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

Benchmarking deep learning for automated peak detection on GIWAXS data

Recent advancements in X-ray sources and detectors have dramatically increased data generation, leading to a greater demand for automated data processing. This is particularly relevant for real-time grazing-incidence wide-angle X-ray scattering (GIWAXS) experiments which can produce hundreds of thousands of diffraction images in a single day at a synchrotron beamline. Deep learning (DL)-based peak-detection techniques are becoming prominent in this field, but rigorous benchmarking is essential to evaluate their reliability, identify potential problems, explore avenues for improvement and build confidence among researchers for seamless integration into their workflows. However, the systematic evaluation of these techniques has been hampered by the lack of annotated GIWAXS datasets, standardized metrics and baseline models. To address these challenges, we introduce a comprehensive framework comprising an annotated experimental dataset, physics-informed metrics adapted to the GIWAXS geometry and a competitive baseline - a classical, non-DL peak-detection algorithm optimized on our dataset. Furthermore, we apply our framework to benchmark a recent DL solution trained on simulated data and discover its superior performance compared with our baseline. This analysis not only highlights the effectiveness of DL methods for identifying diffraction peaks but also provides insights for further development of these solutions.

Fast and reliable probabilistic reflectometry inversion with prior-amortized neural posterior estimation

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, redefining standards in reflectometry. Our method, prior-amortized neural posterior estimation (PANPE), combines simulation-based inference with 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 corefinement of several experimental datasets and can be adapted to provide fast, reliable, and flexible inference across many other inverse problems.

Nanostructured Photonics Probes: A Transformative Approach in Neurotherapeutics and Brain Circuitry

Neuroprobes that use nanostructured photonic interfaces are capable of multimodal sensing, stimulation, and imaging with unprecedented spatio-temporal resolution. In addition to electrical recording, optogenetic modulation, high-resolution optical imaging, and molecular sensing, these advanced probes combine nanophotonic waveguides, optical transducers, nanostructured electrodes, and biochemical sensors. The potential of this technology lies in unraveling the mysteries of neural coding principles, mapping functional connectivity in complex brain circuits, and developing new therapeutic interventions for neurological disorders. Nevertheless, achieving the full potential of nanostructured photonic neural probes requires overcoming challenges such as ensuring long-term biocompatibility, integrating nanoscale components at high density, and developing robust data-analysis pipelines. In this review, we summarize and discuss the role of photonics in neural probes, trends in electrode diameter for neural interface technologies, nanophotonic technologies using nanostructured materials, advances in nanofabrication photonics interface engineering, and challenges and opportunities. Finally, interdisciplinary efforts are required to unlock the transformative potential of next-generation neuroscience therapies.

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.

Millisecond X-ray reflectometry and neural network analysis: unveiling fast processes in spin coating

X-ray reflectometry (XRR) is a powerful tool for probing the structural characteristics of nanoscale films and layered structures, which is an important field of nanotechnology and is often used in semiconductor and optics manufacturing. This study introduces a novel approach for conducting quantitative high-resolution millisecond monochromatic XRR measurements. This is an order of magnitude faster than in previously published work. Quick XRR (qXRR) enables real time and in situ monitoring of nanoscale processes such as thin film formation during spin coating. A record qXRR acquisition time of 1.4 ms is demonstrated for a static gold thin film on a silicon sample. As a second example of this novel approach, dynamic in situ measurements are performed during PMMA spin coating onto silicon wafers and fast fitting of XRR curves using machine learning is demonstrated. This investigation primarily focuses on the evolution of film structure and surface morphology, resolving for the first time with qXRR the initial film thinning via mass transport and also shedding light on later thinning via solvent evaporation. This innovative millisecond qXRR technique is of significance for in situ studies of thin film deposition. It addresses the challenge of following intrinsically fast processes, such as thin film growth of high deposition rate or spin coating. Beyond thin film growth processes, millisecond XRR has implications for resolving fast structural changes such as photostriction or diffusion processes.

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.

Compact sample environment for in situ X-ray scattering during spin-coating

We demonstrate a compact sample environment for the in situ study of crystallization kinetics of thin films on synchrotron beamlines, featuring atmospheric control, automated deposition, spin-coating, and annealing stages. The setup is suitable for studying thin film growth in real time using grazing-incidence X-ray diffraction techniques. Humidity and oxygen levels are being detected by sensors. The spinning stage exhibits low vertical oscillation amplitude (∼3μm at speeds up to 10 000 rpm) and can optionally be employed for antisolvent application or gas quenching to investigate the impact of these techniques, which are often used to assist thin film growth. Differential reflectance spectroscopy is implemented in the spin-coater environment for inspecting thin film thickness and optical properties. The infrared radiation-based annealing system consists of a halogen lamp and a holder with an adjustable lamp-to-sample distance, while the sample surface temperature is monitored by a pyrometer. All features of the sample environment can be controlled remotely by the control software at synchrotron beamlines. In order to test and demonstrate the performance, the crystallization pathway of the antisolvent-assisted MAPbI3 (MA = methylammonium) perovskite thin film during the spinning and annealing stages is monitored and discussed.

Extraction of interaction parameters from specular neutron reflectivity in thin films of diblock copolymers: an "inverse problem"

Diblock copolymers have been shown to undergo microphase separation due to an interplay of repulsive interactions between dissimilar monomers, which leads to the stretching of chains and entropic loss due to the stretching. In thin films, additional effects due to confinement and monomer-surface interactions make microphase separation much more complicated than in that in bulks (i.e., without substrates). Previously, physics-based models have been used to interpret and extract various interaction parameters from the specular neutron reflectivities of annealed thin films containing diblock copolymers (J. P. Mahalik, J. W. Dugger, S. W. Sides, B. G. Sumpter, V. Lauter and R. Kumar, Interpreting neutron reflectivity profiles of diblock copolymer nanocomposite thin films using hybrid particle-field simulations, Macromolecules, 2018, 51(8), 3116; J. P. Mahalik, W. Li, A. T. Savici, S. Hahn, H. Lauter, H. Ambaye, B. G. Sumpter, V. Lauter and R. Kumar, Dispersity-driven stabilization of coexisting morphologies in asymmetric diblock copolymer thin films, Macromolecules, 2021, 54(1), 450). However, extracting Flory-Huggins χ parameters characterizing monomer-monomer, monomer-substrate, and monomer-air interactions has been labor-intensive and prone to errors, requiring the use of alternative methods for practical purposes. In this work, we have developed such an alternative method by employing a multi-layer perceptron, an autoencoder, and a variational autoencoder. These neural networks are used to extract interaction parameters not only from neutron scattering length density profiles constructed using self-consistent field theory-based simulations, but also from a noisy ad hoc model constructed previously. In particular, the variational autoencoder is shown to be the most promising tool when it comes to the reconstruction and extraction of parameters from an ad hoc neutron scattering length density profile of a thin film containing a symmetric di-block copolymer (poly(deuterated styrene-b-n-butyl methacrylate)). This work paves the way for automated analysis of specular neutron reflectivities from thin films of copolymers using machine learning tools.

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.