Signal recognition efficiencies of artificial neural-network pulse-shape discrimination in HPGe $$\varvec{0\nu \beta \beta }$$ 0 ν β β -decay searches

Caldwell, A.; Cossavella, F.; Majorovits, B.; Palioselitis, D.; Volynets, O.

doi:10.1140/epjc/s10052-015-3573-8

Cited by 7 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The GERDA experiment pioneered using ANNs to identify single-site events in semicoaxial high-purity germanium detectors (Agostini et al, 2013(Agostini et al, , 2019. The use of ANNs to differentiate single-site and multisite events in HPGe detectors was also developed by Caldwell et al (2015), Holl et al (2019), andJany et al (2021).…”

Section: Event and Signal Classificationmentioning

confidence: 99%

Colloquium: Machine learning in nuclear physics

et al. 2022

View full text Add to dashboard Cite

TABLE I. Table of ML methods discussed in this Colloquium with an indication of the main type of learning (S, supervised; U, unsupervised; semi-S, semisupervised). Acronym Method Description Learning type AE, VAE Autoencoders, Variational autoencoders ANN capable of learning efficient representations of the input data without any supervision U ANN Artificial neural network Models for learning defined by connected units (or nodes) and hidden layers with well-defined inputs and outputs S BED Bayesian experimental design Bayesian inference for experimental design S BM Boltzmann machine Generative ANN that can learn a probability distribution from sets of changing inputs U BMA, BMM Bayesian model averaging, Bayesian model mixing Bayesian inference applied to model selection or the combined estimation, or performed over a mixture model S BNN Bayesian neural network ANN where the parameters of the network are represented by probabilities learned by Bayesian inference S BO Bayesian optimization Optimization of functions without an a priori knowledge of functional forms. S and semi-S CNN Convolutional neural network ANN where convolution is used to reduce dimensionalities S EMB Ensemble methods and boosting Methods based on collections of decision trees as simple learners S GAN Generative adversarial network System of two ANNs where a generative network generates outputs while a discriminative network evaluates them U GP Gaussian process Collection of random variables that have a joint Gaussian distribution used in Bayesian inference Semi-S KNN k-nearest neighbors Nonparametric method where inputs consist of the k closest training examples in a dataset S KR Kernel regression Extension of linear regression methods to include nonlinear function kernels S LR Logistic regression Convex optimization method based on maximum likelihood estimate for classification problems S LSTM Long short-term memory RNN capable of learning long-term dependencies S PCA Principal component analysis Dimensionality reduction technique based on retaining the largest eigenvalues of the covariance matrix U REG Linear regression Linear algebra methods used for modeling continuous functions in terms of their explanatory variables S RL Reinforcement learning Learning achieved by trial and error of desired and undesired events Neither S nor U RNN Recurrent neural network ANN where connections between nodes allow for temporal dynamic behavior S SVM Support vector machine Convex optimization techniques with efficient ways to distinguish features in datasets S

show abstract

Section: Event and Signal Classificationmentioning

confidence: 99%

Colloquium: Machine learning in nuclear physics

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In an alternative approach, artificial neural networks have been implemented to reject multi-site events recorded in coaxial [12,14] and BEGe [15] detectors. Based on the success of G [16] and M [17] in achieving good sensitivity to 0𝜈𝛽𝛽 decay, the next generation experiment LEGEND [18] will, in its first phase, operate about 200 kg of HPGe detectors under low-background conditions.…”

Section: Jinst 16 P08007mentioning

confidence: 99%

Simulation of semiconductor detectors in 3D with SolidStateDetectors.jl

Abt¹,

Fischer²,

Hagemann³

et al. 2021

J. Inst.

View full text Add to dashboard Cite

The open-source software package SolidStateDetectors.jl to calculate the fields and simulate the drifts of charge carriers in solid state detectors, especially in large volume high-purity germanium detectors, together with the corresponding pulses, is introduced. The package can perform all calculations in full 3D while it can also make use of detector symmetries. The effect of the surroundings of a detector can also be studied. The package is programmed in the user friendly and performance oriented language julia, such that 3D field calculations and drift simulations can be executed efficiently and in parallel. The package was developed for high-purity germanium detectors, but it can be adjusted by the user to other types of semiconductors. The verification of the package is shown for an n-type segmented point-contact germanium detector. Additional features of SolidStateDetectors.jl, which are under development are listed.

show abstract

“…The simulations performed for the prototype detector were based on the ADL package [39], similarly as earlier attempts described in the literature [39][40][41]. Our advantage was that we knew all the parameters of the detector/crystal, including also the response of the preamplifier and the noise of the spectroscopic chain.…”

Section: Pulse Shape Simulationmentioning

confidence: 99%

Fabrication, characterization and analysis of a prototype high purity germanium detector for $$^{76}$$Ge-based neutrinoless double beta decay experiments

et al. 2021

View full text Add to dashboard Cite

Experiments searching for the neutrinoless double beta decay in $$^{76}$$ 76 Ge are currently achieving the lowest background level and, in connection with the excellent energy resolution of germanium detectors, they exhibit the best discovery potential for the decay. Expansion to a ton scale of the active target mass is presently considered – in this case on-site production of the detectors may be an option. In this paper we describe the fabrication and characterization procedures of a prototype detector with a small p+ contact, which enhances the abilities of the pulse shape discrimination – one of the most important tools for background reduction. Simulations of the shapes of pulses from the detector were carried out and tuned, taking the advantage of the fact that all the parameters of the Ge crystal, cryostat and of the spectroscopic chain were known. As a result, the pulse shape analyses performed on the simulated and measured data agree very well. The worked out method allows to optimize geometry and crystal parameters in terms of pulse shape analysis efficiency, before the actual production of the detectors.

show abstract

Signal recognition efficiencies of artificial neural-network pulse-shape discrimination in HPGe $$\varvec{0\nu \beta \beta }$$ 0 ν β β -decay searches

Cited by 7 publications

References 13 publications

Colloquium: Machine learning in nuclear physics

Colloquium: Machine learning in nuclear physics

Simulation of semiconductor detectors in 3D with SolidStateDetectors.jl

Fabrication, characterization and analysis of a prototype high purity germanium detector for $$^{76}$$Ge-based neutrinoless double beta decay experiments

Contact Info

Product

Resources

About