Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Traditional Machine Learning Models”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

PopGNN: Graph Neural Network-Based Flexible Future Population Forecasting Model

Accurate population forecasts is important to plan critical infrastructure and services, from housing and education to healthcare and transport. However, traditional population prediction studies have only employed traditional machine learning models limited to capture complex spatial interdependencies and patterns. Althogh recently computer vision-based framework was introduced with with promising accuracy, it has critical limitations for real-world planning applications: it function only at fixed spatial resolutions, restricting their use in diverse boundaries such as census tracts, neighborhoods, or administrative zones. Therefore, this study suggests a Graph Neural Network (GNN)-based population prediction framework, called PopGNN. This model recorded remarkable performance compared with state-of-the-art models and traditional baseline models in the grid and administrative boundaries. Furthermore, our framework achieved comparable predictive accuracy to a computer vision-based model in both the South Korea and Tennessee case studies. Consequently, this study is valuable in that a single model can provide accurate population forecasts that address diverse planning demands, ranging from granular grid-level estimates for precise service allocation and facility location planning to aggregate administrative-level forecasts for macro-scale regional policy and resource distribution.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Assessment of fine-tuned large language models for real-world chemistry and material science applications

The current generation of large language models (LLMs) has limited chemical knowledge. Recently, it has been shown that these LLMs can learn and predict chemical properties through fine-tuning. Using natural language to train machine learning models opens doors to a wider chemical audience, as field-specific featurization techniques can be omitted. In this work, we explore the potential and limitations of this approach. We studied the performance of fine-tuning three open-source LLMs (GPT-J-6B, Llama-3.1-8B, and Mistral-7B) for a range of different chemical questions. We benchmark their performances against “traditional” machine learning models and find that, in most cases, the fine-tuning approach is superior for a simple classification problem. Depending on the size of the dataset and the type of questions, we also successfully address more sophisticated problems. The most important conclusions of this work are that, for all datasets considered, their conversion into an LLM fine-tuning training set is straightforward and that fine-tuning with even relatively small datasets leads to predictive models. These results suggest that the systematic use of LLMs to guide experiments and simulations will be a powerful technique in any research study, significantly reducing unnecessary experiments or computations.

Van Herck, Joren↗
DOE OSTI2022

Expanded analysis of machine learning models for nuclear transient identification using TPOT

Industries around the world are becoming more and more data driven. The nuclear field is no exception with several different applications being proposed. One popular area of research is the use of machine learning in transient detection. This paper seeks to build upon a previous study which made use of the AutoML package TPOT to train traditional machine learning models to classify transient events occurring with a reactor. Synthetic data was once again collected using a GPWR reactor simulator. Data on 12 different events was collected using 15 different initial conditions. Here, a dataset consisting of over 100,000 data points was compiled and used to train 7 different machine learning models using a pre-defined TPOT dictionary with 12 different preprocessing techniques. Three of the trained models were able to produce validation results in the 90s with the expanded dataset. Once the models were trained, it was possible to look into where during the simulation, misclassifications occurred. Using these three models, analysis was done to determine if TPOT could be used to train models that were effective if important features were missing. The results from this were positive with the newly trained models scoring close to the original models. Finally, to conclude this study, the three high performing models were retrained using different random states to see if there was any major variation when different states were used.

42 ENGINEERING↗
DOE OSTI2022

An adaptive knowledge-based data-driven approach for turbulence modeling using ensemble learning technique under complex flow configuration: 3D PWR sub-channel with DNS data

This work describes a new approach to increase the accuracy of Reynolds-averaged Navier–Stokes (RANS) in modeling turbulence flow leveraging the machine learning technique. Traditionally, different turbulence models for Reynolds stress are developed for different flow patterns based on human knowledge. Each turbulence model has a certain application domain and prediction uncertainty. In recent years, with the rapid improvements of machine learning techniques, researchers start to develop an approach to compensate for the prediction discrepancy of traditional turbulence models with statistical models and data. However, the approach has deficiencies in several aspects. For example, the amount of human knowledge introduced to the statistical model couldn’t be controlled, which makes the statistical model learn from a very naïve stage and limits its application. In this work, a new approach is developed to address those deficiencies. Here, the new approach uses the “ensemble learning” technique to control the amount of human knowledge introduced into the statistical model. Therefore, the new approach could be adaptive to the multiple application domains. In conclusion, according to the results of case study, the new approach shows higher accuracy than both traditional turbulence models and the previous machine learning approach.

42 ENGINEERING↗
DOE OSTI2022

Network Anomaly Detection Using Federated Learning

The internet is turning out to be an integral part of every-one's lives as more and more devices are being connected to serve societal needs. Our work is motivated by two ma-jor observations. Firstly, one drawback of connecting to the network is the threat of network attacks that can compromise users' private information, leading to data loss and adversely affecting productivity. There are several traditional security mechanisms to defend against these attacks, such as firewalls, virtual private networks (VPNs), demilitarized zones (DMZs), and vulnerability scanners. One way to prevent these attacks is early detection and prevention. However, these kinds of architecture do not scale very well because of their centralized nature. Secondly, we observe from heuristics and data set distributions that the majority of the requests made to a server are innocuous. Therefore, almost all server request data sets are highly imbalanced, weighted highly towards the harmless requests.

Marfo, William↗
DOE OSTI2025

Exploring Capability of Multimodal Foundation Model for Image-based Fault Detection of Photovoltaic Modules

Multimodal Foundation Model (MFM), like ChatGPT and Gemini, have emerged as powerful tools for their exceptional natural language processing capabilities and their emerging potential in image analysis. This paper investigates the application of MFMs for photovoltaic (PV) fault detection through image analysis, focusing on ChatGPT 4.0 and Gemini 1.5 Pro. Three types of PV images and the corresponding common PV faults are detected: bird droppings using visible images, cell cracks via electroluminescence (EL) images, and hotspots using infrared (IR) images. Among the two models, Gemini 1.5 Pro demonstrated superior performance, achieving near-perfect results with an average F1 score of 0.97, consistently outperforming ChatGPT 4.0 in accuracy and reliability. Unlike traditional machine learning (ML) models, MFMs can operate in a zero shot manner that does not require additional training by the user, and the input images are not limited by size, angle, scope, or PV technology. The strong adaptability and user-friendliness make MFM a promising tool for analyzing PV images and advancing health monitoring for PV modules.

Li, Baojie↗
DOE OSTI2024

A Deep Learning Approach for In-Network Synchrophasor Missing Data Recovery Using Programmable Network Switches

Phasor measurement unit (PMU) networks deliver accurate and timely measurements, which is essential for managing today’s electric power systems. To ensure data quality and enhance the cyber-resilience of PMU networks against malicious attacks and data errors, this study presents an online PMU missing data recovery scheme by leveraging P4 programmable switches. The data plane incorporates a customized PMU protocol parser that abstracts the necessary payload data for recovery. Recovery processes are executed in the control plane using a pre-trained machine learning model. Both traditional and advanced ML models, such as transformer and TimeGPT, are explicitly employed for data prediction. This approach ensures rapid and precise data recovery. Performance evaluations focus on recovery speed and accuracy, using a real dataset from a campus microgrid. With 20% missing PMU data, the mean absolute percentage error for voltage magnitude is 0.0384%, and the phase angle error discrepancy is approximately 0.4064%.

Phasor Measurement Unit, Machine Learning, Program↗
DOE OSTI2022

What Makes You Hold on to That Old Car? Joint Insights From Machine Learning and Multinomial Logit on Vehicle-Level Transaction Decisions

What makes you hold on to that old car? While the vast majority of household vehicles are still powered by conventional internal combustion engines, the progress of adopting emerging vehicle technologies will critically depend on how soon the existing vehicles are transacted out of the household fleet. Leveraging a nationally representative longitudinal data set, the Panel Study of Income Dynamics, this study examines how household decisions to dispose of or replace a given vehicle are: 1) influenced by the vehicle’s attributes, 2) mediated by households’ concurrent socio-demographic and economic attributes, and 3) triggered by key life cycle events. Coupled with a newly developed machine learning interpretation tool, TreeExplainer, we demonstrate an innovative use of machine learning models to augment traditional logit modeling to both generate behavioral insights and improve model performance. We find the two gradient-boosting-based methods, CatBoost and LightGBM, are the best performing machine learning models for this problem. The multinomial logistic model can achieve similar performance levels after its model specification is informed by TreeExplainer. Both machine learning and multinomial logit models suggest that while older vehicles are more likely to be disposed of or replaced than newer ones, such probability decreases as the vehicles serve the family longer. Pickup trucks and sport utility vehicles are less likely to be disposed of or replaced than cars, and leased vehicles are more likely to be transacted than owned vehicles. We find that married families, families with higher education levels, homeowners, and older families tend to keep their vehicles longer. Life events such as childbirth, residential relocation, and change of household composition and income are found to increase vehicle disposal and/or replacement. We provide additional insights on the timing of vehicle replacement or disposal, in particular, the presence of children and childbirth events are more strongly associated with vehicle replacement among younger parents.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2024

Learning together: Towards foundation models for machine learning interatomic potentials with meta-learning

Abstract The development of machine learning models has led to an abundance of datasets containing quantum mechanical (QM) calculations for molecular and material systems. However, traditional training methods for machine learning models are unable to leverage the plethora of data available as they require that each dataset be generated using the same QM method. Taking machine learning interatomic potentials (MLIPs) as an example, we show that meta-learning techniques, a recent advancement from the machine learning community, can be used to fit multiple levels of QM theory in the same training process. Meta-learning changes the training procedure to learn a representation that can be easily re-trained to new tasks with small amounts of data. We then demonstrate that meta-learning enables simultaneously training to multiple large organic molecule datasets. As a proof of concept, we examine the performance of a MLIP refit to a small drug-like molecule and show that pre-training potentials to multiple levels of theory with meta-learning improves performance. This difference in performance can be seen both in the reduced error and in the improved smoothness of the potential energy surface produced. We therefore show that meta-learning can utilize existing datasets with inconsistent QM levels of theory to produce models that are better at specializing to new datasets. This opens new routes for creating pre-trained, foundation models for interatomic potentials.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2025

Transfer learning-based soybean LAI estimations by integrating PROSAIL, UAV, and PlanetScope imagery

Accurate Leaf Area Index (LAI) estimations at the soybean plot scale is achievable using high-resolution Unmanned Aerial Vehicle (UAV) imagery and field measurement samples. However, the limited coverage of UAV flights restricts large-scale remote sensing monitoring in expansive soybean fields. This study leverages the broad coverage and 3-m resolution of PlanetScope satellite imagery to extend LAI prediction from UAV to satellite scales through transfer learning, using UAV-scale LAI estimates as a benchmark to validate cross-scale consistency. To address this challenge, this study proposed the LAI-TransNet, a two-stage transfer learning framework designed for precise and scalable soybean LAI prediction across large areas, demonstrating its effectiveness in cross-scale monitoring. In Stage 1, a UAV-scale benchmark is established using PROSAIL-simulated UAV reflectance data (UAV-Sim) and field-measured soybean LAI. Traditional machine learning, deep learning, and transfer learning models are trained on a hybrid UAV-Sim and field-measured dataset (UAV-Sim_Measured), with the transfer learning model CNN-TL, fine-tuned using pre-trained weights derived from UAV-Sim, achieving the highest accuracy (R 2 = 0.81, RMSE = 0.64 m 2 /m 2 , rRMSE = 11.5 %). In Stage 2, LAI-TransNet is developed by fine-tuning the CNN-TL model on PlanetScope simulated data (PS-Sim), preprocessed via cross-domain mapping to align UAV and satellite spectral features. Real PlanetScope imagery is corrected for reflectance consistency with reference to UAV imagery spectral profiles. LAI-TransNet outperforms other deep learning models trained directly on PS-Sim (R 2 = 0.69 vs. 0.60–0.63), ensuring robust cross-scale consistency. In conclusion, by bridging UAV and satellite scales, LAI-TransNet enables large-scale soybean LAI monitoring, enhancing precision agriculture management through improved monitoring with the PlanetScope imagery.

Leaf area index (LAI)↗
NASA NTRSDate not supplied

Surrogate Modeling of Subgrid Turbulent Transport Based on 3D Radiative Hydrodynamic Simulations of the Quiet Sun

Turbulent Transport: Plays a critical role in astrophysical plasmas, such as the solar interior, spanning multiple scales and challenging traditional modeling approaches. Objective: Develop machine learning (ML) models—MLP and CNN—to predict subgrid Reynolds stress tensors from StellarBox 3D simulations of the solar atmosphere. Benchmarking: Compare ML-driven models against physics-based Gradient and Smagorinsky approaches.

SMD↗
DOE OSTI2022

Neural network accelerator for quantum control

Efficient quantum control is necessary for practical quantum computing implementations with current technologies. Conventional algorithms for determining optimal control parameters are computationally expensive, largely excluding them from use outside of the simulation. Existing hardware solutions structured as lookup tables are imprecise and costly. By designing a machine learning model to approximate the results of traditional tools, a more efficient method can be produced. Such a model can then be synthesized into a hardware accelerator for use in quantum systems. In this study, we demonstrate a machine learning algorithm for predicting optimal pulse parameters. This algorithm is lightweight enough to fit on a low-resource FPGA and perform inference with a latency of 175 ns and pipeline interval of 5 ns with > 0.99 gate fidelity. In the long term, such an accelerator could be used near quantum computing hardware where traditional computers cannot operate, enabling quantum control at a reasonable cost at low latencies without incurring large data bandwidths outside of the cryogenic environment.

43 PARTICLE ACCELERATORS↗
DOE OSTI2025

Discovering nuclear models from symbolic machine learning

Numerous phenomenological nuclear models have been proposed to describe specific observables within different regions of the nuclear chart. However, developing a unified model that describes the complex behavior of all nuclei remains an open challenge. Here, we explore whether symbolic Machine Learning (ML) can rediscover traditional nuclear physics models or identify alternatives with improved simplicity, fidelity, and predictive power. To address this challenge, we developed a Multi-objective Iterated Symbolic Regression approach that handles symbolic regressions over multiple target observables, accounts for experimental uncertainties and is robust against high-dimensional problems. As a proof of principle, we applied this method to describe the nuclear binding energies and charge radii of light and medium mass nuclei. Our approach identified simple analytical relationships based on the number of protons and neutrons, providing interpretable models with precision comparable to state-of-the-art nuclear models. Additionally, we integrated this ML-discovered model with an existing complementary model to estimate the limits of nuclear stability. These results highlight the potential of symbolic ML to develop accurate nuclear models and guide our description of complex many-body problems.

Nuclear structure↗
DOE OSTI2022

NREL Stratus - Enabling Workflows to Fuse Data Streams, Modeling, Simulation, and Machine Learning

Integrating cloud services into advanced computing facilities provides significant new capabilities over focusing solely on traditional high performance computing (HPC) workloads. This brings complementary capabilities as well as enabling new focused roles for HPC. They are especially potent for workflows that fuse data streams, modeling and simulation ('modsim') and machine learning. A key challenge to adopting a hybrid edge-cloud-HPC model is to align optimal capability, data, and user intent on the right resources for each step in a workflow.?The NREL Stratus service provides a basis for this: Stratus layers capabilities needed to make?cloud services accessible to a lab-based scientific community on commercial offerings, and; currently supports upwards of 200 projects ranging from IOT integration to traditional modeling and simulation. This provides a real-world inventory of scientific workflow elements. A growing knowledge base enables placing these elements appropriately between the edge, cloud, and traditional HPC. This paper outlines a vision via reference architecture and the application of that architecture in a typical workflow highlighting multiple components: sensor data intake, cleaning and transforming (edge/cloud suitable); generation of synthetic data through modsim, computationally heavy ML training and hyperparameter optimization (HPC suitable), and; inference and deployment (cloud ideal). Every step in such a workflow involves a cost-benefit analysis regarding the data movement, computational efficiency, availability, latency, and resource capabilities. The reference architecture and examples outlined allow for understanding new opportunities in the context of emerging workflows that combine IOT, cloud, and HPC to bolster scientific productivity.

AI↗
DOE OSTI2023

Computationally Accelerated Discovery and Experimental Demonstration of High-Performance Materials for Advanced Solar Thermochemical Hydrogen Production

This project achieved its overarching goal of accelerating the discovery and validation of solar thermochemical hydrogen (STCH) materials through a tightly integrated approach that combined high-throughput computational screening, advanced machine learning (ML), and experimental testing. Guided by the objectives outlined in the Statement of Project Objectives (SOPO), our work fulfilled all major milestones across four technical tasks and delivered scientific breakthroughs and practical tools that significantly exceeded the original scope of the project. We began by addressing the challenge of predicting material phase stability through machine learning. A novel Python module was developed to generate thousands of meaningful features from composition, structure, and electronic properties, enabling rapid and reproducible ML model development. Using these tools, we trained a model to predict temperature-dependent Gibbs energies (G(T)) for inorganic crystalline materials with near-chemical accuracy—roughly 40 meV/atom—marking the first such descriptor of its kind. We also introduced a new machine-learned tolerance factor, τ, that accurately predicted perovskite formability with over 90% success, outperforming traditional heuristic models, such as the Goldschmidt tolerance factor. These capabilities allowed for rapid and accurate predictions of phase stability across a vast oxide composition space, setting the stage for high-throughput thermodynamic screening. Building on this foundation, we conducted an extensive computational screening of candidate STCH oxide materials. Over 1.1 million perovskite compositions were evaluated using the τ descriptor, leading to the identification of more than 27,000 predicted stable structures. Using density functional theory (DFT), we refined over 68,000 multinary perovskite structures and computed oxygen vacancy formation energies for over 1,300 ternary and double perovskites. These calculations enabled us to isolate compounds with redox behavior consistent with STCH requirements and resulted in a public dataset now hosted on the Materials Project. Recognizing that thermodynamic screening alone is insufficient, we addressed kinetic limitations by developing a suite of tools to estimate transition state (TS) energies for key redox reactions. We implemented a novel bounding approach that provides lower and upper estimates of TS energies with dramatically reduced computational cost, requiring less than 10% of the CPU time of a full nudged elastic band (NEB) calculation while maintaining high accuracy. This enabled rapid evaluation of over 200 reaction pathways across 90 materials. To further accelerate screening, we developed a SISSO-based ML model to predict diffusion barriers with a 96.7% success rate in classifying fast vs. slow materials, supporting a robust, data-driven framework for assessing redox kinetics. Experimental validation was critical to confirming the predictive power of our models. We synthesized and tested a wide array of candidate materials, including Mn-doped hercynite and several Gd- and La-based perovskites. Notably, Sr 0.4 Gd 0.6 Mn 0.6 Al 0.4 O 3 (SGMA) and Gd 0.5 La 0.5 Co 0.5 Fe 0.5 O 3 (GLCF) emerged as leading STCH materials, exhibiting robust redox cycling and high hydrogen yields exceeding 150 µmol H 2 /g per cycle. These materials also retained over 50% of their hydrogen productivity under high-conversion conditions (H 2 O:H 2 = 1333:1), demonstrating strong thermodynamic favorability and promising performance under industrially relevant scenarios. Additional candidates, such as La 2 MnNiO 6 (L2MN), were found to produce even higher yields than ceria under standard STCH conditions. Our collaborators at Sandia National Laboratories confirmed these findings using high-temperature X-ray diffraction and thermogravimetric analysis, observing stable phase evolution and reversible redox activity. In several respects, the project went beyond the goals initially outlined in the SOPO. We published 17 peer-reviewed articles, including a large dataset of over 66,000 theoretical perovskites and a new structure prediction method (SPuDS-DFT) that accurately identifies ground-state structures at a fraction of the cost of traditional DFT. We demonstrated that our machine-learned G(T) model offers accuracy rivaling quasiharmonic calculations while being orders of magnitude faster. In partnership with the Materials Project, we made our datasets openly available, providing a powerful new resource for the broader materials science community. The combined computational and experimental advances of this project represent a significant advance in STCH materials discovery. By creating a robust, generalizable, and open workflow for thermodynamic and kinetic screening, and validating key findings through synthesis and reactor testing, we have provided a practical and scalable pathway for the rapid identification of new redox-active materials. The tools, data, and materials developed under this project are already supporting ongoing research and have laid the groundwork for the next generation of solar fuel technologies.

08 HYDROGEN↗
DOE OSTI2024

Unifying Quantum Materials Modeling and Experiments: The Role of Machine Learning Interatomic Potentials

Computational experiments have emerged as a powerful complement to traditional experiments in the design of new materials. The development of machine learning (ML) and deep learning techniques, combined with database construction and data mining, has significantly enhanced traditional quantum mechanical methods. This synergy enables the rapid development of structure-property relationships. In this talk, I will discuss our recent efforts in applying Machine Learning Interatomic Potentials (MLIAPs) to accelerate materials modeling across various material classes and challenging applications where traditional methods fall short. First, I will highlight the success of MLIAPs in accurately modeling the melting behavior of complex materials. Our results demonstrate high fidelity with experimental observations and also with calculated reference melting temperatures. In the second application, I will discuss how MLIAPs are trained and applied to elucidate the interplay between segregation tendencies and surface reconstructions in CuNi alloys under oxidizing conditions. A key factor in the success of these MLIAP applications is the design of minimalistic yet flexible datasets along with a computational framework for training MLIAPs.

Saidi, Wissam↗
NASA NTRSDate not supplied

Comparison of Entry Descent and Landing Aerodynamic Databases with Uncertainty Quantification Developed Using Machine Learning Techniques

When developing the aerodynamic databases for use in trajectory simulations, it is important to develop a system of metrics to qualify which aerodynamic models are best to use. Since aerodynamics are just one input into trajectory simulations, the results of these simulations do not reflect on the quality of the aerodynamic database used. This means that aerodynamic database comparisons must be done offline. While traditional metrics that focus on mean/nominal predictions are a good first step, more robust estimates of the prediction interval become important as more focused uncertainty models are developed. We explore the limitations of evaluating aerodynamic models based purely on nominal-centered response surfaces. Before elaborating and evaluating metrics based on distributed models, the value of evaluating prediction interval and confidence interval are discussed to conclude that prediction intervals are more relevant to the use of trajectory analysis. Several metrics to evaluate the prediction interval are introduced with a focus on the standard calibration metric. Finally, we compare candidate models using both mean and distributed metrics. A finalized candidate model developed using state of the art machine learning methods is compared to a baseline model developed using traditional aerodynamic database modeling techniques.

Aerodynamic Database↗