Machine Learning Accelerated Likelihood-Free Event Reconstruction in Dark Matter Direct Detection

Abstract

Reconstructing the position of an interaction for any dual-phase time projection chamber (TPC) with the best precision is key to directly detecting Dark Matter. Using the likelihood-free framework, a new algorithm to reconstruct the 2-D (x; y) position and the size of the charge signal (e) of an interaction is presented. The algorithm uses the charge signal (S2) light distribution obtained by simulating events using a waveform generator. To deal with the computational effort required by the likelihood-free approach, we employ the Bayesian Optimization for Likelihood-Free Inference (BOLFI) algorithm. Together with BOLFI, prior distributions for the parameters of interest (x; y; e) and highly informative discrepancy measures to perform the analyses are introduced. We evaluate the quality of the proposed algorithm by a comparison against the currently existing alternative methods using a large-scale simulation study. BOLFI provides a natural probabilistic uncertainty measure for the reconstruction and it improved the accuracy of the reconstruction over the next best algorithm by up to 15% when focusing on events over a large radii (R > 30 cm, the outer 37% of the detector). In addition, BOLFI provides the smallest uncertainties among all the tested methods.

References in corpus (31)

• A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning
• Dark Matter Search Results from a One Tonne$\times$Year Exposure of XENON1T
• Approximate Bayesian computation scheme for parameter inference and model selection in dynamical systems
• First Dark Matter Search Results from the XENON1T Experiment
• On the Complexity of Best Arm Identification in Multi-Armed Bandit Models
• Inferring population history with DIYABC: a user-friendly approach to Approximate Bayesian Computation
• Adaptive approximate Bayesian computation
• WIMP dark matter candidates and searches - current status and future prospects
• Dark matter direct-detection experiments
• A Comparative Review of Dimension Reduction Methods in Approximate Bayesian Computation
• The XENON100 Dark Matter Experiment
• The XENON1T Dark Matter Experiment
• Galactic Searches for Dark Matter
• Adaptive approximate Bayesian computation for complex models
• A low-mass dark matter search using ionization signals in XENON100
• Design and Performance of the XENON10 Dark Matter Experiment
• Approximate Bayesian Computation for Astronomical Model Analysis: A Case Study in Galaxy Demographics and Morphological Transformation at High Redshift
• Likelihood-Free Cosmological Inference with Type Ia Supernovae: Approximate Bayesian Computation for a Complete Treatment of Uncertainty
• GPS-ABC: Gaussian Process Surrogate Approximate Bayesian Computation
• Approximate Bayesian Computation for Forward Modeling in Cosmology
• cosmoabc: Likelihood-free inference via Population Monte Carlo Approximate Bayesian Computation
• astroABC: An Approximate Bayesian Computation Sequential Monte Carlo sampler for cosmological parameter estimation
• Accelerating ABC methods using Gaussian processes
• Position Reconstruction in a Dual Phase Xenon Scintillation Detector
• Approximate Bayesian Computation in Large Scale Structure: constraining the galaxy-halo connection
• Calibrated Ultra Fast Image Simulations for the Dark Energy Survey
• ELFI: Engine for Likelihood-Free Inference
• Position Reconstruction in LUX
• Summary Statistics in Approximate Bayesian Computation
• Statistical modelling of summary values leads to accurate Approximate Bayesian Computations
• A new approach for obtaining cosmological constraints from Type Ia Supernovae using Approximate Bayesian Computation

Cited by in corpus (6)

• Fast likelihood-free cosmology with neural density estimators and active learning
• Applications and Techniques for Fast Machine Learning in Science
• Convolutional Neural Networks for Direct Detection of Dark Matter
• Using Machine Learning to disentangle LHC signatures of Dark Matter candidates
• Distinguishing $W^{\prime }$ Signals at Hadron Colliders Using Neural Networks
• Domain-informed neural networks for interaction localization within astroparticle experiments