Search NASA⌕ Search

SEARCH · Search NASA

Results for “Reliability Prediction”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 451 records · Page 25
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Benchmarking DFT Accuracy in Predicting O 1s Binding Energies on Metals

X-ray photoelectron spectroscopy (XPS) is a powerful tool for probing the electronic structure and composition of materials, particularly metals and metal oxides of relevance to solar cells and catalysis. Density functional theory (DFT) is often used to support XPS peak assignments, but its reliability for predicting oxygen species is not well established. Here, we compile a large data set of experimental oxygen binding energies and evaluate corresponding DFT predictions. We find that as the binding energies of metal-bound atomic oxygen species increase, especially above ≈530 eV, there is a general decrease in the accuracy of DFTpredicted values. Thus, high-binding-energy atomic oxygen species, such as those proposed as active for selective Ag-catalyzed epoxidation, are less well represented. The chemical nature of the oxygen species also influences accuracy, with molecularly bound species more reliably captured across the entire range of energies. These findings illustrate the limitations of DFT for interpreting XPS spectra and provide a benchmark for improving computational methods.

Adsorption↗
DOE OSTI2025

Harnessing on-machine metrology data for prints with a surrogate model for laser powder directed energy deposition

In this study, we leverage the massive amount of multi-modal on-machine metrology data generated from Laser Powder Directed Energy Deposition (LP-DED) to construct a comprehensive surrogate model of the 3D printing process. By employing Dynamic Mode Decomposition with Control (DMDc), a data-driven technique, we capture the complex physics inherent in this extensive dataset. This physics-based surrogate model emphasizes thermodynamically significant quantities, enabling us to accurately predict key process outcomes. The model ingests 21 process parameters, including laser power, scan rate, and position, while providing outputs such as melt pool temperature, melt pool size, and other essential observables. Furthermore, it incorporates uncertainty quantification to provide bounds on these predictions, enhancing reliability and confidence in the results. We then deploy the surrogate model on a new, unseen part and monitor the printing process as validation of the method. Our experimental results demonstrate that the predictions align with actual measurements with high accuracy, confirming the effectiveness of our approach. Furthermore, this methodology not only facilitates real-time predictions but also operates at process-relevant speeds, establishing a basis for implementing feedback control in LP-DED.

Digital twins↗
DOE OSTI2021

Deciphering Degradation: Machine Learning on Real-World Performance Data (Final Report)

This project addresses a fundamental flaw in solar PV research and solar project financing; the assumed rate of degradation for solar plants. The solar industry currently relies on an out-dated report that observed a 0.5% degradation rate based on a small sample size of systems (~100). While the research conducted at the time was new and innovative, the solar community has not updated this research and universally applies this 0.5% degradation assumption in financial models. Our project updates this assumption by analyzing observed degradation from the industry’s largest dataset of operating solar assets (>10,000 systems) and creating the first machine-learning model based on these observed results to quantify and identify features that drive degradation. There are two strategic goals for this award: reduce the cost of capital (enable solar to attract more capital) and improve the reliability of solar itself. These dual goals are achieved by leveraging an industry dataset to observe system degradation on a large scale, deploying advanced data analysis and machine learning methods to quantify and predict system reliability, and engaging with industry stakeholders to help them accurately price degradation in financial models.

14 SOLAR ENERGY↗
DOE OSTI2015

How to constrain your M dwarf: Measuring effective temperature, bolometric luminosity, mass, and radius

Precise and accurate parameters for late-type (late K and M) dwarf stars are important for characterization of any orbiting planets, but such determinations have been hampered by these stars’ complex spectra and dissimilarity to the Sun. We exploit an empirically calibrated method to estimate spectroscopic effective temperature (T{sub eff}) and the Stefan–Boltzmann law to determine radii of 183 nearby K7–M7 single stars with a precision of 2%–5%. Our improved stellar parameters enable us to develop model-independent relations between T{sub eff} or absolute magnitude and radius, as well as between color and T{sub eff}. The derived T{sub eff}–radius relation depends strongly on [Fe/H], as predicted by theory. The relation between absolute K{sub S} magnitude and radius can predict radii accurate to ≃3%. We derive bolometric corrections to the VR{sub C}I{sub C}grizJHK{sub S} and Gaia passbands as a function of color, accurate to 1%–3%. We confront the reliability of predictions from Dartmouth stellar evolution models using a Markov chain Monte Carlo to find the values of unobservable model parameters (mass, age) that best reproduce the observed effective temperature and bolometric flux while satisfying constraints on distance and metallicity as Bayesian priors. With the inferred masses we derive a semi-empirical mass–absolute magnitude relation with a scatter of 2% in mass. The best-agreement models overpredict stellar T{sub eff} values by an average of 2.2% and underpredict stellar radii by 4.6%, similar to differences with values from low-mass eclipsing binaries. These differences are not correlated with metallicity, mass, or indicators of activity, suggesting issues with the underlying model assumptions, e.g., opacities or convective mixing length.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2012

Communication: A vibrational study of propargyl cation using the vacuum ultraviolet laser velocity-map imaging photoelectron method

By employing the vacuum ultraviolet (VUV) laser velocity-map imaging photoelectron (VUV-VMI-PE) method, we have obtained a vibrationally resolved photoelectron spectrum of gaseous propargyl radical [C{sub 3}H{sub 3}(X{sup 2}B{sub 1})] in the energy range of 0-4600 cm{sup -1} above its ionization energy. The cold C{sub 3}H{sub 3} radicals were produced from a supersonically cooled radical beam source based on 193 nm ArF photodissociation of C{sub 3}H{sub 3}Cl. The VUV-VMI-PE spectrum of C{sub 3}H{sub 3} thus obtained reveals a Franck-Condon factor (FCF) pattern with a highly dominant origin band along with weak vibrational progressions associated with excitations of the C-C {nu}{sub 5}{sup +}(a{sub 1}) and C{identical_to}C {nu}{sub 3}{sup +}(a{sub 1}) symmetric stretching modes and the CCH {nu}{sub 7}{sup +}(b{sub 1}) out-of-plane bending mode of C{sub 3}H{sub 3}{sup +}(X{sup 1}A{sub 1}). The {nu}{sub 5}{sup +}(a{sub 1}) vibrational frequency of 1120 cm{sup -1} determined in the present study is lower than the value deduced from the recent Ar-tagged infrared photodissociation study by 102 cm{sup -1}, confirming the highly accurate vibrational frequency predictions obtained by the most recent state-of-the-art ab initio quantum calculations. The observation of the FCF disallowed {nu}{sub 7}{sup +}(b{sub 1}) mode is indicative of vibronic interactions. The discrepancy observed between the FCF pattern determined in the present study and that predicted by a recent high-level quantum theoretical investigation can be taken as evidence that the potential energy surfaces used in the latter theoretical study are in need of improvement in order to provide a reliable FCF prediction for the C{sub 3}H{sub 3}/C{sub 3}H{sub 3}{sup +} photoionization system.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2013

Predicting Backdrafting and Spillage for Natural-Draft Gas Combustion Appliances: Validating VENT-II

VENT-II is a computer program designed to provide detailed analysis of natural draft and induced draft combustion appliance vent-systems (i.e., furnace or water heater). This program is capable of predicting house depressurization thresholds that lead to backdrafting and spillage of combustion appliances; however, validation reports of the program being applied for this purpose are not readily available. The purpose of this report is to assess VENT-II’s ability to predict combustion gas spillage events due to house depressurization by comparing VENT-II simulated results with experimental data for four appliance configurations. The results show that VENT-II correctly predicts depressurizations resulting in spillage for natural draft appliances operating in cold and mild outdoor conditions, but not for hot conditions. In the latter case, the predicted depressurizations depend on whether the vent section is defined as part of the vent connector or the common vent when setting up the model. Overall, the VENTII solver requires further investigation before it can be used reliably to predict spillage caused by depressurization over a full year of weather conditions, especially where hot conditions occur.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2023

Bison Verification and Validation Activities for TRISO

Numerical modeling and simulation (M&S) tools play a key role in the research, development, and overall safety assessments of next-generation nuclear energy systems. One such tool, Bison, is a nuclear fuel performance code that is applicable to many fuel forms (e.g., light-water reactor fuel, oxide and metallic fuel for fast reactors, tri-structural isotropic (TRISO) fuel, and plate fuel), and it uses the finite element method to model the thermo- mechanical response of nuclear fuels. One fuel form widely utilized in Generation-IV high-temperature gas-cooled and fluoride- salt-cooled nuclear reactor concepts is TRISO fuel. Recently, Bison’s capabilities were significantly expanded to enable it to model the performance of TRISO particles and compacts. It is important that Bison’s computational results be reliable and predictive, since this code is used to inform high-consequence decisions. The various processes developed to address this issue generally entail two fundamental steps: verification and validation (V&V). Verification ensures that the code functions correctly and is reliable. Code/solution verification, code benchmark, and software quality assurance exercises are examples of verification activities. On the other hand, validation is the process of assessing a code’s capability to accurately model physical problems. Comparisons between code results and experiments quantify the validation level. Application of V&V procedures is crucial to the development of computational tools that are free of coding mistakes and can accurately represent reality. The current study presents an overview of Bison V&V activities relevant to the TRISO fuel concept, which include code/solution verification exercises, CRP-6 Benchmark—a Coordinated Research Program through the International Atomic Energy Agency (IAEA)—exercises, and validation exercises with the Advanced Gas Reactor (AGR)- 1/2/3/4 experiment series.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2026

3D Deep Learning Joint Inversion of Active Seismic Full Waveform and Passive Seismic Traveltime Data for Reservoir Imaging and Uncertainty Quantification

Here, we present deep learning (DL) networks for three-dimensional (3D) joint inversion of active seismic full waveform and passive seismic traveltime data to image reservoirs and their properties and quantify imaging uncertainties. Active seismic full-waveform data can provide high-resolution monitoring images but are collected only intermittently because of their high acquisition cost. In contrast, passive seismic data can be gathered at relatively low cost between regular active surveys, although their imaging quality can be compromised by factors such as low signal-to-noise ratios and limited ray coverage of the target. Although these datasets are routinely acquired together at CO 2 storage sites, their combined inversion within a 3D DL framework has not been previously demonstrated. To our knowledge, this is the first study to address this gap, combining the strength of both data types. For efficient data storage and DL training with large 3D seismic datasets, we use a 3D data matrix in which a random number of passive seismic traveltime data are stored as parabolic envelopes using one-hot encoding and a 3D full-waveform data matrix in which multiple shot gathers are summed. Two network architectures are evaluated: a single-encoder U-Net for single-data type inversion and a dual-encoder U-Net for joint inversion of active and passive seismic data. We also evaluate the single-encoder U-Net for joint inversion by concatenating full-waveform data and traveltime data. We propose a systematic approach for selecting an optimal dropout rate that balances regularization during training and Monte Carlo dropout-based uncertainty quantification during prediction by examining the correlation coefficient between standard deviation and prediction error, along with the training misfit, across a range of dropout rates. 3D DL inversion experiments include five different network configurations, with evaluations under ideal, noisy and dropout-enabled conditions. Both model and data uncertainties are assessed, as well as their combined effects. Across all conditions, the networks consistently predict accurate CO 2 saturation models with low prediction errors, such as a structural similarity index of 0.993 and CO 2 difference of 1.1%. Uncertainty estimates show strong spatial correlation with prediction errors, confirming the effectiveness of the proposed dropout selection approach. The results demonstrate that our DL approach, utilizing compact data representations and appropriate uncertainty quantification, yields accurate subsurface images under various inversion conditions and provides valuable insights into the reliability of predictions.

Um, Evan Schankee [Lawrence Berkeley National Labo↗
DOE OSTI2021

Extracting Material Property Measurement Data from Scientific Articles

Machine learning-based prediction of material properties is often hampered by the lack of sufficiently large training datasets. The majority of such measurement data is embedded in scientific literature and the ability to automatically extract these data is essential to support the development of reliable property prediction methods. In this work, we describe a methodology for an automatic property extraction framework using material solubility as the target property. We create an annotated dataset containing tags for solubility-related entities using a combination of regular expressions and manual tagging. We then compare five entity recognition models leveraging both token-level and span-level architectures on the task of classifying solute names, solubility values, and solubility units. Additionally, we explore a novel pretraining approach that leverages automated chemical name and quantity extraction tools to generate large datasets that do not rely on intensive manual effort. Finally, we perform an analysis to identify the causes of classification errors.

Panapitiya, Gihan U.↗
DOE OSTI2023

Review of machine learning and deep learning models for toxicity prediction

The ever-increasing number of chemicals has raised public concerns due to their adverse effects on human health and the environment. To protect public health and the environment, it is critical to assess the toxicity of these chemicals. Traditional in vitro and in vivo toxicity assays are complicated, costly, and time-consuming and may face ethical issues. These constraints raise the need for alternative methods for assessing the toxicity of chemicals. Recently, due to the advancement of machine learning algorithms and the increase in computational power, many toxicity prediction models have been developed using various machine learning and deep learning algorithms such as support vector machine, random forest, k-nearest neighbors, ensemble learning, and deep neural network. This review summarizes the machine learning- and deep learning-based toxicity prediction models developed in recent years. Support vector machine and random forest are the most popular machine learning algorithms, and hepatotoxicity, cardiotoxicity, and carcinogenicity are the frequently modeled toxicity endpoints in predictive toxicology. It is known that datasets impact model performance. The quality of datasets used in the development of toxicity prediction models using machine learning and deep learning is vital to the performance of the developed models. The different toxicity assignments for the same chemicals among different datasets of the same type of toxicity have been observed, indicating benchmarking datasets is needed for developing reliable toxicity prediction models using machine learning and deep learning algorithms. This review provides insights into current machine learning models in predictive toxicology, which are expected to promote the development and application of toxicity prediction models in the future.

Research & Experimental Medicine↗
DOE OSTI2015

Peculiarities of high-overtone transition probabilities in carbon monoxide revealed by high-precision calculation

In the recent work devoted to the calculation of the rovibrational line list of the CO molecule [G. Li et al., Astrophys. J., Suppl. Ser. 216, 15 (2015)], rigorous validation of the calculated parameters including intensities was carried out. In particular, the Normal Intensity Distribution Law (NIDL) [E. S. Medvedev, J. Chem. Phys. 137, 174307 (2012)] was employed for the validation purposes, and it was found that, in the original CO line list calculated for large changes of the vibrational quantum number up to Δn = 41, intensities with Δn > 11 were unphysical. Therefore, very high overtone transitions were removed from the published list in Li et al. Here, we show how this type of validation is carried out and prove that the quadruple precision is indispensably required to predict the reliable intensities using the conventional 32-bit computers. Based on these calculations, the NIDL is shown to hold up for the 0 → n transitions till the dissociation limit around n = 83, covering 45 orders of magnitude in the intensity. The low-intensity 0 → n transition predicted in the work of Medvedev [Determination of a new molecular constant for diatomic systems. Normal intensity distribution law for overtone spectra of diatomic and polyatomic molecules and anomalies in overtone absorption spectra of diatomic molecules, Institute of Chemical Physics, Russian Academy of Sciences, Chernogolovka, 1984] at n = 5 is confirmed, and two additional “abnormal” intensities are found at n = 14 and 23. Criteria for the appearance of such “anomalies” are formulated. The results could be useful to revise the high-overtone molecular transition probabilities provided in spectroscopic databases.

74 ATOMIC AND MOLECULAR PHYSICS↗
DOE OSTI2021

Accomplishments and Year-End Performance Report; Wind Energy Program: Fiscal Year 2021

The National Wind Technology Center (NWTC), located at the U.S. Department of Energy's (DOE's) National Renewable Energy Laboratory (NREL) Flatirons Campus, has been a driving force in advancing wind energy technology research worldwide since its designation as a DOE national research center in 1992. Enabled by the Flatirons Campus's world-class facilities, scientists, engineers, analysts, and researchers are pushing the frontiers of science to pursue wind energy innovation. In Fiscal Year (FY) 2021, NREL continued to provide the technical expertise, research capabilities, and industry understanding to support DOE's ambitious climate action and research goals by advancing technology, addressing market and deployment barriers, and driving down costs with more efficient, reliable, and predictable wind energy systems. One of several highlights, NREL received an R&D 100 Special Recognition Award for its Thermoplastic Resin System for Wind Turbine Blades. This breakthrough in the wind turbine manufacturing process will enable the production of recyclable blades that are stronger, longer, and less expensive, while increasing energy capture, decreasing energy and transportation costs, and increasing blade reliability. In a year when the entire U.S. economy struggled to address workforce gaps, an NREL study compared wind industry needs, training programs, and hiring practices with perspectives from students and recent college graduates. Researchers hope that, by pinpointing areas of disconnect, the expectations of employers who have difficulty filling entry-level jobs can better align with the preparation of the potential applicants who find it hard to break into the field. The lab also made numerous new data and modeling resources available in FY 2021. Recent NREL releases include a modeling tool for predicting the power performance and structural loads of wind turbines within a wind farm (FAST.Farm), a computational framework for modeling golden eagle behavior near wind farms, and 20 years of offshore wind data. Updates were also made to the widely used Wind Plant Integrated Systems Design and Engineering Model (WISDEM), which couples engineering and cost models to examine system-level trade-offs. Now, bolstered by a renewed national commitment to tackle climate change and revitalize the U.S. economy through increased investment in clean energy - particularly in offshore wind energy - NREL stands poised to lead the way to a sustainable future that powers the United States with significant levels of reliable, low-cost, accessible wind energy. This report provides an overview of the achievements NREL made on behalf of DOE's Wind Energy Technologies Office (WETO) and other partners during FY 2021 (between Oct. 1, 2020, and Sept. 30, 2021).

Flatirons Campus↗
DOE OSTI2015

Collision prediction software for radiotherapy treatments

Purpose: This work presents a method of collision predictions for external beam radiotherapy using surface imaging. The present methodology focuses on collision prediction during treatment simulation to evaluate the clearance of a patient’s treatment position and allow for its modification if necessary. Methods: A Kinect camera (Microsoft, Redmond, WA) is used to scan the patient and immobilization devices in the treatment position at the simulator. The surface is reconstructed using the SKANECT software (Occipital, Inc., San Francisco, CA). The treatment isocenter is marked using simulated orthogonal lasers projected on the surface scan. The point cloud of this surface is then shifted to isocenter and converted from Cartesian to cylindrical coordinates. A slab models the treatment couch. A cylinder with a radius equal to the normal distance from isocenter to the collimator plate, and a height defined by the collimator diameter is used to estimate collisions. Points within the cylinder clear through a full gantry rotation with the treatment couch at 0° , while points outside of it collide. The angles of collision are reported. This methodology was experimentally verified using a mannequin positioned in an alpha cradle with both arms up. A planning CT scan of the mannequin was performed, two isocenters were marked in PINNACLE, and this information was exported to AlignRT (VisionRT, London, UK)—a surface imaging system for patient positioning. This was used to ensure accurate positioning of the mannequin in the treatment room, when available. Collision calculations were performed for the two treatment isocenters and the results compared to the collisions detected the room. The accuracy of the Kinect-Skanect surface was evaluated by comparing it to the external surface of the planning CT scan. Results: Experimental verification results showed that the predicted angles of collision matched those recorded in the room within 0.5°, in most cases (largest deviation −1.2°). The accuracy study for the Kinect-Skanect surface showed an average discrepancy between the CT external contour and the surface scan of 2.2 mm. Conclusions: This methodology provides fast and reliable collision predictions using surface imaging. The use of the Kinect-Skanect system allows for a comprehensive modeling of the patient topography including all the relevant anatomy and immobilization devices that may lead to collisions. The use of this tool at the treatment simulation stage may allow therapists to evaluate the clearance of a patient’s treatment position and optimize it before the planning CT scan is performed. This can allow for safer treatments for the patients due to better collision predictions and improved clinical workflow by minimizing replanning and resimulations due to unforeseen clearance issues.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2016

Stereo-particle image velocimetry uncertainty quantification

Particle image velocimetry (PIV) measurements are subject to multiple elemental error sources and thus estimating overall measurement uncertainty is challenging. Recent advances have led to a posteriori uncertainty estimation methods for planar two-component PIV. However, no complete methodology exists for uncertainty quantification in stereo PIV. In the current paper, a comprehensive framework is presented to quantify the uncertainty stemming from stereo registration error and combine it with the underlying planar velocity uncertainties. The disparity in particle locations of the dewarped images is used to estimate the positional uncertainty of the world coordinate system, which is then propagated to the uncertainty in the calibration mapping function coefficients. Next, the calibration uncertainty is combined with the planar uncertainty fields of the individual cameras through an uncertainty propagation equation and uncertainty estimates are obtained for all three velocity components. The methodology was tested with synthetic stereo PIV data for different light sheet thicknesses, with and without registration error, and also validated with an experimental vortex ring case from 2014 PIV challenge. Thorough sensitivity analysis was performed to assess the relative impact of the various parameters to the overall uncertainty. The results suggest that in absence of any disparity, the stereo PIV uncertainty prediction method is more sensitive to the planar uncertainty estimates than to the angle uncertainty, although the latter is not negligible for non-zero disparity. Overall the presented uncertainty quantification framework showed excellent agreement between the error and uncertainty RMS values for both the synthetic and the experimental data and demonstrated reliable uncertainty prediction coverage. Finally, this stereo PIV uncertainty quantification framework provides the first comprehensive treatment on the subject and potentially lays foundations applicable to volumetric PIV measurements.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2019

Distributed Wind Resource Assessment Framework: Functional Requirements and Metrics for Performance and Reliability Modeling

The focus of the distributed wind resource assessment (DWRA) performance framework is to first clarify the key parameters that define the wind resource for any distributed wind turbine project and then describe the loss and uncertainty factors associated with long-term performance of wind turbine projects. Next it will identify and define the key parameters required to analyze the operational performance of a project. This framework could then be the foundation for understanding the predictability of the power and revenue from a project. Improving the predictability and reliability of wind power generation and operations will reduce costs and potentially establish a framework to attract new capital to the distributed wind industry sector. This report is the first part of a research effort to investigate the impact that improved resource assessment and energy estimation for distributed wind can have on consumer confidence, cost of capital, cost of ownership and operations, perception of financial risk, and levelized cost of energy.

17 WIND ENERGY↗
DOE OSTI2015

The anharmonic quartic force field infrared spectra of three polycyclic aromatic hydrocarbons: Naphthalene, anthracene, and tetracene

Current efforts to characterize and study interstellar polycyclic aromatic hydrocarbons (PAHs) rely heavily on theoretically predicted infrared (IR) spectra. Generally, such studies use the scaled harmonic frequencies for band positions and double harmonic approximation for intensities of species, and then compare these calculated spectra with experimental spectra obtained under matrix isolation conditions. High-resolution gas-phase experimental spectroscopic studies have recently revealed that the double harmonic approximation is not sufficient for reliable spectra prediction. In this paper, we present the anharmonic theoretical spectra of three PAHs: naphthalene, anthracene, and tetracene, computed with a locally modified version of the SPECTRO program using Cartesian derivatives transformed from Gaussian 09 normal coordinate force constants. Proper treatments of Fermi resonances lead to an impressive improvement on the agreement between the observed and theoretical spectra, especially in the C–H stretching region. All major IR absorption features in the full-scale matrix-isolated spectra, the high-temperature gas-phase spectra, and the most recent high-resolution gas-phase spectra obtained under supersonically cooled molecular beam conditions in the CH-stretching region are assigned.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
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↗