatial information and demonstrate competitive performance to existing state-of-the-art jet classifiers. We further generalize the end-to-end approach to event-level classification of quark vs. gluon di-jet QCD events. We compare the fully end-to-end approach to using hand-engineered features and demonstrate that the end-to-end algorithm is robust against the effects of underlying event and pile-up.

Abstract As part of its HL-LHC upgrade program, the CMS collaboration is developing a High Granularity Calorimeter (CE) to replace the existing endcap calorimeters. The CE is a sampling calorimeter with unprecedented transverse and longitudinal readout for both electromagnetic (CE-E) and hadronic (CE-H) compartments. The calorimeter will be built with ∼30,000 hexagonal silicon modules. Prototype modules have been constructed with 6-inch hexagonal silicon sensors with cell areas of 1.1 cm 2 , and the SKIROC2-CMS readout ASIC. Beam tests of different sampling configurations were conducted with the prototype modules at DESY and CERN in 2017 and 2018. This paper describes the construction and commissioning of the CE calorimeter prototype, the silicon modules used in the construction, their basic performance, and the methods used for their calibration.

Abstract The Compact Muon Solenoid collaboration is designing a new high-granularity endcap calorimeter, HGCAL, to be installed later this decade. As part of this development work, a prototype system was built, with an electromagnetic section consisting of 14 double-sided structures, providing 28 sampling layers. Each sampling layer has an hexagonal module, where a multipad large-area silicon sensor is glued between an electronics circuit board and a metal baseplate. The sensor pads of approximately 1.1 cm 2 are wire-bonded to the circuit board and are readout by custom integrated circuits. The prototype was extensively tested with beams at CERN's Super Proton Synchrotron in 2018. Based on the data collected with beams of positrons, with energies ranging from 20 to 300 GeV, measurements of the energy resolution and linearity, the position and angular resolutions, and the shower shapes are presented and compared to a detailed Geant4 simulation.

Machine learning has been applied to several problems in particle physics research, beginning with applications to high-level physics analysis in the 1990s and 2000s, followed by an explosion of applications in particle and event identification and reconstruction in the 2010s. In this document we discuss promising future research and development areas for machine learning in particle physics. We detail a roadmap for their implementation, software and hardware resource requirements, collaborative initiatives with the data science community, academia and industry, and training the particle physics community in data science. The main objective of the document is to connect and motivate these areas of research and development with the physics drivers of the High-Luminosity Large Hadron Collider and future neutrino experiments and identify the resource needs for their implementation. Additionally we identify areas where collaboration with external communities will be of great benefit.

Abstract The CMS experiment at the CERN LHC will be upgraded to accommodate the 5-fold increase in the instantaneous luminosity expected at the High-Luminosity LHC (HL-LHC) [1]. Concomitant with this increase will be an increase in the number of interactions in each bunch crossing and a significant increase in the total ionising dose and fluence. One part of this upgrade is the replacement of the current endcap calorimeters with a high granularity sampling calorimeter equipped with silicon sensors, designed to manage the high collision rates [2]. As part of the development of this calorimeter, a series of beam tests have been conducted with different sampling configurations using prototype segmented silicon detectors. In the most recent of these tests, conducted in late 2018 at the CERN SPS, the performance of a prototype calorimeter equipped with ≈12,000 channels of silicon sensors was studied with beams of high-energy electrons, pions and muons. This paper describes the custom-built scalable data acquisition system that was built with readily available FPGA mezzanines and low-cost Raspberry Pi computers.

We describe a novel application of the end-to-end deep learning technique to the task of discriminating top quark-initiated jets from those originating from the hadronization of a light quark or a gluon. The end-to-end deep learning technique combines deep learning algorithms and low-level detector representation of the high-energy collision event. In this study, we use lowlevel detector information from the simulated CMS Open Data samples to construct the top jet classifiers. To optimize classifier performance we progressively add low-level information from the CMS tracking detector, including pixel detector reconstructed hits and impact parameters, and demonstrate the value of additional tracking information even when no new spatial structures are added. Relying only on calorimeter energy deposits and reconstructed pixel detector hits, the end-to-end classifier achieves a ROC-AUC score of 0.975±0.002 for the task of classifying boosted top quark jets. After adding derived track quantities, the classifier ROC-AUC score increases to 0.9824±0.0013, serving as the first performance benchmark for these CMS Open Data samples.

The replacement of the existing endcap calorimeter in the Compact Muon Solenoid (CMS) detector for the high-luminosity LHC (HL-LHC), scheduled for 2027, will be a high granularity calorimeter. It will provide detailed position, energy, and timing information on electromagnetic and hadronic showers in the immense pileup of the HL-LHC. The High Granularity Calorimeter (HGCAL) will use 120-, 200-, and 300-μm-thick silicon (Si) pad sensors as the main active material and will sustain 1 MeV neutron equivalent fluences up to about 1016 neq cm−2. In order to address the performance degradation of the Si detectors caused by the intense radiation environment, irradiation campaigns of test diode samples from 8-inch and 6-inch wafers were performed in two reactors. Characterization of the electrical and charge collection properties after irradiation involved both bulk polarities for the three sensor thicknesses. Since the Si sensors will be operated at −30oC to reduce increasing bulk leakage current with fluence, the charge collection investigation of 30 irradiated samples was carried out with the infrared-TCT setup at −30oC. TCAD simulation results at the lower fluences are in close agreement with the experimental results and provide predictions of sensor performance for the lower fluence regions not covered by the experimental study. All investigated sensors display 60% or higher charge collection efficiency at their respective highest lifetime fluences when operated at 800 V, and display above 90% at the lowest fluence, at 600 V. The collected charge close to the fluence of 1016 neq cm−2 exceeds 1 fC at voltages beyond 800 V.

Surface damage caused by ionizing radiation in SiO$_2$ passivated silicon particle detectors consists mainly of the accumulation of a positively charged layer along with trapped-oxide-charge and interface traps inside the oxide and close to the Si/SiO$_2$-interface. High density positive interface net charge can be detrimental to the operation of a multi-channel $n$-on-$p$ sensor since the inversion layer generated under the Si/SiO$_2$-interface can cause loss of position resolution by creating a conduction channel between the electrodes. In the investigation of the radiation-induced accumulation of oxide charge and interface traps, a capacitance-voltage characterization study of n/$γ$- and $γ$-irradiated Metal-Oxide-Semiconductor (MOS) capacitors showed that close agreement between measurement and simulation were possible when oxide charge density was complemented by both acceptor- and donor-type deep interface traps with densities comparable to the oxide charges. Corresponding inter-strip resistance simulations of a $n$-on-$p$ sensor with the tuned oxide charge density and interface traps show close agreement with experimental results. The beneficial impact of radiation-induced accumulation of deep interface traps on inter-electrode isolation may be considered in the optimization of the processing parameters of isolation implants on $n$-on-$p$ sensors for the extreme radiation environments.

Abstract Surface damage caused by ionizing radiation in SiO 2 passivated silicon particle detectors consists mainly of the accumulation of a positively charged layer along with trapped-oxide-charge and interface traps inside the oxide and close to the Si/SiO 2 -interface. High density positive interface net charge can be detrimental to the operation of a multi-channel n -on- p sensor since the inversion layer generated under the Si/SiO 2 -interface can cause loss of position resolution by creating a conduction channel between the electrodes. In the investigation of the radiation-induced accumulation of oxide charge and interface traps, a capacitance-voltage characterization study of n/ γ - and γ -irradiated Metal-Oxide-Semiconductor (MOS) capacitors showed that close agreement between measurement and simulation were possible when oxide charge density was complemented by both acceptor- and donor-type deep interface traps with densities comparable to the oxide charges. Corresponding inter-strip resistance simulations of a n -on- p sensor with the tuned oxide charge density and interface traps show close agreement with experimental results. The beneficial impact of radiation-induced accumulation of deep interface traps on inter-electrode isolation may be considered in the optimization of the processing parameters of isolation implants on n -on- p sensors for the extreme radiation environments.

Machine learning algorithms are gaining ground in high energy physics for applications in particle and event identification, physics analysis, detector reconstruction, simulation and trigger. Currently, most data-analysis tasks at LHC experiments benefit from the use of machine learning. Incorporating these computational tools in the experimental framework presents new challenges. This paper reports on the implementation of the end-to-end deep learning with the CMS software framework and the scaling of the end-to-end deep learning with multiple GPUs. The end-to-end deep learning technique combines deep learning algorithms and low-level detector representation for particle and event identification. We demonstrate the end-to-end implementation on a top quark benchmark and perform studies with various hardware architectures including single and multiple GPUs and Google TPU.

We describe a novel application of the end-to-end deep learning technique to the task of discriminating top quark-initiated jets from those originating from the hadronization of a light quark or a gluon. The end-to-end deep learning technique uses low-level detector representation of high-energy collision event as inputs to deep learning algorithms. In this study, we use low-level detector information from the simulated Compact Muon Solenoid (CMS) open data samples to construct the top jet classifiers. To optimize classifier performance we progressively add low-level information from the CMS tracking detector, including pixel detector reconstructed hits and impact parameters, and demonstrate the value of additional tracking information even when no new spatial structures are added. Relying only on calorimeter energy deposits and reconstructed pixel detector hits, the end-to-end classifier achieves an area under the receiver operator curve (AUC) score of $0.975\ifmmode\pm\else\textpm\fi{}0.002$ for the task of classifying boosted top quark jets. After adding derived track quantities, the classifier AUC score increases to $0.9824\ifmmode\pm\else\textpm\fi{}0.0013$, serving as the first performance benchmark for these CMS open data samples.

Leber congenital amaurosis (LCA) is a genetic disease associated with blindness that is caused by mutations in retinal pigment epithelium (RPE65), an enzyme involved in the visual cycle. When light hits photosensitive pigments in the retina, it conformationally changes 11‐cis‐retinol (a form of vitamin A) to 11‐trans‐retinol. This conversion allows for a series of chemical reactions and the formation of electrical signals that communicate with the brain. RPE65 is essential to the cycle because it changes 11‐trans‐retinol back into 11‐cis‐retinol‐‐recycling the enzyme and allowing for sustained vision[1] . The Marquette High SMART (Students Modeling A Research Topic) Team used 3D printing technology to model how mutations in LCA affect RPE65's structure and function. RPE65 has 533 amino acids folded into sheets that arrange themselves into seven propeller blades, which collectively create a mostly hydrophilic tertiary structure. One face of RPE65 is hydrophobic and is associated with the microsomal membrane. A hydrophobic, tunnel‐like structure leads to an iron cofactor that facilitates its enzymatic efficiency. The iron cofactor is held in the active site by the histidine residues H180, H241, H417, and H527 in a coordinated motif. Mutations near the active site cause lowered enzymatic activity and LCA. Other residues that are commonly mutated in LCA include Gly40, Arg91, Glu102, Arg124, His182, and Val473. Ocular imaging data has shown phenotypic changes in the photoreceptors in patients with RPE65 mutations. With novel gene delivery methods and other treatment strategies, these technologies will be useful to understanding how to treat LCA and other retinal diseases. [2] Support or Funding Information This work was supported by the National Institutes of of Health Science Education Partnership Award (NIH‐SEPA 1R25OD010505‐01) and the National Institutes of Health Clinical and Translational Science Award (NIH‐CTSA UL1RR031973).

From particle identification to the discovery of the Higgs boson, deep learning algorithms have become an increasingly important tool for data analysis at the Large Hadron Collider (LHC). We present an innovative end-to-end deep learning approach for jet identification at the Compact Muon Solenoid (CMS) experiment at the LHC. The method combines deep neural networks with low-level detector information, such as calorimeter energy deposits and tracking information, to build a discriminator to identify different particle species. Using two physics examples as references: electron vs. photon discrimination and quark vs. gluon discrimination, we demonstrate the performance of the end-to-end approach on simulated events with full detector geometry as available in the CMS Open Data. We also offer insights into the importance of the information extracted from various sub-detectors and describe how end-to-end techniques can be extended to event-level classification using information from the whole CMS detector.

As part of its HL-LHC upgrade program, the CMS Collaboration is developing a High Granularity Calorimeter (CE) to replace the existing endcap calorimeters. The CE is a sampling calorimeter with unprecedented transverse and longitudinal readout for both electromagnetic (CE-E) and hadronic (CE-H) compartments. The calorimeter will be built with $\sim$30,000 hexagonal silicon modules. Prototype modules have been constructed with 6-inch hexagonal silicon sensors with cell areas of 1.1~$cm^2$, and the SKIROC2-CMS readout ASIC. Beam tests of different sampling configurations were conducted with the prototype modules at DESY and CERN in 2017 and 2018. This paper describes the construction and commissioning of the CE calorimeter prototype, the silicon modules used in the construction, their basic performance, and the methods used for their calibration.