Search NASA⌕ Search
Home/Archive/DOE OSTI

DOE OSTI · 3030002

Data driven drift correction for complex optical systems

Mishra, Aashwin [SLAC National Accelerator Laboratory (SLAC), Menlo Park, CA (United States)]·Seaberg, Matthew [SLAC National Accelerator Laboratory (SLAC), Menlo Park, CA (United States)] (ORCID:0000000245604698)·Roussel, Ryan [SLAC National Accelerator Laboratory (SLAC), Menlo Park, CA (United States)]·Song, Sanghoon [SLAC National Accelerator Laboratory (SLAC), Menlo Park, CA (United States)] (ORCID:0000000334931850)·Edelen, Auralee [SLAC National Accelerator Laboratory (SLAC), Menlo Park, CA (United States)]·Ratner, Daniel [SLAC National Accelerator Laboratory (SLAC), Menlo Park, CA (United States)]·Mehta, Apurva [SLAC National Accelerator Laboratory (SLAC), Menlo Park, CA (United States)] (ORCID:0000000308706932)
View original source ↗Read source document ↗Export metadata ↓

Abstract

To exploit the thousand-fold increase in spectral brightness of modern light sources, increasingly intricate experiments are being conducted that demand extremely precise beam trajectory. Maintaining the optimal trajectory over several hours of an experiment with the needed precision necessitates active drift control. Here, we outline time varying Bayesian optimization (TVBO) as a data driven approach for robust drift correction, and illustrate its application for a split and delay optical system composed of six crystals and twelve input dimensions. Using numerical simulations, we exhibit the application of TVBO for linear drift, non-smooth temporal drift as well as constrained TVBO for multi-objective control settings, representing real-life operating conditions. This approach can be easily adapted to other X-ray beam conditioning and guidance systems, including multi-crystal monochromators and grazing-incidence mirrors, to maintain sub-micrometer and nanoradian beam stability over the course of an experiment spanning several hours.

Explore related subjects

Bayesian optimizationFOS: Physical sciencesHigh Energy Physics - Experiment (hep-ex)Optics (physics.optics)X-ray free electron laserX-ray opticsdrift correctionmachine learningsplit and delay

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Mishra, Aashwin [SLAC National Accelerator Laboratory (SLAC), Menlo Park, CA (United States)], Seaberg, Matthew [SLAC National Accelerator Laboratory (SLAC), Menlo Park, CA (United States)] (ORCID:0000000245604698), Roussel, Ryan [SLAC National Accelerator Laboratory (SLAC), Menlo Park, CA (United States)], Song, Sanghoon [SLAC National Accelerator Laboratory (SLAC), Menlo Park, CA (United States)] (ORCID:0000000334931850), Edelen, Auralee [SLAC National Accelerator Laboratory (SLAC), Menlo Park, CA (United States)], Ratner, Daniel [SLAC National Accelerator Laboratory (SLAC), Menlo Park, CA (United States)], Mehta, Apurva [SLAC National Accelerator Laboratory (SLAC), Menlo Park, CA (United States)] (ORCID:0000000308706932). 2026-04-10. Data driven drift correction for complex optical systems. https://doi.org/10.1107/s1600577526003395

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related reports

NASA NTRS2026

Benchmarking Bayesian Optimization Frameworks and Acquisition Strategies for Materials Discovery and Autonomous Laboratories

Bayesian optimization (BO) can accelerate materials discovery by guiding expensive experiments toward the most promising processing conditions. We systematically compare five BO surrogate and framework combinations (Gaussian processes in Ax, Gaussian processes and Monte-Carlo neural networks in BayBE, random forests in Lolopy, and tree-structured Parzen (TPE) estimators in Hyperopt) on three benchmarks that mimic common materials design tasks (a discrete solid-electrolyte composition space, a hybrid discrete/continuous laminate-composite design problem solved with micromechanics modeling, and the continuous Ishigami analytic function which is a standard optimization benchmark). Each BO surrogate is paired with posterior mean, probability of improvement, and expected improvement acquisition functions and run for 100 trials from randomized initial samples with uniform random search providing a control. Across five random seeds per setting, BayBE’s Gaussian-process surrogate with expected improvement consistently reached ≥95 % of the known optimum in the fewest evaluations, while Lolopy’s random forest matched or exceeded GP performance on purely categorical or mixed spaces at a higher computational cost. Posterior mean alone often stagnated at local optima, underscoring the need for exploration, whereas probability and expected improvement balanced exploration and exploitation leading to better optimization in fewer trials. Execution times ranged from milliseconds for TPE to minutes for neural-network and random-forest surrogates. These results establish baseline expectations for BO in automated materials laboratories and highlight expected improvement with Gaussian processes as a reliable first choice, with random forests offering a strong alternative when categorical variables dominate. The benchmark suite and code are released to facilitate future surrogate, acquisition, and constraint-handling research in data-driven materials optimization.

Bayesian optimization↗
DOE OSTI2026

Uncertainty-Aware Machine Learning for Small-Angle X-ray Scattering Analysis in Autonomous Experimentation

Small-angle X-ray scattering (SAXS) is a powerful high-throughput characterization tool for probing nanoscale structure in native sample environments, providing real-time morphological information such as nanoparticle size and shape during synthesis. However, automated SAXS data analysis for extracting meaningful structural parameters is non-trivial and remains a bottleneck in closed-loop experimentation towards autonomous materials discovery, which demands fast, reliable, and uncertainty-aware data analysis. Here, we develop a machine-learning approach for automated SAXS analysis tailored to closed-loop nanoparticle synthesis. A Random Forest (RF) regression model is trained on 100,000 synthetic SAXS curves generated from polydisperse spherical nanoparticles with realistic background contributions. Using normalized one-dimensional SAXS intensity profiles as input, the RF model directly predicts nanoparticle radius, size polydispersity, and background parameters, while the ensemble standard deviation across trees provides built-in uncertainty quantification (UQ). On synthetic data, we show that combining fit-quality metrics (R 2 , MAE) with thresholds on prediction uncertainty reliably identifies accurate parameter estimates without access to ground truth. We then apply the trained model to 365 experimental SAXS profiles of citrate-reduced gold nanoparticles synthesized using an automated droplet-flow microreactor with in situ SAXS at a synchrotron beamline, classifying the results into high- and low-confidence subsets based on UQ metrics. Finally, we integrate RF-based SAXS analysis into a simulated closed-loop optimization campaign using Gaussian process Bayesian optimization to minimize nanoparticle polydispersity, benchmarking against conventional automated Levenberg–Marquardt fitting. The RF-guided campaign exhibits substantially faster convergence and lower relative opportunity cost (∼0.07 vs ∼0.3), demonstrating that uncertainty-aware machine-learning SAXS analysis significantly enhances the efficiency and robustness of autonomous nanomaterials synthesis workflows.

Bayesian optimization↗
DOE OSTI2026

Bayesian Optimization of Non-Invariant Systems with Constraints Developed for Application to the ECR Ion Source VENUS

In this work, we consider the optimization of non-invariant systems with both safety and control constraints. We present a new approach based on Bayesian optimization for the dynamic, safe and controlled optimization of such systems. Although there are other possible use cases, we focus on the application to the electron cyclotron resonance ion source VENUS. From experimental data, we have observed that VENUS behaves to first order as a non-invariant dynamic system with moving areas of instability. Our novel approach aims at providing a tool that can maintain system optimization in a safe way. This is accomplished by making sure the objective function, the beam current in the case of VENUS, does not fall under an operational minimum, while simultaneously requiring the optimization to avoid areas where VENUS is unstable. We compare the result of our approach on synthetic data modeled to mimic the behavior of VENUS with two methods from the literature, a standard Bayesian optimizer and a safe Bayesian optimizer, both adapted to deal with dynamic systems. A cross Student T-test is conducted to show the significance of the improvement given by the new method we introduce here, regarding the two preexisting methods we compared to. The results of the tests conducted on synthetic data show that the proposed method succeeds at maintaining the system optimized and obeys the predefined constraints better than the literature methods explored.

Bayesian optimization↗