Super Resolution Convolutional Neural Network for Feature Extraction in Spectroscopic Data

ORAL

Abstract

Two dimensional (2D) peak finding is a common practice in data analysis for physics experiments, which is typically achieved by computing the local derivatives. However, this method is inherently unstable when the local landscape is complicated, or the signal-to-noise ratio of the data is low. In this work, we propose a new method in which the peak tracking task is formalized as an inverse problem, thus can be solved with a convolutional neural network (CNN). In addition, we show that the underlying physics principle of the experiments can be used to generate the training data. By generalizing the trained neural network on real experimental data, we show that the CNN method can achieve comparable or better results than traditional derivative based methods. This approach can be further generalized in different physics experiments when the physical process is known.

–

Presenters

  • Han Peng

    University of Oxford, Department of Engineering, University of Oxford

Authors

  • Han Peng

    University of Oxford, Department of Engineering, University of Oxford

  • Xiang Gao

    Department of Chemistry, University of Florida

  • Yu He

    Stanford University, SLAC National Accelerator Laboratory, Applied physics, Stanford University, Department of Applied Physics, Stanford University

  • Yiwei Li

    University of Oxford, Department of Physics, University of Oxford, United Kingdom, Department of Physics, University of Oxford

  • Yuchen Ji

    School of Physical Science and Technology, ShanghaiTech University

  • Chuhang Liu

    School of Physical Science and Technology, ShanghaiTech University

  • Sandy Adhitia Ekahana

    University of Oxford, Department of Physics, University of Oxford

  • Ding Pei

    Department of Physics, University of Oxford

  • zhongkai liu

    shanghaiTech University, School of Physical Science and Technology, ShanghaiTech University, People's Republic of China, School of Physical Science and Technology, ShanghaiTech University

  • Zhixun Shen

    Stanford University, SLAC National Accelerator Laboratory, SIMES, SLAC National Accelerator Lab, GLAM, Stanford University, Applied physics, Stanford University, Department of Applied Physics, Stanford University

  • Yulin Chen

    University of Oxford, Department of Physics, University of Oxford, United Kingdom, Department of Physics, University of Oxford