Iterative peak-fitting of frequency-domain data via deep convolution neural networks

Abstract

High-throughput material screening for the discovery and design of novel functional materials requires automatized analyses of theoretical and experimental data. Here we study the subject of human-free analyses of one-dimensional spectroscopic data, {\it e.g.} in the frequency domain, via employing deep convolution neural network. Specifically, we trained various deep convolution neural network and benchmarked their performance in decomposing one-dimensional noisy data into multiple nonorthogonal peaks in an iterative manner, after which a conventional basin-hopping algorithm was applied to further reduce residual fitting error. Among six different network architectures, a variant of "Squeeze-and-excitation" network (SENet) structure that we first propose in this study shows the best performance. Dependency of training performance with respect to the choice of the loss function is also discussed. We conclude by applying our modified SENet model to experimental photoemission spectra of graphene, MoS${}_2$, and WS${}_2$ and address its potential applications and limitations.

arXiv comment17 pages, 8 figures

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Global Optimization by Basin-Hopping and the Lowest Energy Structures of Lennard-Jones Clusters Containing up to 110 Atoms
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• Empirical Evaluation of Rectified Activations in Convolutional Network
• Theory-guided Data Science: A New Paradigm for Scientific Discovery from Data
• Perspective on density functional theory
• Data-driven materials science: status, challenges and perspectives
• Machine Learning in Electronic Quantum Matter Imaging Experiments