Optimization of convolutional neural networks for background suppression in the PandaX-III experiment

The tracks recorded by a gaseous detector provide a possibility for charged particle identi fication. For searching the neutrinoless double beta decay events of 136Xe in the PandaX-III experiment, we optimized the convolutional neural network based on the Monte Carlo simulation data to improve the signal-background discrimination power. EfficientNet is chosen as the baseline model and the optimization is performed by tuning the hyperparameters. In particular, the maximum discrimination power is achieved by optimizing the channel number of the top convolutional layer. In comparison with our previous work, the significance of discrimination has been improved by ∼70%.

[1]  J. M. L'opez-Castano,et al.  Final Result of the Majorana Demonstrator's Search for Neutrinoless Double-β Decay in ^{76}Ge. , 2022, Physical review letters.

[2]  M. Decowski,et al.  Search for the Majorana Nature of Neutrinos in the Inverted Mass Ordering Region with KamLAND-Zen. , 2022, Physical review letters.

[3]  T. Papaevangelou,et al.  REST-for-Physics, a ROOT-based framework for event oriented data analysis and combined Monte Carlo response , 2021, Comput. Phys. Commun..

[4]  P. T. Surukuchi,et al.  Search for Majorana neutrinos exploiting millikelvin cryogenics with CUORE , 2021, Nature.

[5]  K. Ni,et al.  Signal identification with Kalman Filter towards background-free neutrinoless double beta decay searches in gaseous detectors , 2021, Journal of High Energy Physics.

[6]  K. Ni,et al.  Enhanced search sensitivity to the double beta decay of 136Xe to excited states with topological signatures , 2020, Science China Physics, Mechanics & Astronomy.

[7]  R. K. Neely,et al.  Convolutional neural network for multiple particle identification in the MicroBooNE liquid argon time projection chamber , 2020, Physical Review D.

[8]  M. Del Tutto,et al.  Demonstration of background rejection using deep convolutional neural networks in the NEXT experiment , 2020, Journal of High Energy Physics.

[9]  M. Misiaszek,et al.  Final Results of GERDA on the Search for Neutrinoless Double-β Decay. , 2020, Physical review letters.

[10]  T. Parente,et al.  Residual , 2020, Encyclopedic Dictionary of Archaeology.

[11]  S. Wang.  The TPC detector of PandaX-III Neutrinoless Double Beta Decay experiment , 2020, Journal of Instrumentation.

[12]  Sachin Dev,et al.  Geant4 - A Simulation Toolkit , 2019 .

[13]  P. Fierlinger,et al.  Search for Neutrinoless Double-β Decay with the Complete EXO-200 Dataset. , 2019, Physical review letters.

[14]  Quoc V. Le,et al.  EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks , 2019, ICML.

[15]  Naftali Tishby,et al.  Machine learning and the physical sciences , 2019, Reviews of Modern Physics.

[16]  Tao Zhang,et al.  Topological background discrimination in the PandaX-III neutrinoless double beta decay experiment , 2019, Journal of Physics G: Nuclear and Particle Physics.

[17]  P. Ferrario,et al.  High Pressure Gas Xenon TPCs for Double Beta Decay Searches , 2019, Front. Phys..

[18]  A. Goldschmidt,et al.  Electron drift and longitudinal diffusion in high pressure xenon-helium gas mixtures , 2019, Journal of Instrumentation.

[19]  Bo Chen,et al.  MnasNet: Platform-Aware Neural Architecture Search for Mobile , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  J. Liu,et al.  Design and commissioning of a 600 L Time Projection Chamber with Microbulk Micromegas , 2018, Journal of Instrumentation.

[21]  B. J. P. Jones,et al.  The NEXT White (NEW) detector , 2018, Journal of Instrumentation.

[22]  Hao Qiao,et al.  Signal-background discrimination with convolutional neural networks in the PandaX-III experiment using MC simulation , 2018, Science China Physics, Mechanics & Astronomy.

[23]  Mark Sandler,et al.  MobileNetV2: Inverted Residuals and Linear Bottlenecks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[24]  Gang Sun,et al.  Squeeze-and-Excitation Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[25]  Stephan Aune,et al.  PandaX-III: Searching for neutrinoless double beta decay with high pressure 136Xe gas time projection chambers , 2016, 1610.08883.

[26]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  M. Decowski,et al.  Search for Majorana Neutrinos Near the Inverted Mass Hierarchy Region with KamLAND-Zen. , 2016, Physical review letters.

[28]  P. Vahle,et al.  A convolutional neural network neutrino event classifier , 2016, ArXiv.

[29]  L. M. Moutinho,et al.  First proof of topological signature in the high pressure xenon gas TPC with electroluminescence amplification for the NEXT experiment , 2016, Journal of High Energy Physics.

[30]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[31]  L. M. Moutinho,et al.  First proof of topological signature in the high pressure xenon gas TPC with electroluminescence amplification for the NEXT experiment , 2015, 1507.05902.

[32]  Christian Szegedy,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[33]  Jainmin Li,et al.  The second-phase development of the China JinPing underground laboratory , 2014, 1404.2651.

[34]  M. Franz,et al.  Colloquium : Majorana fermions in nuclear, particle, and solid-state physics , 2014, 1403.4976.

[35]  M. Weber,et al.  Search for Majorana neutrinos with the first two years of EXO-200 data , 2014, Nature.

[36]  A. Giachero,et al.  Searching for Neutrinoless Double-Beta Decay of130Te with CUORE , 2014, 1402.6072.

[37]  J. C. Loach,et al.  The Majorana Demonstrator Neutrinoless Double-Beta Decay Experiment , 2012 .

[38]  Steven R. Elliott,et al.  Double Beta Decay , 2011, 1110.6159.

[39]  T. Geralis,et al.  Development and performance of Microbulk Micromegas detectors , 2010 .

[40]  Frank T. Avignone,et al.  Double Beta Decay, Majorana Neutrinos, and Neutrino Mass , 2007, 0708.1033.

[41]  A. Strumia.  Baryogenesis via leptogenesis , 2006, hep-ph/0608347.

[42]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.

[43]  Deborah Silver,et al.  Feature Visualization , 1994, Scientific Visualization.

[44]  Jing Cheng,et al.  Status and prospects of a deep underground laboratory in China , 2010 .

[45]  A. Wuosmaa,et al.  Search of Neutrinoless Double Beta Decay with the GERDA Experiment , 2010 .