Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “scientific machine learning”

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 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Machine Learning for DUNE Supernova Trigger

One of the major scientific goals of the Deep Underground Neutrino Experiment (DUNE) is to detect and measure the neutrino flux from galactic core-collapse supernovae. These neutrinos, which exist in the low energy range of up to a few tens of MeV and are responsible for carrying away over 99% of the gravitational binding energy of the supernova, provide an opportunity to study the end of life evolution of massive stars, as well as unique properties and interactions of neutrinos. Because galactic supernovae are expected to occur only on the timespan of every few decades, it is crucial that DUNE is able to detect supernova neutrino interactions when they occur. However, detecting these supernova interactions requires sifting through a large amount of data, and DUNE detectors require a trigger to signal when supernova neutrino events occur. Machine learning provides a potential approach to creating this trigger. This project generates ADC and ground truth images of neutrino interactions in a LArTPC detector as simulated by the Model of Argon Reaction Low Energy Yields (MARLEY) to be used for machine learning. The eventual goal of this work is to facilitate DUNE s detection of supernova neutrino interactions by building a machine learning pipeline to train the trigger algorithm.

Damish, Stephanie↗
DOE OSTI2025

AI Benchmark Democratization and Carpentry

Benchmarks are a cornerstone of modern machine learning, enabling reproducibility, comparison, and scientific progress. However, AI benchmarks are increasingly complex, requiring dynamic, AI-focused workflows. Rapid evolution in model architectures, scale, datasets, and deployment contexts makes evaluation a moving target. Large language models often memorize static benchmarks, causing a gap between benchmark results and real-world performance. Beyond traditional static benchmarks, continuous adaptive benchmarking frameworks are needed to align scientific assessment with deployment risks. This calls for skills and education in AI Benchmark Carpentry. From our experience with MLCommons, educational initiatives, and programs like the DOE's Trillion Parameter Consortium, key barriers include high resource demands, limited access to specialized hardware, lack of benchmark design expertise, and uncertainty in relating results to application domains. Current benchmarks often emphasize peak performance on top-tier hardware, offering limited guidance for diverse, real-world scenarios. Benchmarking must become dynamic, incorporating evolving models, updated data, and heterogeneous platforms while maintaining transparency, reproducibility, and interpretability. Democratization requires both technical innovation and systematic education across levels, building sustained expertise in benchmark design and use. Benchmarks should support application-relevant comparisons, enabling informed, context-sensitive decisions. Dynamic, inclusive benchmarking will ensure evaluation keeps pace with AI evolution and supports responsible, reproducible, and accessible AI deployment. Community efforts can provide a foundation for AI Benchmark Carpentry.

von Laszewski, Gregor [Virginia U.]↗
DOE OSTI2025

DeepHyper: A Python Package for Massively Parallel Hyperparameter Optimization in Machine Learning

Machine learning models are increasingly applied across scientific disciplines, yet their effectiveness often hinges on heuristic decisions—such as data transformations, training strategies, and model architectures—that are not learned by the models themselves. Automating the selection of these heuristics and analyzing their sensitivity is crucial for building robust and efficient learning workflows. DeepHyper addresses this challenge by democratizing hyperparameter optimization, providing accessible tools to streamline and enhance machine learning workflows from a laptop to the largest supercomputer in the world. Building on top of hyperparameter optimization, it unlocks new capabilities around ensembles of models for improved accuracy and uncertainty quantification. All of these organized around efficient parallel computing.

ensemble↗
DOE OSTI2026

Steady Spills, Stronger Signals: Machine Learning for Slow Spill Analysis

Particle accelerator experiments rely on stable, consistent proton beams to maximize scientific discovery. This presentation introduces beam spills, duty factor, and beam stability using a meteor shower analogy before exploring how feedback control and machine learning, including recurrent neural networks (RNNs), can analyze spill data, identify patterns, and predict beam behavior. Together, these approaches support beam optimization and improve our understanding of accelerator performance for experiments such as Mu2e.

Prescott, Matthew J. [Fermilab]↗
DOE OSTI2025

Data-Enabled Fusion Technology (Final Scientific/Technical Report)

Advancing Scientific Understanding in Fusion Energy and Machine Learning This research represented a significant step forward in machine learning (ML) applications for fusion energy experiments. The project integrated advanced data-driven modeling, optimization techniques, and artificial intelligence to enhance the predictive capabilities and operational efficiency of plasma-based fusion systems. Specifically, tasks focused on ML-enhanced diagnostics, operator guidance tools, and predictive modeling helped improve the ability to interpret complex fusion experiments. Key areas of advancement included: 1) data-driven plasma control, i.e., using ML algorithms to optimize experimental conditions and classify plasma behaviors based on historical data; 2) spectroscopy and diagnostics, i.e., applying AI models to extract previously inaccessible insights from experimental spectroscopy data; and 3) configuration mapping and operator guidance, i.e., developing a predictive framework to assist scientists in identifying the most effective experimental parameters, reducing reliance on manual adjustments. By refining these ML-driven techniques, the project contributed to the broader scientific community’s understanding of plasma dynamics and fusion energy viability. Technical Effectiveness and Economic Feasibility The methods investigated demonstrated high technical effectiveness, as reflected in milestones assessing the predictive accuracy, performance, and optimization of fusion configurations. The development of an Operator Guidance Tool (OGT), for example, led to more precise control of plasma conditions by learning from experimental data and offering real-time adjustments. From an economic standpoint, DeFT provided: 1) the ability to reduce trial-and-error experimentation, which lowered operational costs; 2) improved data interpretation methods, which enabled more efficient resource allocation in large-scale fusion research projects; and 3) the automation of key diagnostic tasks, which reduced manual labor and human error, increasing overall efficiency. 13 The final assessments of predictive models and optimization strategies demonstrated that these approaches were scalable and could be implemented across multiple fusion energy research programs. Public Benefit and Societal Impact This project contributed directly to the broader goal of achieving sustainable and commercially viable fusion energy, which had profound implications for clean energy production and climate change mitigation. The integration of AI-driven solutions into fusion research: 1) sped up scientific discovery, accelerating progress towards achieving energy breakthroughs; 2) reduced the cost of experimentation, making fusion research more accessible; and 3) provided a framework for future AI applications in high-energy physics, benefiting adjacent fields like space exploration, material science, and renewable energy. Additionally, by fostering collaborations between AI researchers and plasma physicists, this project promoted interdisciplinary innovation that could lead to broader applications beyond fusion research.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2026

Accelerating Structure–Property Relationship Discovery with Multimodal Machine Learning and Self-Driving Microscopy

Microscopy combined with local spectroscopy is widely used to correlate nanoscale structure with functional properties in materials, but conventional measurements rely heavily on human-selected sampling locations and predefined targets, limiting data set diversity and the potential for discovery. Here, we present a framework that integrates autonomous microscopy with dual-novelty deep kernel learning (DN-DKL) for adaptive data acquisition and a dual variational autoencoder (VAE) for representation learning. DN-DKL actively guides the microscopy toward structurally and spectroscopically novel regions, enabling efficient collection of large spectral data sets. Dual-VAE embeds local structures and spectroscopic responses into a shared latent manifold that serves as a structure–property relationship map. We applied this framework for the investigation of halide perovskite films by using conductive atomic force microscopy. The results reveal distinct hysteresis behaviors that are linked to specific nanoscale structural motifs, including grain boundary junction points that show hysteresis under different bias conditions and asymmetric grain boundaries that suppress the charge transport. This framework establishes a general strategy that leverages the complementary strengths of self-driving microscopy, machine learning, and human expertise to accelerate scientific discovery in functional materials.

atomic force microscopy↗
DOE OSTI2026

Universal Workflow Language and Software Enable Geometric Learning and FAIR Scientific Protocol Reporting

Written language and conventional data structures for representing scientific procedures suffer from low process detail, often fail to accurately represent protocols, and lack universality. New strategies for the handling of experimental data are needed to provide viable process information for both humans and machines. In this work, we present the universal workflow language (UWL) and interface (UWLi). UWL is a findable, accessible, interoperable, and reusable (FAIR)-compatible, graph-based data architecture that can capture arbitrary scientific procedures through workflow representation, and UWLi is an accompanying software package for building, manipulating, and interpreting UWL entries. The UWL format was found to be highly effective in identifying deficiencies in the reported process details of high-impact, peer-reviewed scientific journals, and in simulated scenarios, the graph format was shown to be more effective than conventional methods in predictively modeling the outcome of diverse scientific protocols. Implementation of UWL could enable more accurate scientific communication and more impactful process datasets.

14 SOLAR ENERGY↗
DOE OSTI2025

PowerModel-AI: A First On-the-Fly Machine-Learning Predictor for AC Power Flow Solutions

The real-time creation of machine-learning models via active or on-the-fly learning has attracted considerable interest across various scientific and engineering disciplines. These algorithms enable machines to build models autonomously while remaining operational. Through a series of query strategies, the machine can evaluate whether newly encountered data fall outside the scope of the existing training set. In this study, we introduce PowerModel-AI, an end-to-end machine learning software designed to accurately predict AC power flow solutions. We present detailed justifications for our model design choices and demonstrate that selecting the right input features effectively captures load flow decoupling inherent in power flow equations. Our approach incorporates on-the-fly learning, where power flow calculations are initiated only when the machine detects a need to improve the dataset in regions where the model’s suboptimal performance is based on specific criteria. Otherwise, the existing model is used for power flow predictions. This study includes analyses of five Texas A&M synthetic power grid cases, encompassing the 14-, 30-, 37-, 200-, and 500-bus systems. The training and test datasets were generated using PowerModels.jl, an open-source power flow solver/optimizer developed at Los Alamos National Laboratory, NM, USA.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Loss Landscape Analysis for Reliable Quantized ML Models for Scientific Sensing

In this paper, we propose a method to perform empirical analysis of the loss landscape of machine learning (ML) models. The method is applied to two ML models for scientific sensing, which necessitates quantization to be deployed and are subject to noise and perturbations due to experimental conditions. Our method allows assessing the robustness of ML models to such effects as a function of quantization precision and under different regularization techniques -- two crucial concerns that remained underexplored so far. By investigating the interplay between performance, efficiency, and robustness by means of loss landscape analysis, we both established a strong correlation between gently-shaped landscapes and robustness to input and weight perturbations and observed other intriguing and non-obvious phenomena. Our method allows a systematic exploration of such trade-offs a priori, i.e., without training and testing multiple models, leading to more efficient development workflows. This work also highlights the importance of incorporating robustness into the Pareto optimization of ML models, enabling more reliable and adaptive scientific sensing systems.

Baldi, Tommaso [Pisa, Scuola Normale Superiore]↗
NASA NTRS2022

MLtool: Universal Supervised Machine Learning Tool to Model Tabulated Data

Machine Learning (ML) is a subfield of Artificial Intelligence that gives computers the ability to learn from past data without being explicitly programmed. The predictive capabilities of ML models have already been used to facilitate several scientific breakthroughs. However, the practical application of ML is often limited due to the gaps in technical knowledge of its users. The common issue faced by many scientific researchers is the inability to choose the appropriate ML pipelines that are needed to treat real-world data, which is often sparse and noisy. To solve this problem, we have developed an automated Machine Learning tool (MLtool) that includes a set of ML algorithms and approaches to aid scientific researchers. The current version of MLtool is implemented as an object-oriented Python code that is easily extensible. It includes 44 different regression algorithms used to model data. MLtool helps users select the best model for their data, based on the scoring metrics used. Besides regression algorithms, MLtool also includes a suite of pre- and post-processing techniques such as missing value imputation, categorical variable encoding, input feature normalization, uncertainty quantification, exploratory data analysis (EDA), etc. MLtool was tested on several publicly available multi-dimensional data sets and was found capable of making accurate predictions.

Machine learning↗
NASA NTRS2022

MLtool Python Code

Machine Learning (ML) is a subfield of Artificial Intelligence that gives computers the ability to learn from past data without being explicitly programmed. The predictive capabilities of ML models have already been used to facilitate several scientific breakthroughs. However, the practical application of ML is often limited due to the gaps in technical knowledge of its users. The common issue faced by many scientific researchers is the inability to choose the appropriate ML pipelines that are needed to treat real-world data, which is often sparse and noisy. To solve this problem, we have developed an automated Machine Learning tool (MLtool) that includes a set of ML algorithms and approaches to aid scientific researchers. The current version of MLtool is implemented as an object-oriented Python code that is easily extensible. It includes 44 different regression algorithms used to model data. MLtool helps users select the best model for their data, based on the scoring metrics used. Besides regression algorithms, MLtool also includes a suite of pre- and post-processing techniques such as missing value imputation, categorical variable encoding, input feature normalization, uncertainty quantification, exploratory data analysis (EDA), etc. MLtool was tested on several publicly available multi-dimensional data sets and was found capable of making accurate predictions.

Machine Learning↗
DOE OSTI2025

Optical neural engine for solving scientific partial differential equations

Abstract Solving partial differential equations (PDEs) is the cornerstone of scientific research and development. Data-driven machine learning (ML) approaches are emerging to accelerate time-consuming and computation-intensive numerical simulations of PDEs. Although optical systems offer high-throughput and energy-efficient ML hardware, their demonstration for solving PDEs is limited. Here, we present an optical neural engine (ONE) architecture combining diffractive optical neural networks for Fourier space processing and optical crossbar structures for real space processing to solve time-dependent and time-independent PDEs in diverse disciplines, including Darcy flow equation, the magnetostatic Poisson’s equation in demagnetization, the Navier-Stokes equation in incompressible fluid, Maxwell’s equations in nanophotonic metasurfaces, and coupled PDEs in a multiphysics system. We numerically and experimentally demonstrate the capability of the ONE architecture, which not only leverages the advantages of high-performance dual-space processing for outperforming traditional PDE solvers and being comparable with state-of-the-art ML models but also can be implemented using optical computing hardware with unique features of low-energy and highly parallel constant-time processing irrespective of model scales and real-time reconfigurability for tackling multiple tasks with the same architecture. The demonstrated architecture offers a versatile and powerful platform for large-scale scientific and engineering computations.

Tang, Yingheng (ORCID:0009000153622546)↗
DOE OSTI2025

Leveraging structure-informed machine learning for fast steric zipper propensity prediction across whole proteomes

Predicting the amyloid fold and the propensity of peptide segments to adopt amyloid-like structures remain a challenge. However, recent progress has facilitated structure-based prediction of steric zipper propensity and the use of machine learning to accelerate the calculation of predictive models across many scientific areas. Leveraging these advances, we have developed a new approach for rapid proteome-wide assessment of zipper profiles that is informed by four million steric zipper predictions collected over ten years. This collection is used to build a machine learning model capable of rapidly predicting steric zipper propensity, and allowing for the assessment of zippers at both the protein and proteome level. Our predictions show enrichment for zipper forming segments in proteins involved in cell wall reorganization in yeast, highlighting a potential category of interest for experimental characterization. Overall, our predictive model allows for the exploration of amyloid formation across the tree of life and provides a tool for assessment of both novel and designed sequences for zipper density.

Biochemistry & Molecular Biology↗
DOE OSTI2024

End-to-end codesign of Hessian-aware quantized neural networks for FPGAs

Here, we develop an end-to-end workflow for the training and implementation of co-designed neural networks (NNs) for efficient field-programmable gate array (FPGA) hardware. Our approach leverages Hessian-aware quantization of NNs, the Quantized Open Neural Network Exchange intermediate representation, and the hls4ml tool flow for transpiling NNs into FPGA firmware. This makes efficient NN implementations in hardware accessible to nonexperts in a single open sourced workflow that can be deployed for real-time machine-learning applications in a wide range of scientific and industrial settings. We demonstrate the workflow in a particle physics application involving trigger decisions that must operate at the 40-MHz collision rate of the CERN Large Hadron Collider (LHC). Given the high collision rate, all data processing must be implemented on FPGA hardware within the strict area and latency requirements. Based on these constraints, we implement an optimized mixed-precision NN classifier for high-momentum particle jets in simulated LHC proton-proton collisions.

47 OTHER INSTRUMENTATION↗
DOE OSTI2025

Deploying and Tracking Software with NCCS Software Provisioning

The National Center for Computational Sciences (NCCS) at Oak Ridge National Laboratory has a long history of deploying ground-breaking leadership-class supercomputers for the U.S. Department of Energy. The latest in this line of supercomputers is Frontier, the first supercomputer to break the exascale barrier (1018 floating-point operations per second) on the TOP500 list. Frontier serves a wide array of scientific domains, from traditional simulation-based workloads to newer AI and Machine Learning workloads. To best serve the NCCS user community, NCCS uses Spack to deploy a comprehensive software stack of scientific software packages, providing straightforward access to these packages through Lmod Environment Modules. Maintaining a large software stack while also including multiple new compiler releases each year is a very time-consuming task. Additionally, it is not straightforward to provide a software stack alongside existing vendor-provided software such as the HPE/Cray Programming Environment (CPE), and existing CPE, Spack, and Lmod integration does not allow for multiple versions of GPU libraries such as AMD’s ROCm to be used. To address these challenges and shortcomings, NCCS has developed the NCCS Software Provisioning tool (NSP)1, a tool for deploying and monitoring software stacks on HPC systems. NSP allows NCCS to quickly and effectively provision software stacks from the ground up using template-driven recipes and configuration files. NSP is successfully deployed on Frontier and several other NCCS clusters, enabling the NCCS software team to quickly deploy software stacks for newly-released compilers, expand current software offerings, better support GPU-based software, and monitor Lmod module usage to identify unused software packages that can be removed from the software stack. In this work, we discuss the shortcomings of the previous CPE, Spack, and Lmod usage at NCCS, provide further details on the implementation and structure of NSP, then discuss the benefits that NSP provides.

Rentschler, Asa [ORNL] (ORCID:0009000597694743)↗
NASA NTRSDate not supplied

GeoNEX-ML: A Machine Learning System for Geostationary Satellite Imagery

Improved capabilities of earth monitoring satellites are enabling a wide range of studies on the environmental effects of climate change, often leveraging the recent advancements in machine learning. At the same time, the new capabilities, including higher spatial resolution and temporal frequency, are expanding the amount of data generated at exponential rates. Further, a large majority of archived datasets generated by scientific processing is never used. This motivates the development of an efficient machine learning system for end-to-end processing of multi-level satellite datasets, from level 1 top of atmosphere observations to user friendly environmental variables of interest. Using current generation geostationary satellites GOES-16/17 (NOAA/NASA), Himawari-8/9 (JAXA), and GK-2A (Korea), we present an interchangeable set of machine models to perform spectral adjustment, physical model emulation, LEO-GEO emulation, and optical flow in a high performance computing environment. We use these tools to generate consistent virtual observations across sensors, perform atmospheric correction and cloud detection, and estimate land surface temperature and atmospheric winds. This approach aims to improve the robustness of remotely sensed data processing by learning from diverse sets of observations while enabling near real-time and on-demand capabilities.

Geostationary satellites↗
NASA NTRSDate not supplied

Deep Learning System for Efficient Processing of Geostationary Satellite Imagery

Improved capabilities of Earth monitoring satellites are enabling a wide range of studies on the environmental effects of climate change, often leveraging the recent advancements in machine learning. At the same time, the new capabilities, including higher spatial resolution and temporal frequency, are expanding the amount of data generated at exponential rates. Further, a large majority of archived datasets generated by scientific processing is never used. This motivates the development of an efficient machine learning system for end-to-end processing of multi-level satellite datasets, from level 1 top of atmosphere observations to user friendly environmental variables of interest. Using current generation geostationary satellites GOES-16/17 (NOAA/NASA), and Himawari-8/9 (JAXA), we present an interchangeable set of machine models to perform spectral adjustment among sensors, physical model emulation, LEO-GEO emulation, and optical flow in a high performance computing environment. We use these tools on the NASA Earth eXchange (NEX) to generate consistent virtual observations across sensors, perform atmospheric correction and cloud detection, and estimate surface reflectance, surface temperature and atmospheric winds. This approach aims to improve the robustness of remotely sensed data processing by learning from diverse sets of observations while enabling near real-time and on-demand capabilities.

Thomas Vandal↗
DOE OSTI2026

Resolving root causes of experiment discrepancies guided by machine learning

Abstract Scientists rely on accurate experimental data to explain nature and then harness this knowledge for applications addressing human needs. However, discrepancies between experiments of the same observable can impede scientific progress if one does not understand the underlying causes. Here, we developed a process that unravels data discrepancies by first using Bayesian machine learning to relate discrepancies to few of many, potentially biasing metadata features that encode experiment procedures. This machine learning output guides human experts to study discrepancy causes by simulating suspicious aspects of historical experiments or designing modern ones to address open questions. The study findings then lead to rejecting or correcting historical data on firm scientific bases. This process is demonstrated for the energy spectrum of neutrons emitted promptly (<1 ns) after fission of 252 Cf, a trusted nuclear physics Standard. It reduces the spread in experimental 252 Cf spectra by up to a factor of 6.

Neudecker, D. (ORCID:0000000339200627)↗