Neural network analysis of neutron and X-ray reflectivity data incorporating prior knowledge.

Due to the ambiguity related to the lack of phase information, determining the physical parameters of multilayer thin films from measured neutron and X-ray reflectivity curves is, on a fundamental level, an underdetermined inverse problem. This ambiguity poses limitations on standard neural networks, constraining the range and number of considered parameters in previous machine learning solutions. To overcome this challenge, a novel training procedure has been designed which incorporates dynamic prior boundaries for each physical parameter as additional inputs to the neural network. In this manner, the neural network can be trained simultaneously on all well-posed subintervals of a larger parameter space in which the inverse problem is underdetermined. During inference, users can flexibly input their own prior knowledge about the physical system to constrain the neural network prediction to distinct target subintervals in the parameter space. The effectiveness of the method is demonstrated in various scenarios, including multilayer structures with a box model parameterization and a physics-inspired special parameterization of the scattering length density profile for a multilayer structure. In contrast to previous methods, this approach scales favourably when increasing the complexity of the inverse problem, working properly even for a five-layer multilayer model and a periodic multilayer model with up to 17 open parameters.

Closing the loop: autonomous experiments enabled by machine-learning-based online data analysis in synchrotron beamline environments.

Recently, there has been significant interest in applying machine-learning (ML) techniques to the automated analysis of X-ray scattering experiments, due to the increasing speed and size at which datasets are generated. ML-based analysis presents an important opportunity to establish a closed-loop feedback system, enabling monitoring and real-time decision-making based on online data analysis. In this study, the incorporation of a combined one-dimensional convolutional neural network (CNN) and multilayer perceptron that is trained to extract physical thin-film parameters (thickness, density, roughness) and capable of taking into account prior knowledge is described. ML-based online analysis results are processed in a closed-loop workflow for X-ray reflectometry (XRR), using the growth of organic thin films as an example. Our focus lies on the beamline integration of ML-based online data analysis and closed-loop feedback. Our data demonstrate the accuracy and robustness of ML methods for analyzing XRR curves and Bragg reflections and its autonomous control over a vacuum deposition setup.

Machine learning for scattering data: strategies, perspectives and applications to surface scattering.

Machine learning (ML) has received enormous attention in science and beyond. Discussed here are the status, opportunities, challenges and limitations of ML as applied to X-ray and neutron scattering techniques, with an emphasis on surface scattering. Typical strategies are outlined, as well as possible pitfalls. Applications to reflectometry and grazing-incidence scattering are critically discussed. Comment is also given on the availability of training and test data for ML applications, such as neural networks, and a large reflectivity data set is provided as reference data for the community.

Advice on describing Bayesian analysis of neutron and X-ray reflectometry.

As a result of the availability of modern software and hardware, Bayesian analysis is becoming more popular in neutron and X-ray reflectometry analysis. The understandability and replicability of these analyses may be harmed by inconsistencies in how the probability distributions central to Bayesian methods are represented in the literature. Herein advice is provided on how to report the results of Bayesian analysis as applied to neutron and X-ray reflectometry. This includes the clear reporting of initial starting conditions, the prior probabilities, the results of any analysis and the posterior probabilities that are the Bayesian equivalent of the error bar, to enable replicability and improve understanding. It is believed that this advice, grounded in the authors' experience working in the field, will enable greater analytical reproducibility in the work of the reflectometry community, and improve the quality and usability of results.

Automated matching of two-time X-ray photon correlation maps from phase-separating proteins with Cahn-Hilliard-type simulations using auto-encoder networks.

Machine learning methods are used for an automated classification of experimental two-time X-ray photon correlation maps from an arrested liquid-liquid phase separation of a protein solution. The correlation maps are matched with correlation maps generated with Cahn-Hilliard-type simulations of liquid-liquid phase separations according to two simulation parameters and in the last step interpreted in the framework of the simulation. The matching routine employs an auto-encoder network and a differential evolution based algorithm. The method presented here is a first step towards handling large amounts of dynamic data measured at high-brilliance synchrotron and X-ray free-electron laser sources, facilitating fast comparison with phase field models of phase separation.

Reverse-engineering method for XPCS studies of non-equilibrium dynamics.

X-ray photon correlation spectroscopy (XPCS) is a powerful tool in the investigation of dynamics covering a broad time and length scale. It has been widely used to probe dynamics for systems in both equilibrium and non-equilibrium states; in particular, for systems undergoing a phase transition where the structural growth kinetics and the microscopic dynamics are strongly intertwined. The resulting time-dependent dynamic behavior can be described using the two-time correlation function (TTC), which, however, often contains more interesting features than the component along the diagonal, and cannot be easily interpreted via the classical simulation methods. Here, a reverse engineering (RE) approach is proposed based on particle-based heuristic simulations. This approach is applied to an XPCS measurement on a protein solution undergoing a liquid-liquid phase separation. It is demonstrated that the rich features of experimental TTCs can be well connected with the key control parameters including size distribution, concentration, viscosity and mobility of domains. The dynamic information obtained from this RE analysis goes beyond the existing theory. The RE approach established in this work is applicable for other processes such as film growth, coarsening or evolving systems.

Neural network analysis of neutron and X-ray reflectivity data: automated analysis using mlreflect, experimental errors and feature engineering.

The Python package mlreflect is demonstrated, which implements an optimized pipeline for the automated analysis of reflectometry data using machine learning. The package combines several training and data treatment techniques discussed in previous publications. The predictions made by the neural network are accurate and robust enough to serve as good starting parameters for an optional subsequent least-mean-squares (LMS) fit of the data. For a large data set of 242 reflectivity curves of various thin films on silicon substrates, the pipeline reliably finds an LMS minimum very close to a fit produced by a human researcher with the application of physical knowledge and carefully chosen boundary conditions. The differences between simulated and experimental data and their implications for the training and performance of neural networks are discussed. The experimental test set is used to determine the optimal noise level during training. The extremely fast prediction times of the neural network are leveraged to compensate for systematic errors by sampling slight variations in the data.

Fast fitting of reflectivity data of growing thin films using neural networks.

X-ray reflectivity (XRR) is a powerful and popular scattering technique that can give valuable insight into the growth behavior of thin films. This study shows how a simple artificial neural network model can be used to determine the thickness, roughness and density of thin films of different organic semiconductors [diindenoperylene, copper(II) phthalocyanine and α-sexithiophene] on silica from their XRR data with millisecond computation time and with minimal user input or a priori knowledge. For a large experimental data set of 372 XRR curves, it is shown that a simple fully connected model can provide good results with a mean absolute percentage error of 8-18% when compared with the results obtained by a genetic least mean squares fit using the classical Parratt formalism. Furthermore, current drawbacks and prospects for improvement are discussed.