Physics-Guided Dual Implicit Neural Representations for Source Separation

TL;DR

This paper introduces a self-supervised dual neural network framework for source separation that effectively isolates signals from complex backgrounds in high-dimensional data without labeled training data.

Contribution

The paper presents a novel dual implicit neural representation approach that jointly models signal distortions and background contributions for source separation.

Findings

Successfully separates signals from complex backgrounds in neutron scattering data.

Operates effectively without labeled data or pre-defined dictionaries.

Applicable to diverse domains like astronomy and biomedical imaging.

Abstract

Significant challenges exist in efficient data analysis of most advanced experimental and observational techniques because the collected signals often include unwanted contributions--such as background and signal distortions--that can obscure the physically relevant information of interest. To address this, we have developed a self-supervised machine-learning approach for source separation using a dual implicit neural representation framework that jointly trains two neural networks: one for approximating distortions of the physical signal of interest and the other for learning the effective background contribution. Our method learns directly from the raw data by minimizing a reconstruction-based loss function without requiring labeled data or pre-defined dictionaries. We demonstrate the effectiveness of our framework by considering a challenging case study involving large-scale simulated as well as experimental momentum-energy-dependent inelastic neutron scattering data in a four-dimensional parameter space, characterized by heterogeneous background contributions and unknown distortions to the target signal. The method is found to successfully separate physically meaningful signals from a complex or structured background even when the signal characteristics vary across all four dimensions of the parameter space. An analytical approach that informs the choice of the regularization parameter is presented. Our method offers a versatile framework for addressing source separation problems across diverse domains, ranging from superimposed signals in astronomical measurements to structural features in biomedical image reconstructions.