Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “machine learning optimization”

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 1,765 records · Page 98
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Towards memristor supremacy with novel machine learning algorithms

The von Neumann architecture for current computers is slowly showing signs of limitations, due to the finite bus rate between the RAM (memory) and the CPU (computing unit). In-Memory computing is an alternative to this architecture, which however is still in the early stages of development. Memristors are an analog and classical alternative, as these components can act both as a memory, or as a simple computing unit. When wired together, these can in fact be used for a variety of applications. During the course of our research, we have developed an in-depth experimental understanding of both the limitations and the real possibilities of these devices, and developed automated algorithms for their characterization; at the theoretical level, we have incorporated the experimental features to implement novel analog computing units for specific tasks. We have shown that memristors can tackle QUBO and cubic optimization problems, and exhibit tunneling phenomena.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Benchmarking Operators in Deep Neural Networks for Improving Performance Portability of SYCL

SYCL is a portable programming model for heterogeneous computing, so it is important to obtain reasonable performance portability of SYCL. Towards the goal of better understanding and improving performance portability of SYCL for machine learning workloads, we have been developing benchmarks for basic operators in deep neural networks (DNNs). These operators could be offloaded to heterogeneous computing devices such as graphics processing units (GPUs) to speed up computation. In this paper, we introduce the benchmarks, evaluate the performance of the operators on GPU-based systems, and describe the causes of the performance gap between the SYCL and Compute Unified Device Architecture (CUDA) kernels. We find that the causes are related to the utilization of the texture cache for read-only data, optimization of the memory accesses with strength reduction, use of local memory, and register usage per thread. We hope that the efforts of developing benchmarks for studying performance portability will stimulate discussion and interactions within the community.

Jin, Zheming [ORNL] (ORCID:000000027197780X)↗
DOE OSTI2022

Training data selection for accuracy and transferability of interatomic potentials

Abstract Advances in machine learning (ML) have enabled the development of interatomic potentials that promise the accuracy of first principles methods and the low-cost, parallel efficiency of empirical potentials. However, ML-based potentials struggle to achieve transferability, i.e., provide consistent accuracy across configurations that differ from those used during training. In order to realize the promise of ML-based potentials, systematic and scalable approaches to generate diverse training sets need to be developed. This work creates a diverse training set for tungsten in an automated manner using an entropy optimization approach. Subsequently, multiple polynomial and neural network potentials are trained on the entropy-optimized dataset. A corresponding set of potentials are trained on an expert-curated dataset for tungsten for comparison. The models trained to the entropy-optimized data exhibited superior transferability compared to the expert-curated models. Furthermore, the models trained to the expert-curated set exhibited a significant decrease in performance when evaluated on out-of-sample configurations.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Integrated Design of Ultradurable, Low CO 2 Alternative Binder Systems via Machine Learning

This ARPA-E project developed a machine learning tool to use in formulation design of cementitious binders for concrete having 50% less embodied CO 2 and possessing twice the durability compared to concrete based on ordinary portland cement (OPC) binders. The technical focus was on limestone/calcined clay cement (LC3), the leading replacement for OPC. Here, hierarchical machine learning (HML) was used to model the flowability, set time, strength, and durability of LC3 concrete. This methodology identifies latent variables derived from domain knowledge and empirical models that develop an accurate model for a response surface from small datasets. For the flowability metric, particle packing was a dominant factor, while strength and durability were both strongly determined by the fraction of metakaolin and the water:solids ratio. Under constraints of water:binder ratio, material performance metrics, embodied CO 2 , and cost per tonne of OPC, multi-objective optimization was used to design binders parameterized by the mineral composition replacing OPC, particle size distributions, and water:solids ratio. The trained algorithm was able to predict multiple mixes met these performance criteria, and experimental testing validated the predictions. The model demonstrated here is relevant for North America, where pure kaolin deposits are found broadly. The approach is being taken forward into commercial application by Ansatz AI, a materials informatics company founded by PI Washburn and co-PI Poczos. Through collaborations with the cement and concrete industry, and funding from SBIR programs, a commercial software will be developed in future research.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Evaluating Operators in Deep Neural Networks for Improving Performance Portability of SYCL

SYCL is a portable programming model for heterogeneous computing, so it is important to obtain reasonable performance portability of SYCL. Towards the goal of better understanding and improving performance portability of SYCL for machine learning workloads, we have been developing benchmarks for basic operators in deep neural networks (DNNs). These operators could be offloaded to heterogeneous computing devices such as graphics processing units (GPUs) to speed up computation. In this work, we introduce the benchmarks, evaluate the performance of the operators on GPU-based systems, and describe the causes of the performance gap between the SYCL and Compute Unified Device Architecture (CUDA) kernels. We find that the causes are related to the utilization of the texture cache for read-only data, optimization of the memory accesses with strength reduction, shared local memory accesses, and register usage per thread. We hope that the efforts of developing benchmarks for studying performance portability will stimulate discussion and interactions within the community.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Data-Centric AI and the Open Energy Data Initiative (OEDI)

This presentation emphasizes the critical importance of data-centric AI. The limitations of model-centric AI when dealing with poor or insufficient data are highlighted, and it is illustrated how training models on inaccurate or noisy data leads to suboptimal results. This talk advocates for a hybrid approach that combines a focus on data quality and model parameters to achieve optimal results. The Open Energy Data Initiative (OEDI) is introduced as a valuable resource for obtaining high-quality energy-related datasets, hosting nearly 2,000 publicly accessible datasets, including 99 solar-related datasets, totaling over 2.7 petabytes of data. OEDI's data lakes enable users to query and work with data without extensive transfers. In conclusion, the significance of data-centric AI and adherence to data curation best practices is emphasized, positioning OEDI as a prime source of high-quality data for AI and machine learning in the renewable energy sector.

AI↗
DOE OSTI2025

High-throughput and data-driven search for stable optoelectronic AMSe 3 materials

The rapid advancement in emerging optoelectronic technologies demands highly efficient, affordable, and ecofriendly materials. In this context, ternary chalcogenides, especially ternary selenides, show early promise as a material class due to their stability and remarkable electronic, optical, and transport properties. In this work, we integrate first-principles-based high-throughput computations with machine learning (ML) techniques to predict the thermodynamic stability and optoelectronic properties of 920 valency-satisfied selenide compounds. Through investigating polymorphism, our study reveals the edge-sharing orthorhombic Pnma phase (NH 4 CdCl 3 -type) as the most stable structure for most ternary selenides. High-fidelity supervised ML models are trained and tested to accelerate stability and band gap predictions. These data-driven models pin down the most influential features that dominantly control key material characteristics. The multistep high-throughput computations identify the ternary selenides with optimal direct band gaps, light carrier masses, and strong optical absorption edges. The extensive materials screening considering phase stability, toxicity, and defect tolerance, finally identifies the seven most suitable candidates for photovoltaic applications. Two of these final compounds, SrZrSe 3 and SrHfSe 3 , have already been synthesized in a single-phase form, with the latter showing an optically suitable band gap, aligning well with our findings. The non-adiabatic molecular dynamics reveal sufficiently long photoexcited charge carrier lifetimes (on the order of nanoseconds) in some of these selected selenide materials, indicating their exciting characteristics. Overall, our study suggests a robust in silico framework that can be extended to screen large datasets of various material classes for identifying promising photoactive candidates.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Geo Thermal Cloud: Cloud Fusion of Big Data and Multi-Physics Models using Machine Learning for Discovery, Exploration, and Development of Hidden Geothermal Resources

The project is motivated by the challenges, risks, and costs associated with geothermal exploration and production. Many processes and parameters impacting geothermal conditions are poorly understood. Diverse datasets are available to help characterize subsurface geothermal conditions (public and proprietary; satellite, airborne surveys, vegetation/water sampling, geological, geophysical, etc.). Yet, it is not clear how to properly leverage these datasets for geothermal exploration due to an incomplete understanding of how physical processes impacting subsurface geothermal conditions are represented in these observations. Recent advancements in machine learning (ML) provide great promise to resolve these issues. The tremendous challenges and risks of geothermal exploration and production bring the demand for novel ML methods and tools that can (1) analyze large field datasets, (2) assimilate model simulations (large inputs and outputs), (3) process sparse datasets, (4) perform transfer learning (between sites with different exploratory levels), (5) extract hidden geothermal signatures in the field and simulation data, (6) label geothermal resources and processes, (7) identify high-value data acquisition targets, and (8) guide geothermal exploration and production by selecting optimal exploration, production, and drilling strategies. Our goals and work under Phases 1 and 2 (as proposed) of this project address all these needs.

15 GEOTHERMAL ENERGY↗
DOE OSTI2022

Deep Generative Modeling of Periodic Variable Stars Using Physical Parameters

The ability to generate physically plausible ensembles of variable sources is critical to the optimization of time domain survey cadences and the training of classification models on data sets with few to no labels. Traditional data augmentation techniques expand training sets by reenvisioning observed exemplars, seeking to simulate observations of specific training sources under different (exogenous) conditions. Unlike fully theory-driven models, these approaches do not typically allow principled interpolation nor extrapolation. Moreover, the principal drawback of theory-driven models lies in the prohibitive computational cost of simulating source observables from ab initio parameters. In this work, we propose a computationally tractable machine learning approach to generate realistic light curves of periodic variables capable of integrating physical parameters and variability classes as inputs. Our deep generative model, inspired by the transparent latent space generative adversarial networks, uses a variational autoencoder (VAE) architecture with temporal convolutional network layers, trained using the OGLE-III optical light curves and physical characteristics (e.g., effective temperature and absolute magnitude) from Gaia DR2. A test using the temperature–shape relationship of RR Lyrae demonstrates the efficacy of our generative “physics-enhanced latent space VAE” (PELS-VAE) model. Such deep generative models, serving as nonlinear nonparametric emulators, present a novel tool for astronomers to create synthetic time series over arbitrary cadences.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2024

Missing Wedge Completion via Unsupervised Learning with Coordinate Networks

Cryogenic electron tomography (cryoET) is a powerful tool in structural biology, enabling detailed 3D imaging of biological specimens at a resolution of nanometers. Despite its potential, cryoET faces challenges such as the missing wedge problem, which limits reconstruction quality due to incomplete data collection angles. Recently, supervised deep learning methods leveraging convolutional neural networks (CNNs) have considerably addressed this issue; however, their pretraining requirements render them susceptible to inaccuracies and artifacts, particularly when representative training data is scarce. To overcome these limitations, we introduce a proof-of-concept unsupervised learning approach using coordinate networks (CNs) that optimizes network weights directly against input projections. This eliminates the need for pretraining, reducing reconstruction runtime by 3–20× compared to supervised methods. Our in silico results show improved shape completion and reduction of missing wedge artifacts, assessed through several voxel-based image quality metrics in real space and a novel directional Fourier Shell Correlation (FSC) metric. Our study illuminates benefits and considerations of both supervised and unsupervised approaches, guiding the development of improved reconstruction strategies.

42 ENGINEERING↗
DOE OSTI2023

Navigating the Expansive Landscapes of Soft Materials: A User Guide for High-Throughput Workflows

Synthetic polymers are highly customizable with tailored structures and functionality, yet this versatility generates challenges in the design of advanced materials due to the size and complexity of the design space. Thus, exploration and optimization of polymer properties using combinatorial libraries has become increasingly common, which requires careful selection of synthetic strategies, characterization techniques, and rapid processing workflows to obtain fundamental principles from these large data sets. Herein, we provide guidelines for strategic design of macromolecule libraries and workflows to efficiently navigate these high-dimensional design spaces. We describe synthetic methods for multiple library sizes and structures as well as characterization methods to rapidly generate data sets, including tools that can be adapted from biological workflows. We further highlight relevant insights from statistics and machine learning to aid in data featurization, representation, and analysis. This Perspective acts as a “user guide” for researchers interested in leveraging high-throughput screening toward the design of multifunctional polymers and predictive modeling of structure–property relationships in soft materials.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Machine learned interatomic potential for dispersion strengthened plasma facing components

Tungsten (W) is a material of choice for the divertor material due to its high melting temperature, thermal conductivity, and sputtering threshold. However, W has a very high brittle-to-ductile transition temperature, and at fusion reactor temperatures (≥1000 K), it may undergo recrystallization and grain growth. Dispersion-strengthening W with zirconium carbide (ZrC) can improve ductility and limit grain growth, but much of the effects of the dispersoids on microstructural evolution and thermomechanical properties at high temperatures are still unknown. We present a machine learned Spectral Neighbor Analysis Potential for W–ZrC that can now be used to study these materials. In order to construct a potential suitable for large-scale atomistic simulations at fusion reactor temperatures, it is necessary to train on ab initio data generated for a diverse set of structures, chemical environments, and temperatures. Further accuracy and stability tests of the potential were achieved using objective functions for both material properties and high temperature stability. Additionally, validation of lattice parameters, surface energies, bulk moduli, and thermal expansion is confirmed on the optimized potential. Tensile tests of W/ZrC bicrystals show that although the W(110)–ZrC(111) C-terminated bicrystal has the highest ultimate tensile strength (UTS) at room temperature, observed strength decreases with increasing temperature. At 2500 K, the terminating C layer diffuses into the W, resulting in a weaker W–Zr interface. Meanwhile, the W(110)–ZrC(111) Zr-terminated bicrystal has the highest UTS at 2500 K.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Error mitigation in variational quantum eigensolvers using tailored probabilistic machine learning

Quantum computing technology has the potential to revolutionize the simulation of materials and molecules in the near future. A primary challenge in achieving near-term quantum advantage is effectively mitigating the noise effects inherent in current quantum processing units (QPUs). This challenge is also decisive in the context of quantum-classical hybrid schemes employing variational quantum eigensolvers (VQEs) that have attracted significant interest in recent years. In this paper, we present a method that employs parametric Gaussian process regression (GPR) within an active learning framework to mitigate noise in quantum computations, focusing on VQEs. Our approach, grounded in probabilistic machine learning, exploits a custom prior based on the VQE ansatz to capture the underlying correlations between VQE outputs for different variational parameters, thereby enhancing both accuracy and efficiency. We demonstrate the effectiveness of our method on a two-site Anderson impurity model and a eight-site Heisenberg model, using the IBM open-source quantum computing framework, Qiskit, showcasing substantial improvements in the accuracy of VQE outputs while reducing the number of direct QPU energy evaluations. This paper contributes to the ongoing efforts in quantum-error mitigation and optimization, bringing us a step closer to realizing the potential of quantum computing in quantum matter simulations. Published by the American Physical Society 2024

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Data-Driven and Multiscale Modeling of DNA-Templated Dye Aggregates

Dye aggregates are of interest for excitonic applications, including biomedical imaging, organic photovoltaics, and quantum information systems. Dyes with large transition dipole moments (μ) are necessary to optimize coupling within dye aggregates. Extinction coefficients (ε) can be used to determine the μ of dyes, and so dyes with a large ε (>150,000 M –1 cm –1 ) should be engineered or identified. However, dye properties leading to a large ε are not fully understood, and low-throughput methods of dye screening, such as experimental measurements or density functional theory (DFT) calculations, can be time-consuming. In order to screen large datasets of molecules for desirable properties (i.e., large ε and μ), a computational workflow was established using machine learning (ML), DFT, time-dependent (TD-) DFT, and molecular dynamics (MD). ML models were developed through training and validation on a dataset of 8802 dyes using structural features. A Classifier was developed with an accuracy of 97% and a Regressor was constructed with an R2 of above 0.9, comparing between experiment and ML prediction. Using the Regressor, the ε values of over 18,000 dyes were predicted. The top 100 dyes were further screened using DFT and TD-DFT to identify 15 dyes with a μ relative to a reference dye, pentamethine indocyanine dye Cy5. Two benchmark MD simulations were performed on Cy5 and Cy5.5 dimers, and it was found that MD could accurately capture experimental results. The results of this study exhibit that our computational workflow for identifying dyes with a large μ for excitonic applications is effective and can be used as a tool to develop new dyes for excitonic applications.

77 NANOSCIENCE AND NANOTECHNOLOGY↗
DOE OSTI2025

Machine learning-powered data cleaning for LEGEND: a semi-supervised approach using affinity propagation and support vector machines

Neutrinoless double-beta decay ($0\nu\beta\beta$) is a rare nuclear process that, if observed, will provide insight into the nature of neutrinos and help explain the matter-antimatter asymmetry in the Universe. The large enriched germanium experiment for neutrinoless double-beta decay (LEGEND) will operate in two phases to search for $0\nu\beta\beta$. The first (second) stage will employ 200 (1000) kg of High-Purity Germanium (HPGe) enriched in 76 Ge to achieve a half-life sensitivity of 10 27 (10 28 ) years. In this study, we present a semi-supervised data-driven approach to remove non-physical events captured by HPGe detectors powered by a novel artificial intelligence model. We utilize affinity propagation to cluster waveform signals based on their shape and a support vector machine to classify them into different categories. We train, optimize, and test our model on data taken from a natural abundance HPGe detector installed in the Full Chain Test experimental stand at the University of North Carolina at Chapel Hill. We demonstrate that our model yields a maximum sacrifice of physics events of $0.024 ^{+0.004}_{-0.003} \%$ after data cleaning. Our model is being used to accelerate data cleaning development for LEGEND-200 and will serve to improve data cleaning procedures for LEGEND-1000.

artificial intelligence↗
DOE OSTI2023

Development of an interatomic potential for the W–Ta system

A physics-inspired, data-driven interatomic potential framework for multi-element system is presented. This potential is based on the generalization of the embedded atom method potential and systematically incorporates two-, three- and many-body effects. Different atomic environments are described by atom-centered Gaussian basis sets which provides sufficient flexibility to capture diverse atomic environments and allows for easy optimization of the free parameters. An interatomic potential model for the tungsten–tantalum (W–Ta) system is developed using this framework by training on data from ab initio density functional theory (DFT) calculations. The potential is thoroughly tested at various compositions by comparing bulk and defect properties from experimental and DFT data. It is shown that the potential predicts the elastic constants, defect properties, such as vacancy and interstitial formation energies, core structures of dislocations, and melting points for both pure and tantalum and tungsten with an accuracy comparable to other single element machine learning based potentials. In conclusion, the potential model is used to investigate the formation energies of ordered alloys and vacancy formation energies for chemically random W–Ta alloys.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2023

Accurate Hellmann–Feynman forces from density functional calculations with augmented Gaussian basis sets

The Hellmann–Feynman (HF) theorem provides a way to compute forces directly from the electron density, enabling efficient force calculations for large systems through machine learning (ML) models for the electron density. The main issue holding back the general acceptance of the HF approach for atom-centered basis sets is the well-known Pulay force which, if naively discarded, typically constitutes an error upward of 10 eV/Å in forces. In this work, we demonstrate that if a suitably augmented Gaussian basis set is used for density functional calculations, the Pulay force can be suppressed, and HF forces can be computed as accurately as analytical forces with state-of-the-art basis sets, allowing geometry optimization and molecular dynamics to be reliably performed with HF forces. Our results pave a clear path forward for the accurate and efficient simulation of large systems using ML densities and the HF theorem.

Pathak, Shivesh (ORCID:0000000172798195)↗
DOE OSTI2025

A hybrid neural architecture: Online attosecond x-ray characterization

The emergence of high-repetition-rate x-ray free-electron lasers (XFELs), such as SLAC’s LCLS-II, serves as our canonical example for autonomous controls that necessitate high-throughput diagnostics paired with streaming computational pipelines capable of single-shot analysis with extremely low latency. We present the deterministic characterization with an integrated parallelizable hybrid resolver architecture, a hybrid machine learning framework designed for fast, accurate analysis of XFEL diagnostics using angular streaking-based sinogram images. This architecture integrates convolutional neural networks and bidirectional long short-term memory models to denoise input, identify x-ray sub-spike features, and extract sub-spike relative delays with sub-30 attosecond temporal resolution. Deployed on low-latency hardware, it achieves over 10 kHz throughput with 168.3 μs inference latency, indicating scalability to 14 kHz with field-programmable gate array integration. By transforming regression tasks into classification problems and leveraging optimized error encoding, we achieve high precision with low-latency performance that is critical for real-time streaming event selection and experimental control feedback signals. This represents a key development in real-time control pipelines for next-generation autonomous science, generally, and high repetition-rate x-ray experiments in particular.

Accelerator Physics (physics.acc-ph)↗