SEARCH · Engineering Papers
Results for “factorization machine”
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.
Development of a Convolutional Neural Network Classifier for Data Starved Spectra - 20199
The Institute for Clean Energy Technology (ICET) at Mississippi State University is exploring the utility of machine learning in augmenting its mobile radiation surveying platforms, which are currently being developed as means to survey depleted uranium contaminated areas in support of remediation and decommissioning efforts. Mobile survey platforms provide a means to efficiently scan large areas of interest while reducing human exposure to radiation and other hazards. The survey platforms can also be used for scanning for any gamma emitting isotope in addition to depleted uranium. The spectral data that the platforms collect may be data starved with relatively low counts and poorly defined spectral features depending on the speed of the platforms and scintillation detector selection. Such data-starved spectra are difficult to use for isotope identification, requiring advanced knowledge of the possible radionuclides that could be present and environmental factors that could attenuate signals or introduce background noise. These factors in combination with the volume of survey data increases the time it takes to perform analysis of survey data when the source type is unknown. There are a number of algorithms in the field of machine learning that can be used to classify data that would be challenging and time-consuming for a human to identify. Supervised machine learning algorithms train models based on extensive amounts of human-labeled training data. Once sufficiently trained, these models can be used to quickly make high-fidelity predictions on new data. Convolutional neural networks are machine learning algorithms that excel in learning representations of 'shapes'. They do this by taking numerical input data and convolving them with spatial feature detectors referred to as filters. These filters are incrementally adjusted to reduce the prediction error on the data during the backpropagation step of training. Discussed in this paper is the development of a convolutional neural network classifier (CNNC) that can utilize spectral survey data for source discrimination and isotope identification. Bench-top laboratory experiments data using LaBr{sub 3}(Ce) scintillation detectors were used to train and evaluate the performance of the developed CNNC. The CNNC is capable of discriminating a variety of gamma emitting source types, differentiating different forms of uranium (depleted vs. natural), and estimating the amount of uranium for a known geometry. The discussed CNNC may be useful in scenarios where survey systems are deployed in situations where hazardous radioactive material maybe present, but the type is unknown. When used in remediation applications the CNNC can be used to screen-out false positives, helping reduce remediation costs. (authors)
Meeting Global Health Needs via Infectious Disease Forecasting: Development of a Reliable Data-Driven Framework
Infectious diseases (IDs) have a significant detrimental impact on global health. Timely and accurate ID forecasting can result in more informed implementation of control measures and prevention policies. To meet the operational decision-making needs of real-world circumstances, we aimed to build a standardized, reliable, and trustworthy ID forecasting pipeline and visualization dashboard that is generalizable across a wide range of modeling techniques, IDs, and global locations. We forecasted 6 diverse, zoonotic diseases (brucellosis, campylobacteriosis, Middle East respiratory syndrome, Q fever, tick-borne encephalitis, and tularemia) across 4 continents and 8 countries. We included a wide range of statistical, machine learning, and deep learning models (n=9) and trained them on a multitude of features (average n=2326) within the One Health landscape, including demography, landscape, climate, and socioeconomic factors. The pipeline and dashboard were created in consideration of crucial operational metrics—prediction accuracy, computational efficiency, spatiotemporal generalizability, uncertainty quantification, and interpretability—which are essential to strategic data-driven decisions. While no single best model was suitable for all disease, region, and country combinations, our ensemble technique selects the best-performing model for each given scenario to achieve the closest prediction. For new or emerging diseases in a region, the ensemble model can predict how the disease may behave in the new region using a pretrained model from a similar region with a history of that disease. The data visualization dashboard provides a clean interface of important analytical metrics, such as ID temporal patterns, forecasts, prediction uncertainties, and model feature importance across all geographic locations and disease combinations. As the need for real-time, operational ID forecasting capabilities increases, this standardized and automated platform for data collection, analysis, and reporting is a major step forward in enabling evidence-based public health decisions and policies for the prevention and mitigation of future ID outbreaks.
Machine learning for slow-extraction uniformity at the Fermilab Delivery Ring
The Muon-to-Electron Conversion Experiment (Mu2e) requires uniform slow extraction from the Fermilab Delivery Ring during each 43 ms spill. This project analyzed 13,737 spills from seven parquet files collected during March and June 2026 commissioning. Each spill contained 430 samples at 0.1 ms resolution and was summarized by the Spill Duty Factor. Null Action and active proportional-integral-derivative conditions established operational baselines. Fixed-ramp sessions were segmented to evaluate reproducibility, drift, and spill-to-spill spread, while a deliberate quadrupole-ramp step identified the beam-response peak and trough. Median profiles were reproducible within fixed conditions but drifted over multi-hour periods. The resulting baselines and response features support future physics-based and machine-learning approaches to real-time spill regulation.
Interpreting High-resolution Spectroscopy of Exoplanets using Cross-correlations and Supervised Machine Learning
We present a new method for performing atmospheric retrieval on ground-based, high-resolution data of exoplanets. Our method combines cross-correlation functions with a random forest, a supervised machine-learning technique, to overcome challenges associated with high-resolution data. A series of cross-correlation functions are concatenated to give a “CCF-sequence” for each model atmosphere, which reduces the dimensionality by a factor of ∼100. The random forest, trained on our grid of ∼65,000 models, provides a likelihood-free method of retrieval. The precomputed grid spans 31 values of both temperature and metallicity, and incorporates a realistic noise model. We apply our method to HARPS-N observations of the ultra-hot Jupiter KELT-9b and obtain a metallicity consistent with solar (logM = − 0.2 ± 0.2). Our retrieved transit chord temperature (T=6000{sub −200}{sup +0}K) is unreliable as strong ion lines lie outside of the extent of the training set, which we interpret as being indicative of missing physics in our atmospheric model. We compare our method to traditional nested sampling, as well as other machine-learning techniques, such as Bayesian neural networks. We demonstrate that the likelihood-free aspect of the random forest makes it more robust than nested sampling to different error distributions, and that the Bayesian neural network we tested is unable to reproduce complex posteriors. We also address the claim in Cobb et al. 2019 that our random forest retrieval technique can be overconfident but incorrect. We show that this is an artifact of the training set, rather than of the machine-learning method, and that the posteriors agree with those obtained using nested sampling.
High-Throughput Screening and Accurate Prediction of Ionic Liquid Viscosities Using Interpretable Machine Learning
Ionic liquids (ILs) are a novel group of green solvents with great promise for various industrial applications, including carbon capture and lignocellulosic biomass deconstruction. However, the use of ILs at the industrial scale remains challenging due to their high viscosities at ambient temperatures. To develop ILs with lower viscosities, a systematic study of their quantitative structure–property relationship (QSPR) is desirable. Here, we developed four machine learning (ML) models to predict viscosity at various temperature and pressure ranges, trained over a wide range of ILs consisting of various cationic and anionic families. ML methods including two-factor polynomial regression (two-factor PR), support vector regression (SVR), feed-forward neural networks (FFNN), and categorical boosting (CATBoost) were developed based on features that have proven useful in previous ML studies: COSMO-RS (conductor-like screening model for real solvents)-derived surface screening charge densities (sigma profiles). FFNN and CATBoost were the most accurate in predicting IL viscosities with lower average absolute relative deviation and higher R2 values on the test set. Tanimoto similarity scores were calculated to characterize the chemical space and structural similarity of the investigated ions. Furthermore, SHapley Additive exPlanation (SHAP) analysis was employed to interpret the ML results. Temperature, the polar area of ILs, and the nonpolar regions of ions are key features that influence the viscosity predictions. Importantly, the IL viscosity prediction here is the most accurate reported to date.
Quantifying Leaf Chlorophyll Concentration of Sorghum from Hyperspectral Data Using Derivative Calculus and Machine Learning
Leaf chlorophyll concentration (LCC) is an important indicator of plant health, vigor, physiological status, productivity, and nutrient deficiencies. Hyperspectral spectroscopy at leaf level has been widely used to estimate LCC accurately and non-destructively. This study utilized leaf-level hyperspectral data with derivative calculus and machine learning to estimate LCC of sorghum. We calculated fractional derivative (FD) orders starting from 0.2 to 2.0 with 0.2 order increments. Additionally, 43 common vegetation indices (VIs) were calculated from leaf spectral reflectance factor to make comparisons with reflectance-based data. Within the modeling pipeline, three feature selection methods were assessed: Pearson’s correlation coefficient (PCC), partial least squares based variable importance in the projection (VIP), and random forest-based mean decrease impurity (MDI). Finally, we used partial least squares regression (PLSR), random forest regression (RFR), support vector regression (SVR), and extreme learning regression (ELR) to estimate the LCC of sorghum. Results showed that: (1) increasing derivative order can show improved model performance until certain order for reflectance-based analysis; however, it is inconclusive to state that a particular order is optimal for estimating LCC of sorghum; (2) VI-based modeling outperformed derivative augmented reflectance factor-based modeling; (3) mean decrease impurity was found effective in selecting sensitive features from large feature space (reflectance-based analysis), whereas simple Pearson’s correlation coefficient worked better with smaller feature space (VI-based analysis); and (4) SVR outperformed all other models within reflectance-based analysis; alternatively, ELR with VIs from original reflectance yielded slightly better results compared to all other models.
Smart CO2 Transport-Route Planning Tool
NETL has developed the Smart CO2 Transport-Route Planning Tool to help inform energy transport planning and development. The stand-alone, open-source tool applies data-driven, geospatial and machine-learning informed logic to identify potential routes or evaluate existing corridors based on current legislation, best construction practices, and more. Underpinning the interactive tool, is NETL’s CO2 Transport Planning Database (https://edx.netl.doe.gov/dataset/ccs-pipeline-route-planning-database-v1). This geospatial resource contains more than 70 gigabytes of data representing more than 60 critical factors for the spatial routing of CO2 transport, including land use requirements, existing infrastructure, high consequence areas, and natural hazards.
Microscopic and Macroscopic Characterization of Grain Boundary Energy and Strength in Silicon Carbide via Machine-Learning Techniques
Predicting the properties of grain boundaries poses a challenge because of the complex relationships between structural and chemical attributes both at the atomic and continuum scales. Grain boundary systems are typically characterized by parameters used to classify local atomic arrangements in order to extract features such as grain boundary energy or grain boundary strength. The present work utilizes a combination of high-throughput atomistic simulations, macroscopic and microscopic descriptors, and machine-learning techniques to characterize the energy and strength of silicon carbide grain boundaries. Additionally, a diverse data set of symmetric tilt and twist grain boundaries are described using macroscopic metrics such as misorientation, the alignment of critical low-index planes, and the Schmid factor, but also in terms of microscopic metrics, by quantifying the local atomic structure and chemistry at the interface. These descriptors are used to create random-forest regression models, allowing for their relative importance to the grain boundary energy and decohesion stress to be better understood. Results show that while the energetics of the grain boundary were best described using the microscopic descriptors, the ability of the macroscopic descriptors to reasonably predict grain boundaries with low energy suggests a link between the crystallographic orientation and the resultant atomic structure that forms at the grain boundary within this regime. For grain boundary strength, neither microscopic nor macroscopic descriptors were able to fully capture the response individually. However, when both descriptor sets were utilized, the decohesion stress of the grain boundary could be accurately predicted. These results highlight the importance of considering both macroscopic and microscopic factors when constructing constitutive models for grain boundary systems, which has significant implications for both understanding the fundamental mechanisms at work and the ability to bridge length scales.
shiftNMFk 1.1: Robust Nonnegative matrix factorization with kmeans clustering and signal shift, for allocation of unknown physical sources, toy version for open sourcing with publications
This code is a toy (short) version of CODE-2016-83. From a general perspective, the code represents an unsupervised adaptive machine learning algorithm that allows efficient and high performance de-mixing and feature extraction of a multitude of non-negative signals mixed and recorded by a network of uncorrelated sensor arrays. The code identifies the number of the mixed original signals and their locations. Further, the code also allows deciphering of signals that have been delayed in regards to the mixing process in each sensor. This code is high customizable and it can be efficiently used for a fast macro-analyses of data. The code is applicable to a plethora of distinct problems: chemical decomposition, pressure transient decomposition, unknown sources/signal allocation, EM signal decomposition. An additional procedure for allocation of the unknown sources is incorporated in the code.
shiftNMFk 1.1: Robust Nonnegative matrix factorization with kmeans clustering and signal shift, for allocation of unknown physical sources, toy version for open sourcing with publications
This code is a toy (short) version of CODE-2016-83. From a general perspective, the code represents an unsupervised adaptive machine learning algorithm that allows efficient and high performance de-mixing and feature extraction of a multitude of non-negative signals mixed and recorded by a network of uncorrelated sensor arrays. The code identifies the number of the mixed original signals and their locations. Further, the code also allows deciphering of signals that have been delayed in regards to the mixing process in each sensor. This code is high customizable and it can be efficiently used for a fast macro-analyses of data. The code is applicable to a plethora of distinct problems: chemical decomposition, pressure transient decomposition, unknown sources/signal allocation, EM signal decomposition. An additional procedure for allocation of the unknown sources is incorporated in the code.
SU-E-T-325: The New Evaluation Method of the VMAT Plan Delivery Using Varian DynaLog Files and Modulation Complexity Score (MCS)
Purpose: The aim of the study is to evaluate the use of Varian DynaLog files to verify VMAT plans delivery and modulation complexity score (MCS) of VMAT. Methods: Delivery accuracy of machine performance was quantified by multileaf collimator (MLC) position errors, gantry angle errors and fluence delivery accuracy for volumetric modulated arc therapy (VMAT). The relationship between machine performance and plan complexity were also investigated using the modulation complexity score (MCS). Plan and Actual MLC positions, gantry angles and delivered fraction of monitor units were extracted from Varian DynaLog files. These factors were taken from the record and verify system of MLC control file. Planned and delivered beam data were compared to determine leaf position errors and gantry angle errors. Analysis was also performed on planned and actual fluence maps reconstructed from those of the DynaLog files. This analysis was performed for all treatment fractions of 5 prostate VMAT plans. The analysis of DynaLog files have been carried out by in-house programming in Visual C++. Results: The root mean square of leaf position and gantry angle errors were about 0.12 and 0.15, respectively. The Gamma of planned and actual fluence maps at 3%/3 mm criterion was about 99.21. The gamma of the leaf position errors were not directly related to plan complexity as determined by the MCS. Therefore, the gamma of the gantry angle errors were directly related to plan complexity as determined by the MCS. Conclusion: This study shows Varian dynalog files for VMAT plan can be diagnosed delivery errors not possible with phantom based quality assurance. Furthermore, the MCS of VMAT plan can evaluate delivery accuracy for patients receiving of VMAT. Machine performance was found to be directly related to plan complexity but this is not the dominant determinant of delivery accuracy.
Wavelet Analysis of Properties of Marine Boundary Layer Mesoscale Cells Observed From AMSR–E
Marine boundary layer clouds tend to organize into closed or open mesoscale cellular convection (MCC). Here, two-dimensional wavelet analysis is applied for the first time to passive microwave retrievals of cloud water path (CWP), water vapor path (WVP), and rain rate (RR) from Advanced Microwave Scanning Radiometer for Earth Observing System in 2008 over the Northeast and Southeast Pacific, and the Southeast Atlantic subtropical stratocumulus to cumulus transition regions. The (co-)variability between CWP, WVP, and RR in 160 × 160 km 2 analysis boxes is partitioned between four mesoscale wavelength octaves (20, 40, 80, and 160 km). The cell scale is identified as the wavelength of the peak CWP variance. Together with a machine-learning classification of cell type, this allows the statistical characteristics of open and closed MCC of various scales, and its relation to WVP, RR, and potential environmental controlling factors to be analyzed across a very large set of cases. Here, the results show that the cell wavelength is most commonly 40–80 km. Cell-scale CWP perturbations are good predictors of the WVP and RR perturbations. For cells larger than 20 km, there is no obvious dependence of cell scale on the environmental controlling factors tested, suggesting that the cell scale may depend more on its historical evolution than the current environmental conditions.
Automated model-predictive design of synthetic promoters to control transcriptional profiles in bacteria
Abstract Transcription rates are regulated by the interactions between RNA polymerase, sigma factor, and promoter DNA sequences in bacteria. However, it remains unclear how non-canonical sequence motifs collectively control transcription rates. Here, we combine massively parallel assays, biophysics, and machine learning to develop a 346-parameter model that predicts site-specific transcription initiation rates for any σ 70 promoter sequence, validated across 22132 bacterial promoters with diverse sequences. We apply the model to predict genetic context effects, design σ 70 promoters with desired transcription rates, and identify undesired promoters inside engineered genetic systems. The model provides a biophysical basis for understanding gene regulation in natural genetic systems and precise transcriptional control for engineering synthetic genetic systems.
Coherent-state storage and retrieval between superconducting cavities using parametric frequency conversion
In superconducting quantum information, machined aluminum superconducting cavities have proven to be a well-controlled, low-dissipation electromagnetic environment for quantum circuits such as qubits. They can possess large internal quality factors, Q{sub int} > 10{sup 8}, and present the possibility of storing quantum information for times far exceeding those of microfabricated circuits. However, in order to be useful as a storage element, these cavities require a fast “read/write” mechanism—in other words, they require tunable coupling between other systems of interest such as other cavity modes and qubits, as well as any associated readout hardware. In this work, we demonstrate these qualities in a simple dual cavity architecture in which a low-Q “readout” mode is parametrically coupled to a high-Q “storage” mode, allowing us to store and retrieve classical information. Specifically, we employ a flux-driven Josephson junction-based coupling scheme to controllably swap coherent states between two cavities, demonstrating full, sequenced control over the coupling rates between modes.
Improving Effective Mass Estimations in Pu-Metal Annuli
Determining the effective mass of 240 Pu in a plutonium metal item can be achieved through a number of destructive and non-destructive assay techniques. However, these techniques have one or more shortcomings. These include the need for large quantities of plutonium, long measurement time, or lack of sufficient accuracy. While efforts have been made to mitigate these issues by estimating 240 Pu quantities through neutron coincidence counting techniques, these estimates are subject to systematic bias, and their estimates are not well characterized when other factors of the annulus’ physical form and composition are accounted for. In this work, we expand upon these non-destructive assay techniques via the implementation of random forest machine learning models, which produce correction functions that augment and improve the effective mass estimates derived from classical leakage multiplication, singles, doubles, and triples multiplicity counting equations.
Investigating the opioid epidemic across the United States: Associations between county-level characteristics and overdose mortality
The opioid crisis remains a critical public health challenge in the United States. Despite national efforts that reduced opioid prescribing by nearly 44% between 2011 and 2021, opioid overdose deaths more than tripled during the same period. This alarming trend reflects a major shift in the crisis, with illegal opioids now driving the majority of overdose deaths instead of prescription opioids. Although supply-side factors fueling this transition have been widely studied, the structural and community-level conditions that shape overdose mortality are less well understood. To help address this gap, this study has three primary objectives: (1) overcome structural gaps in national data to construct a complete nationwide county-level dataset from 2010 to 2022; (2) using data analysis, identify and investigate spatiotemporal anomalies in overdose mortality; and (3) using two machine-learning models, quantify the importance of thirteen social vulnerability variables in predicting overdose mortality. Our results identify unemployment and limited vehicle access as key county-level predictors of overdose mortality. Higher levels of these vulnerabilities are associated with elevated mortality, whereas lower levels are associated with reduced mortality. These findings highlight factors that may be relevant for public health planning and policy prioritization within the context of the opioid crisis.
Explainable machine learning model for multi-step forecasting of reservoir inflow with uncertainty quantification
We propose an explainable machine learning (ML) model with uncertainty quantification (UQ) to improve multi-step reservoir inflow forecasting. Traditional ML methods have challenges in forecasting inflows multiple days ahead, and lack explainability and UQ. To address these limitations, we introduce an encoder–decoder long short-term memory (ED-LSTM) network for multi-step forecasting, employ the SHapley Additive exPlanation (SHAP) technique for understanding the influence of hydrometeorological factors on inflow prediction, and develop a novel UQ method for prediction trustworthiness. We apply these methods to forecast 7-day inflow in snow-dominant and rain-driven reservoirs. The results demonstrate the effectiveness of the ED-LSTM model, with high forecasting accuracy for short lead times. Our UQ method provides reliable uncertainty estimates, covering 90% of data with a 90% confidence level. The SHAP analysis reveals the importance of historical inflow and precipitation as influential factors. These findings and methods may support reservoir operators in optimizing water resources management decisions.