Improving the Deconvolution of Spectrum at Finite Temperature via Neural Network

TL;DR

This paper introduces a neural network-based method for deconvolving spectral data at finite temperatures, improving accuracy and stability over traditional regularization techniques in condensed matter physics.

Contribution

It proposes a novel neural network discretization scheme combined with stochastic optimization to enhance spectral deconvolution at finite temperatures.

Findings

More accurate gap estimation in superconductors

Reduced oscillations in deconvoluted spectra

Clearer material analysis results from experimental data

Abstract

In the study of condensed matter physics, spectral information plays an important role for understand the mechanism of materials. However, it is difficult to obtain the spectrum directly through experiments or simulation. For example, the spectral information deconvoluted by scanning tunneling spectroscopy suffers from the temperature broadening effect, which is ill-posed and makes the deconvolution result unstable. To solve this problem, the core idea of existing methods, such as the maximum entropy method, tends to select appropriate regularization to suppress unstable oscillations. However, the choice of regularization is difficult, and the oscillation has not been completely eliminated. We think non-uniform sampling is the core improvement direction, combined with stochastic optimization and deep learning, we introduce a neural network based discretization scheme to solve the deconvolution problem. Due to the neural network can represent any piece-wise linear function, our method replace the target spectrum by network and can find a better approximation solution through optimization accurate and efficient. Experiments on theoretical datasets about superconductors demonstrate that the gap is estimated to be more accurate and oscillating less, plugin real experimental data, our approach can get clearer results for material analysis.