Fast and Reliable Probabilistic Reflectometry Inversion with Prior-Amortized Neural Posterior Estimation

TL;DR

This paper introduces PANPE, a probabilistic deep learning method that rapidly and reliably reconstructs multilayer structures from reflectometry data, outperforming traditional algorithms in speed and reliability.

Contribution

The paper presents PANPE, a novel neural posterior estimation approach with adaptive priors for fast, comprehensive reflectometry structure inference, improving reliability and efficiency.

Findings

Supports high-throughput sample analysis

Enables real-time structural monitoring

Provides fast, reliable inverse problem solutions

Abstract

Reconstructing the structure of thin films and multilayers from measurements of scattered X-rays or neutrons is key to progress in physics, chemistry, and biology. However, finding all structures compatible with reflectometry data is computationally prohibitive for standard algorithms, which typically results in unreliable analysis with only a single potential solution identified. We address this lack of reliability with a probabilistic deep learning method that identifies all realistic structures in seconds, setting new standards in reflectometry. Our method, Prior-Amortized Neural Posterior Estimation (PANPE), combines simulation-based inference with novel adaptive priors that inform the inference network about known structural properties and controllable experimental conditions. PANPE networks support key scenarios such as high-throughput sample characterization, real-time monitoring of evolving structures, or the co-refinement of several experimental data sets, and can be adapted to provide fast, reliable, and flexible inference across many other inverse problems.