Joshua Stallbaumer | Searcharxiv

arXiv2026

Neural Network Based Molecular Structure Retrieval from Coulomb Explosion Imaging Data

Determining the structure and following the structural evolution of molecules undergoing chemical reactions is one of the key goals of ultrafast molecular physics and chemistry. Recently, Coulomb explosion imaging has emerged as a promising technique for imaging the evolving structure of individual molecules in the gas phase. However, its practical application for structure determination is hampered by the lack of suitable algorithms to directly retrieve the molecular structure from the measured fragment-ion momentum data. Here, we propose a scheme to solve the underlying inverse problem by employing neural networks to infer the initial atomic positions from the final ion momenta on an event-by-event basis. Using this scheme, we retrieve the structure of several polyhalomethane isomers from simulated Coulomb explosion imaging data with an average per-atom position error of approximately 0.1 atomic units, i.e., to within 5% of the typical bond lengths. This development paves the way for an automated structure retrieval from Coulomb explosion data one molecule at a time, making it ideally suitable for analyzing pump-probe experiments where several products are formed that need to be distinguished.

physics.chem-ph↗

arXiv2025

Exploiting correlations in multi-coincidence Coulomb explosion patterns for differentiating molecular structures using machine learning

Coulomb explosion imaging (CEI) is a powerful technique for capturing the real-time motion of individual atoms during ultrafast photochemical reactions. CEI generates high-dimensional data with naturally embedded correlations that allow mapping the coordinated motion of nuclei in molecules. This enables reliable separation of competing reaction pathways and makes this approach uniquely suited for characterizing weak reaction channels. However, rich information contained in experimental CEI patterns remains largely underexploited due to challenges in visualizing correlations between multiple observables in multi-dimensional parameter space. Here we present a new approach to CEI of intermediate-sized polyatomic molecules, detecting up to eight ionic fragments in coincidence and leveraging machine-learning-based analysis to identify patterns and correlations in the resulting high-dimensional momentum-space data, enabling robust molecular structure identification and differentiation. Our approach provides high-dimensional background-free data encoding exceptionally rich structural information and establishes an automated, scalable framework for extracting insightful information from the data. As a demonstration, we apply this method to image and distinguish dichloroethylene isomers, showcasing its potential for broader applications in molecular imaging. Our results pave the way for channel-specific analysis of ultrafast structural dynamics in chemically relevant systems, particularly for disentangling mixed reaction pathways and detecting contributions from weak channels and minority species.

physics.chem-ph↗