Search NASA⌕ Search

SEARCH · Search NASA

Results for “noise 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 91 records · Page 5
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

High-Order Qubit Dephasing at Sweet Spots by Non-Gaussian Fluctuators: Symmetry Breaking and Floquet Protection

Although the Gaussian noise assumption is widely adopted in studying qubit decoherence, non-Gaussian noise sources have been detected in many qubits. Further understanding and mitigating the distinctive decoherence effect of the non-Gaussian noise remain critical. Here, we study the qubit dephasing caused by non-Gaussian fluctuators, and predict a symmetry-breaking effect that is unique to non-Gaussian noise. This broken symmetry results in an experimentally measurable mismatch between the extremum points of the dephasing rate and qubit frequency, which demands extra carefulness in characterizing the noise and locating the optimal working point. To further enhance the coherence time, we propose suppressing the second-order derivative of the qubit frequency by Floquet engineering. Our simulation on a tunable and gapped two-level quantum system, with the parameters from a heavy fluxonium, shows an order-of-magnitude improvement of the dephasing time, even after including the drive noise.

Huang, Ziwen↗
DOE OSTI2022

Non-destructive measurement and real-time monitoring of apple hardness during ultrasonic contact drying via portable NIR spectroscopy and machine learning

Portable near-infrared spectrometer in the spectral range of 900–1700 nm was evaluated for the first time to assess and monitor apple hardness in real-time during ultrasonic drying. Calibration models were developed using PLS and ANN, and their performances were evaluated by internal leave-one-out cross-validation and an external dataset. Several pre-treatments including standard normal variate (SNV), multiplicative scatter correction (MSC), Savitzky–Golay first and second derivatives were employed to examine the effects of spectral variations in hardness prediction. Seven important wavelengths were selected using weighted regression coefficients to develop a simple MLR model to facilitate the model interpretation and circumvent noise. The models using PLS, MLR, and ANN with selected wavelengths predicted the apple hardness with R 2 p of 0.91, 0.91, 0.95, and RMSEP of 14.78, 14.85, and 12.46 N, respectively. Finally, the results indicate that portable NIR spectrometers are quite promising for real-time monitoring of apple hardness during ultrasonic drying.

47 OTHER INSTRUMENTATION↗
DOE OSTI2025

Effect of likelihood misspecification in Gaussian process-driven autonomous experimentation

In recent years, several groups have designed Autonomous Experiment (AE) models with the aim of using them as an alternative method for neutron scattering scanning. In an AE, Gaussian processes (GPs) are most frequently used due to their interpretability, their non-parametric nature, their universal approximation, and their closed-form predictive distribution. GPs have two key components, namely, the model for the likelihood of a neutron count knowing the underlying dynamic structure factor and the acquisition function. In this paper, we investigate the impact, on the quality of an AE, of the likelihood and acquisition function choices, in energy scans and (Q, ω) ones, with respect to the signal-over-noise ratio. While we hypothesized that the quality of GP predictions would decrease when the normal to Poisson likelihood approximation breaks down at low count rates, we found that the use of the correct Poisson likelihood does not improve the quality of the data collected, as well as yields very poor results in (Q, ω) scans at low count rates. In fact, the best results are obtained with a combination of normal likelihood, including the observation noise, and the change in variance acquisition function. In addition, we find that the performance, or quality of the predictive distribution, is a misleading measure of efficiency, that is, of the quality of the data collected.

Perryman, David Elliott [Inst. Laue-Langevin (ILL)↗
DOE OSTI2024

A deep learning approach to fast analysis of collective Thomson scattering spectra

Fast analysis of collective Thomson scattering ion acoustic wave features using a deep convolutional neural network model is presented. The network was trained from spectra to predict the plasma parameters, including ion velocities, population fractions, and ion and electron temperatures. A fully kinetic particle-in-cell simulation was used to model a laboratory astrophysics experiment and simulate a diagnostic image of the ion acoustic wave feature. Network predictions were compared with Bayesian inference of the plasma model parameters for both the simulated and experimentally measured images. Both approaches were fairly accurate predicting the simulated image and the network predictions matched a good portion of the Bayesian results for the experimentally measured image. The Bayesian approach is more robust to noise and motivates future work to train deep learning models with realistic noise. The advantage of the deep learning model is making thousands of predictions in a few hundred milliseconds, compared to a few seconds to minutes per prediction for the optimization and Bayesian approaches presented here. The results demonstrate promising capabilities of deep learning models to analyze Thomson data orders of magnitude faster than conventional methods when using the neural network for standalone analysis. If more rigorous analysis is needed, neural network predictions can be used to quickly initialize other optimization methods and increase chances of success. This is especially useful when the dataset becomes very large or highly dimensional and manually refining initial conditions for the entire dataset are no longer tractable.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2023

A multiscale recurrent neural network model for predicting energy production from geothermal reservoirs

Optimization of energy production from geothermal reservoirs requires reliable prediction of energy production performance under alternative operation and development scenarios. Traditionally, reservoir simulation models are used for the evaluation and screening of alternative production and development plans. However, simulation models require extensive data collection and modeling efforts and are time-consuming to build, run, and update. Data-driven predictive models, on the other hand, can serve as efficient prediction tools that can be used for decision support and management of daily operations and surveillance activities. Data-driven models become particularly attractive when a reservoir simulation model for a field does not exist and/or is difficult to build. Machine learning (ML)-based data-driven models that have recently become popular in several fields exploit statistical patterns and relations in training data to generate predictions. As such, they tend to perform better in interpolation problems (that is, prediction within the training data range) than when they are used to extrapolate beyond the training data. Production data from geothermal reservoirs tend to exhibit short-term variabilities as well as long-term trends, such as monotonically declining production temperatures. Capturing both short-term features and long-term trends with ML-based models is not trivial. We evaluate the use of recurrent neural networks (RNN) for the prediction of energy production from geothermal reservoirs. RNN is a class of ML architectures that are used to represent and predict sequential/dynamic data. Thus, it can be challenging to apply RNN to problems where long-term trends must be captured and extrapolation beyond the training data range is needed. We introduce the multiscale RNN architecture to extend the application of RNN to detect and predict both short-term variabilities and long-term trends in geothermal data. The developed architecture consists of a long-term component to only capture low-frequency data patterns, and a short-term component to detect features with higher frequency and more nonlinearity. The final prediction is obtained by combining the long-term and short-term predictions. Both synthetic and field data are used to evaluate the presented multiscale RNN model. The prediction performance of the multiscale RNN is compared against those obtained from the regular RNN and the autoregressive (AR) model. The results suggest that the multiscale architecture improves the long-term prediction performance of the regular RNN and enhances its robustness against noise.

15 GEOTHERMAL ENERGY↗
DOE OSTI2020

Indicator Patterns of Forced Change Learned by an Artificial Neural Network

Abstract Many problems in climate science require the identification of signals obscured by both the “noise” of internal climate variability and differences across models. Following previous work, we train an artificial neural network (ANN) to predict the year of a given map of annual‐mean temperature (or precipitation) from forced climate model simulations. This prediction task requires the ANN to learn forced patterns of change amidst a background of climate noise and model differences. We then apply a neural network visualization technique (layerwise relevance propagation) to visualize the spatial patterns that lead the ANN to successfully predict the year. These spatial patterns thus serve as “reliable indicators” of the forced change. The architecture of the ANN is chosen such that these indicators vary in time, thus capturing the evolving nature of regional signals of change. Results are compared to those of more standard approaches like signal‐to‐noise ratios and multilinear regression in order to gain intuition about the reliable indicators identified by the ANN. We then apply an additional visualization tool (backward optimization) to highlight where disagreements in simulated and observed patterns of change are most important for the prediction of the year. This work demonstrates that ANNs and their visualization tools make a powerful pair for extracting climate patterns of forced change.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

TRUST Nonlinear Dynamics Testbed Assessment

The following assessment evaluates the efficacy of the control script for carrying out a linear signal to generate a linear mechanical response of the system: the TRUST nonlinear dynamics (TRUSTND) testbed. The hardware has three main components: the controller (NI PXIe 8861) embedded in the National Instruments chassis (NI PXIe 1092), the signal amplifier (The Modal Shop Linear Power Amplifier 2050E09) to amplify the output of a custom LabVIEW script, and a shaker (The Modal Shop Electrodynamic Exciter 2075E) where wave spring specimens live and are tested within the attached aluminum testbed (center mass). Different kinds of signals (single-tone, swept frequency and white noise) were sent through this hardware in the E-1 lab space at TA-53. First, the linearity of the setup was tested by specifying a sine wave in the control script and checking the quality of the oscillations in a wave spring (McMaster-Carr 9714K19 [1]). When passing a sine wave through the amplifier was succeeded, the frequency response of the wave spring was tested with white noise for comparison to finite-element model predictions. The testbed outputs a repeatable, linear response to the input excitation when used with the wave spring. These measurements reduce the uncertainty associated with the testbed and test procedure to better characterize uncertainty associated with material behavior (SX358 foam samples) in future tests

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2026

Improving the Precision of First-Principles Calculation of Parton Physics from Lattice Quantum Chromodynamics

Large momentum effective theory (LaMET) provides a general framework for computing the multi-dimensional partonic structure of the proton from first principles using lattice quantum chromodynamics (QCD). In this effective field theory approach, LaMET predicts parton distributions through a power expansion and perturbative matching of a class of Euclidean observables—quasi-distributions—evaluated at large proton momenta. Recent advances in lattice renormalization, such as the hybrid scheme with leading renormalon resummation, together with improved matching kernel that incorporates higher-loop corrections and resummations, have enhanced both the perturbative and power accuracy of LaMET, enabling a reliable quantification of theoretical uncertainties. Moreover, the Coulomb-gauge correlator approach further simplifies lattice analyses and improves the precision of transverse-momentum-dependent structures, particularly in the non-perturbative region. State-of-the-art LaMET calculations have already yielded certain parton observables with important phenomenological impact. In addition, the recently proposed kinematically enhanced lattice interpolation operators promise access to unprecedented proton momenta with greatly improved signal-to-noise ratios, which will extend the range of LaMET prediction and further suppress the power corrections. The remaining challenges, such as controlling excited-state contamination in lattice matrix elements and extracting gluonic distributions, are expected to benefit from emerging lattice techniques for ground-state isolation and noise reduction. Thus, lattice QCD studies of parton physics have entered an exciting stage of precision control and systematic improvement, which will have a broader impact for nuclear and particle experiments.

Zhao, Yong [Argonne National Laboratory (ANL), Arg↗
DOE OSTI2025

Monte Carlo N-Particle Transport Performance of Predicting Digital Radiographic IQI Inspection

The identification of porosity, geometric noncompliance, and other defect types are critical to the qualification of materials and components. X-ray radiographic nondestructive testing is a common industrial inspection method for process quality control and component qualification and certification. Digital radiography provides a quick and efficient alternative when compared to traditional film-based inspection. The quality of radiographic inspection is dependent on equipment specifications, such as the source spot size and detector pixel size, and the specific parameters selected for use for the radiographic technique. To evaluate if an x-ray system and technique is sufficient for a given requirement, a radiographic image quality indicator (IQI) can be used. Radiographic IQIs in hard to machine materials or hard to manufacture defects can be time consuming and expensive to manufacture. This study was conducted to evaluate current Savannah River National Laboratory (SRNL) x-ray imaging systems with a custom tantalum IQI and using Monte Carlo simulations to predict the performance of future systems. The tantalum IQI was tested using a Siefert Isovolt 420 keV x-ray tube with a Perkin Elmer XRD 1611 flat panel with 100-micron pixels. Using the Monte Carlo N-Particle transport software, the radiographic tally was used to simulate the photon flux through an identical tantalum IQI. These simulations provided a benchmark as to the best theoretical identification on a given system using our tantalum IQI. The simulations were refined to match SRNL’s current systems’ noise levels, leading to confidence in their ability to predict the performance of other systems that may be purchased and deployed in the future at the Savannah River Site. Future studies will be conducted to prove this research can be extended to artificially evaluate the ability for systems to identify critical defect sizes through x-ray radiographic inspection, drastically reducing the cost and time burdens of producing high-fidelity radiographic test articles.

digital X-ray radiography↗
DOE OSTI2022

Adversarial autoencoder ensemble for fast and probabilistic reconstructions of few-shot photon correlation functions for solid-state quantum emitters

Second-order photon correlation measurements [g (2) (τ) functions] are widely used to classify single-photon emission purity in quantum emitters or to measure the multiexciton quantum yield of emitters that can simultaneously host multiple excitations – such as quantum dots – by evaluating the value of g (2) (τ = 0). Accumulating enough photons to accurately calculate this value is time consuming and could be accelerated by fitting of few-shot photon correlations. Here, we develop an uncertainty-aware, deep adversarial autoencoder ensemble (AAE) that reconstructs noise-free g (2) (τ) functions from noise-dominated, few-shot inputs. The model is trained with simulated g (2) (τ) functions that are facilely generated by Poisson sampling time bins. The AAE reconstructions are performed orders-of-magnitude faster, with reconstruction errors and estimates of g (2) (τ = 0) that are lower in variance and similar in accuracy compared to Maximum likelihood estimation and Levenberg-Marquardt least-squares fitting approaches, for simulated and experimentally measured few-shot g (2) (τ) functions (~100 two-photon events) of InP/ZnS/ZnSe and CdS/CdSe/CdS quantum dots. The deep-ensemble model comprises eight individual autoencoders, allowing for probabilistic reconstructions of noise-free g (2) (τ) functions, and we show that the predicted variance scales inversely with number of shots, with comparable uncertainties to computationally intensive Markov chain Monte Carlo sampling. Furthermore, this work demonstrates the advantage of machine learning models to perform uncertainty-aware, fast, and accurate reconstructions of simple Poisson-distributed photon correlation functions, allowing for on-the-fly reconstructions and accelerated materials characterization of solid-state quantum emitters.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2020

Evaluating the Potential and Challenges of an Uncertainty Quantification Method for Long Short–Term Memory Models for Soil Moisture Predictions

Recently, recurrent deep networks have shown promise to harness newly available satellite–sensed data for long–term soil moisture projections. However, to be useful in forecasting, deep networks must also provide uncertainty estimates. Here we evaluated Monte Carlo dropout with an input–dependent data noise term (MCD+N), an efficient uncertainty estimation framework originally developed in computer vision, for hydrologic time series predictions. MCD+N simultaneously estimates a heteroscedastic input–dependent data noise term (a trained error model attributable to observational noise) and a network weight uncertainty term (attributable to insufficiently constrained model parameters). Although MCD+N has appealing features, many heuristic approximations were employed during its derivation, and rigorous evaluations and evidence of its asserted capability to detect dissimilarity were lacking. To address this, we provided an in–depth evaluation of the scheme's potential and limitations. We showed that for reproducing soil moisture dynamics recorded by the Soil Moisture Active Passive (SMAP) mission, MCD+N indeed gave a good estimate of predictive error, provided that we tuned a hyperparameter and used a representative training data set. The input–dependent term responded strongly to observational noise, while the model term clearly acted as a detector for physiographic dissimilarity from the training data, behaving as intended. However, when the training and test data were characteristically different, the input–dependent term could be misled, undermining its reliability. Additionally, due to the data–driven nature of the model, data noise also influences network weight uncertainty, and therefore the two uncertainty terms are correlated. Altogether, this approach has promise, but care is needed to interpret the results.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Investigation of the effects of turbulence modeling on the prediction of compression-ignition combustion unsteadiness

Adverse effects of global warming due to the greenhouse gas emissions is changing the actual paradigm for the use energy resources. In the absence of a mid-term solution for reducing these emissions in transportation, internal combustion (IC) engines are going to coexist in the social spheres in the foreseeable future. Therefore, the study of other IC engine-related problems remains relevant to ensuring the health of the society. In this investigation, a numerical methodology for comprehensive understanding of Noise, Vibration and Harshness in internal combustion engines is proposed. Due to its inherent complexity and lack of awareness, the main objective is to evaluate the impact of the turbulence modeling framework on the in-cylinder acoustic field recreation. Modal decomposition methods have been applied to isolate the coherent flow structures and to analyze how they change with the turbulence approach. Results demonstrate that the choice of the turbulence model is a critical aspect for noise modeling. Unsteady Reynolds-Averaged Navier-Stokes schemes predict a raw estimation of the internal acoustic field with the added value of being computationally less expensive. However, the use of more complex turbulence approaches such us large eddy simulation offers an accurate prediction of the acoustic structures and their cyclic dispersion.

Broatch, A.↗
DOE OSTI2020

Simulating the Multi-epoch Direct Detection Technique to Isolate the Thermal Emission of the Non-transiting Hot Jupiter HD187123b

We report the 6.5σ detection of water from the hot Jupiter HD187123b with a Keplerian orbital velocity K {sub p} of 53 ± 13 km s{sup −1}. This high-confidence detection is made using a multi-epoch, high-resolution, cross-correlation technique, and corresponds to a planetary mass of 1.4{sub −0.3}{sup +0.5} M {sub J} and an orbital inclination of 21° ± 5°. The technique works by treating the planet/star system as a spectroscopic binary and obtaining high signal-to-noise, high-resolution observations at multiple points across the planet’s orbit to constrain the system’s binary dynamical motion. All together, seven epochs of Keck/NIRSPEC L-band observations were obtained, with five before the instrument upgrade and two after. Using high-resolution SCARLET planetary and PHOENIX stellar spectral models, we were able to drastically increase the confidence of the detection by running simulations that could reproduce, and thus remove, the nonrandom structured noise in the final likelihood space well. The ability to predict multi-epoch results will be extremely useful for furthering the technique. Here, we use these simulations to compare three different approaches to combining the cross correlations of high-resolution spectra and find that the Zucker log(L) approach is least affected by unwanted planet/star correlation for our HD187123 data set. Furthermore, we find that the same total signal-to-noise ratio (S/N) spread across an orbit in many, lower S/N epochs rather than fewer, higher S/N epochs could provide a more efficient detection. This work provides a necessary validation of multi-epoch simulations, which can be used to guide future observations and will be key to studying the atmospheres of farther separated, non-transiting exoplanets.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

DriveSense: A Noise-Resilient Framework for Driving Mode Identification

Accurate drive mode classification is essential for enhancing the reliability and predictive maintenance of heavy-duty electric trucks. This study proposes a novel fuzzy logic-based framework, DriveSense, for real-time drive mode classification, addressing key challenges such as sensor noise, transitional behaviors, and computational efficiency. The proposed approach integrates a two-stage filtering pipeline, combining adaptive outlier removal and a dynamic Kalman filter to enhance data quality. A fuzzy inference system with smoothened trapezoidal membership functions is then applied to classify driving modes into standstill, constant speed, acceleration, and deceleration while mitigating the effects of noise and edge cases. Performance evaluation using real-world and simulated drive cycles demonstrates significant improvements in classification accuracy (up to 97.8%), F1-score (up to 0.97), and robustness against noise, while reducing false positives. Comparative analysis against baseline models, demonstrates DriveSense’s superior accuracy and generalizability across diverse driving patterns. The framework’s lightweight and interpretable fuzzy inference engine operates with low computational latency, ensuring compatibility with real-time embedded systems typical of heavy-duty electric trucks. Moreover, DriveSense models transitional behaviors through overlapping fuzzy sets and adaptive borderline classification logic, enabling smooth identification of subtle shifts such as rolling stops or gradual deceleration. These results highlight DriveSense’s potential to enhance predictive maintenance strategies, reduce downtime, and support scalable, fleet-wide diagnostics.

Kumar, Praveen [Oak Ridge National Laboratory (ORN↗
DOE OSTI2025

Uncertainty Quantification for Data-Driven Machine Learning Models in Nuclear Engineering Applications: Where We Are and What Do We Need?

Machine learning (ML) has been leveraged to tackle a diverse range of tasks in almost all branches of nuclear engineering. Many of the successes in ML applications can be attributed to the recent performance breakthroughs in deep learning, the growing availability of computational power, data, and easy-to-use ML libraries. However, these empirical successes have often outpaced our formal understanding of the ML algorithms. An important but under-rated area is uncertainty quantification (UQ) of ML. ML-based models are subject to approximation uncertainty when they are used to make predictions, due to sources including but not limited to, data noise, data coverage, extrapolation, imperfect model architecture and the stochastic training process. The goal of this paper is to clearly explain and illustrate the importance of UQ of ML. We will elucidate the differences in the basic concepts of UQ of physics-based models and data-driven ML models. Various sources of uncertainties in physical modeling and data-driven modeling will be discussed, demonstrated, and compared. We will also present and demonstrate a few techniques to quantify the ML prediction uncertainties, including Monte Carlo dropout, deep ensemble, Bayesian neural networks, Gaussian Processes and conformal prediction. Lastly, we will discuss the need for building a verification, validation and UQ framework to establish ML credibility.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2021

Characterization of the molten salt FMgNaK through ab initio molecular dynamics and experimental density measurements

The selection of a salt species for use in a molten salt reactor MSR is a key part of any MSR design. However, many salts have sparse or no thermophysical property data sets, especially those with higher melting points. One such salt is the eutectic mixture of (NaF)0.345(KF)0.59(MgF 2 )0.065, or FMgNaK, and is explored here through ab initio molecular dynamics (AIMD) simulation (1023-1273K) as well as experimental measurement of the liquid density using the Archimedean method (973-1223K). Predicted densities from AIMD are similar to experimentally-measured densities, though with more noise, suggesting that the small scale necessitated by AIMD simulations may be problematic for simulating FMgNaK in particular. Here the coefficient of thermal expansion is predicted from simulation, and salt structure is characterized. Mg-F-Mg chaining is observed in the salt network, though the low concentration of Mg inhibits chaining on the scale that is observed in (LiF) 0.67 (BeF 2 ) 0.33 , or FLiBe.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Measurement of hybrid rocket solid fuel regression rate for a slab burner using deep learning

This study presents an imaging-based deep learning tool to measure the fuel regression rate in a 2D slab burner experiment for hybrid rocket fuels. The slab burner experiment is designed to verify mechanistic models of reacting boundary layer combustion in hybrid rockets by the measurement of fuel regression rates. A DSLR camera with a high intensity flash is used to capture images throughout the burn and the images are then used to find the fuel boundary to calculate the regression rate. A U-net convolutional neural network architecture is explored to segment the fuel from the experimental images. Here, a Monte-Carlo Dropout process is used to quantify the regression rate uncertainty produced from the network. The U-net computed regression rates are compared with values from other techniques from literature and show error less than 10%. An oxidizer flux dependency study is performed and shows the U-net predictions of regression rates are accurate and independent of the oxidizer flux, when the images in the training set are not over-saturated. Training with monochrome images is explored and is not successful at predicting the fuel regression rate from images with high noise. The network is superior at filtering out noise introduced by soot, pitting, and wax deposition on the chamber glass as well as the flame when compared to traditional image processing techniques, such as threshold binary conversion and spatial filtering. U-net consistently provides low error image segmentations to allow accurate computation of the regression rate of the fuel.

42 ENGINEERING↗
DOE OSTI2021

Selecting XFEL single-particle snapshots by geometric machine learning

A promising new route for structural biology is single-particle imaging with an X-ray Free-Electron Laser (XFEL). This method has the advantage that the samples do not require crystallization and can be examined at room temperature. However, high-resolution structures can only be obtained from a sufficiently large number of diffraction patterns of individual molecules, so-called single particles. Here, we present a method that allows for efficient identification of single particles in very large XFEL datasets, operates at low signal levels, and is tolerant to background. This method uses supervised Geometric Machine Learning (GML) to extract low-dimensional feature vectors from a training dataset, fuse test datasets into the feature space of training datasets, and separate the data into binary distributions of “single particles” and “non-single particles.” As a proof of principle, we tested simulated and experimental datasets of the Coliphage PR772 virus. We created a training dataset and classified three types of test datasets: First, a noise-free simulated test dataset, which gave near perfect separation. Second, simulated test datasets that were modified to reflect different levels of photon counts and background noise. These modified datasets were used to quantify the predictive limits of our approach. Third, an experimental dataset collected at the Stanford Linear Accelerator Center. The single-particle identification for this experimental dataset was compared with previously published results and it was found that GML covers a wide photon-count range, outperforming other single-particle identification methods. Moreover, a major advantage of GML is its ability to retrieve single particles in the presence of structural variability.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗