Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “AI efficiency”

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 361 records · Page 20
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Coupled Lattice Boltzmann Modeling Framework for Pore-Scale Fluid Flow and Reactive Transport

In this paper, we propose a modeling framework for pore-scale fluid flow and reactive transport based on a coupled lattice Boltzmann model (LBM). We develop a modeling interface to integrate the LBM modeling code parallel lattice Boltzmann solver and the PHREEQC reaction solver using multiple flow and reaction cell mapping schemes. The major advantage of the proposed workflow is the high modeling flexibility obtained by coupling the geochemical model with the LBM fluid flow model. Consequently, the model is capable of executing one or more complex reactions within desired cells while preserving the high data communication efficiency between the two codes. Meanwhile, the developed mapping mechanism enables the flow, diffusion, and reactions in complex pore-scale geometries. We validate the coupled code in a series of benchmark numerical experiments, including 2D single-phase Poiseuille flow and diffusion, 2D reactive transport with calcite dissolution, as well as surface complexation reactions. The simulation results show good agreement with analytical solutions, experimental data, and multiple other simulation codes. In addition, we design an AI-based optimization workflow and implement it on the surface complexation model to enable increased capacity of the coupled modeling framework. Compared to the manual tuning results proposed in the literature, our workflow demonstrates fast and reliable model optimization results without incorporating pre-existing domain knowledge.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2026

Addressing Rising Energy Demand Through Innovation

The U.S. is facing a significant increase in energy demand, driven by AI advancements, the rapid expansion of data centers, manufacturing and industrial growth, and the electrification of transportation and buildings. Buildings alone account for approximately 75% of U.S. electricity consumption and 40% of total energy use. To address these challenges, NLR leverages its state-of-the-art research facilities, advanced energy modeling, hardware-in-the-loop emulation, and real-world demonstrations to provide data-driven insights that de-risk emerging energy solutions, increase efficiency and demand flexibility, optimize grid controls, and identify vulnerabilities to enhance energy security. This presentation will highlight our research ecosystem and its role in supporting a more reliable, affordable, and adaptive energy infrastructure in the face of accelerating demand.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2022

kynema-fmb [SWR-23-07]

Kynema-FMB (FKA: Kynema) is an open-source performance portable flexible multibody (FMB) dynamics solver designed for time-domain simulations. While originally tailored for wind turbine structural dynamics, the formulation and implementation are those of a general flexible-multidbody dynamics solver that can readily be applied to a wide range of systems. Kynema was designed with a narrow focus, namely to provide a lightweight, fast, accurate FMD solver for coupling to computational-fluid-dynamics (CFD) codes, especially the CFD codes in the Kynema suite, for fluid-structure-interaction (FSI) simulations. Kynema-FMB is equipped to model systems that can be represented as a collection of beams and rigid bodies that are connected through constraints. Degrees of freedom are defined in the inertial/global frame of reference and include displacements and rotations (formally as rotation matrices, but stored as quaternions). The underlying formulation is built on a Lie-group time integrator designed for index-3 differential-algebraic equations, which is second-order accurate in time (Bruls et al., 2012). Beam models are based on geometrically exact beam theory and are discretized as high-order spectral finite elements similar to those in BeamDyn (Wang et al., 2017). The governing equations for a FMD system like a wind turbine constitute a highly nonlinear system of constrained partial-differential equations. Kynema-FMB uses analytical Jacobians in the nonlinear-system solves in each time step. Linear systems use sparse storage and several third-party sparse-linear-system solvers are enabled. Ill conditioning of linear systems is mitigated with preconditioning described in Bottasso et al, 2008. Kynema-FMB is integrated with a simple open-source controller (ROSCO). There is an application programming interface (API) for coupling to geometry-resolved CFD (like that in Sharma et al., 2023) and actuator-force CFD (like that in Kuhn et al., 2025). In the latter, for actuator-line models, Kynema-FMB includes an internal blade-element solver that depends on user-provided lookup tables for coefficients of lift and drag, i.e., aerodynamic polars. Kynema-FMB is written in C++ and leverages Kokkos and Kokkos-Kernels (KokkosEcosystem) as its performance portability layer enabling simulations on both CPU and GPU systems. The repository is equipped with extensive automated testing at the unit and regression/system levels. The following describes the high-level development objectives conceived for Kynema: *Kynema will follow modern software development best practices, including test-driven development (TDD), version control, hierarchical automated testing, and continuous integration (CI) for a robust development environment. *The core data structures are memory efficient and enable vectorization and parallelization at multiple levels. *Data structures are data-oriented to exploit methods for accelerated computing including high utilization of chip resources (e.g., single instruction multiple data (SIMD) instruction sets) and parallelization using GP-GPUs. *The computational algorithms incorporate robust open-source libraries for mathematical operations, resource allocation, and data management. *The API design considers multiple stakeholder needs and ensure integration with existing and future ecosystems for data science, machine learning, and AI. *Kynema-FMB is written in modern C++ and leverages Kokkos as its performance-portability library with inspiration from the kynema stack.

Sprague, MichaelA.↗
DOE OSTI2022

Hvac: Removing I/O Bottleneck for Large-Scale Deep Learning Applications

Scientific communities are increasingly adopting deep learning (DL) models in their applications to accelerate scientific discovery processes. However, with rapid growth in the computing capabilities of HPC supercomputers, large-scale DL applications have to spend a significant portion of training time performing I/O to a parallel storage system. Previous research works have investigated optimization techniques such as prefetching and caching. Unfortunately, there exist non-trivial challenges to adopting the existing solutions on HPC supercomputers for large-scale DL training applications, which include non-performance and/or failures at extreme scale, lack of portability and generality in design, complex deployment methodology, and being limited to a specific application or dataset. To address these challenges, we propose High-Velocity AI Cache (HVAC), a distributed read-cache layer that targets and fully exploits the node-local storage or near node-local storage technology. HVAC seamlessly accelerates read I/O by aggregating node-local or near node-local storage, avoiding metadata lookups and file locking while preserving portability in the application code. We deploy and evaluate HVAC on 1,024 nodes (with over 6000 NVIDIA V100 GPUS) of the Summit supercomputer. In particular, we evaluate the scalability, efficiency, accuracy, and load distribution of HVAC compared to GPFS and XFS-on-NVMe. With four different DL applications, we observe an average 25 % performance improvement atop GPFS and 9% drop against XFS-on-NVMe, which scale linearly and are considered the performance upper bound. We envision HVAC as an important caching library for upcoming HPC supercomputers such as Frontier.

Khan, Awais↗
DOE OSTI2025

Certifying almost all quantum states with few single-qubit measurements

Certifying that an n -qubit state synthesized in the laboratory is close to a given target state is a fundamental task in quantum information science. However, existing rigorous protocols applicable to general target states have potentially prohibitive resource requirements in the form of either deep quantum circuits or exponentially many single-qubit measurements. Here we prove that almost all n -qubit target states, including those with exponential circuit complexity, can be certified from only O ( n 2 ) single-qubit measurements. Given access to the target state’s amplitudes, our protocol requires only O ( n 3 ) classical computation. This result is established by a technique that relates certification to the mixing time of a random walk. Our protocol has applications for benchmarking quantum systems, for optimizing quantum circuits to generate a desired target state and for learning and verifying neural networks, tensor networks and various other representations of quantum states using only single-qubit measurements. We show that such verified representations can be used to efficiently predict highly non-local properties of a synthesized state that would otherwise require an exponential number of measurements on the state. We demonstrate these applications in numerical experiments with up to 120 qubits and observe an advantage over existing methods such as cross-entropy benchmarking.

information theory and computation↗
DOE OSTI2022

Large Scale Caching and Streaming of Training Data for Online Deep Learning

The training of deep neural network models on large data remains a difficult problem, despite progress towards scalable techniques. In particular, there is a mismatch between the random but predetermined order in which AI flows select training samples and the streaming I/O patterns for which traditional HPC data storage (e.g., parallel file systems) are designed. In addition, as more data are obtained, it is feasible neither simply to train learning models incrementally, due to catastrophic forgetting (i.e., bias towards new samples), nor to train frequently from scratch, due to prohibitive time and/or resource constraints. In this paper, we study data management techniques that combine caching and streaming with rehearsal support in order to enable efficient access to training samples in both offline training and continual learning. We revisit state-of-art streaming approaches based on data pipelines that transparently handle prefetching, caching, shuffling, and data augmentation, and discuss the challenges and opportunities that arise when combining these methods with data-parallel training techniques. We also report on preliminary experiments that evaluate the I/O overheads involved in accessing the training samples from a parallel file system (PFS) under several concurrency scenarios, highlighting the impact of the PFS on the design of the data pipelines.

data pipelines↗
DOE OSTI2025

Light-powered end-to-end neutron detection and imaging with an edge-deployed optical AI chip

Neutron detection is widely used in many applications including nuclear physics, nuclear energy, nuclear technologies and nuclear safeguards. Developing an end-to-end neutron detection and imaging workflow paves way towards fully automated processes for many applications. We implemented an automated workflow for neutron detection experiments which use a solid state image sensor to capture neutron hits as a digital image. We deploy the workflow to an edge-based optical neural network (ONN) to increase the radiation-hardness and lifetime of neutron detection instruments. We present a two-stage neural network framework for detection of neutrons at sub-pixel resolution. The first stage uses a region proposal network to efficiently detect and extract neutron hits from the input camera image. The second stage feeds the extracted hits into a fully connected neural network to predict the sub-pixel hit position. The performance of the two-stage framework is evaluated using the edge-based ONN. The results show that we can achieve above 96% neutron detection accuracy as well as sub-pixel and sub-micron position resolution, while enjoying the advantages of the ONN hardware including radiation-hardness, low energy consumption and high computing speed for integrated edge camera and hardware deployment, when compared with electronic counterparts.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

Integrated edge-to-exascale workflow for real-time steering in neutron scattering experiments

We introduce a computational framework that integrates artificial intelligence (AI), machine learning, and high-performance computing to enable real-time steering of neutron scattering experiments using an edge-to-exascale workflow. Focusing on time-of-flight neutron event data at the Spallation Neutron Source, our approach combines temporal processing of four-dimensional neutron event data with predictive modeling for multidimensional crystallography. At the core of this workflow is the Temporal Fusion Transformer model, which provides voxel-level precision in predicting 3D neutron scattering patterns. The system incorporates edge computing for rapid data preprocessing and exascale computing via the Frontier supercomputer for large-scale AI model training, enabling adaptive, data-driven decisions during experiments. This framework optimizes neutron beam time, improves experimental accuracy, and lays the foundation for automation in neutron scattering. Although real-time experiment steering is still in the proof-of-concept stage, the demonstrated potential of this system offers a substantial reduction in data processing time from hours to minutes via distributed training, and significant improvements in model accuracy, setting the stage for widespread adoption across neutron scattering facilities and more efficient exploration of complex material systems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Exploring Advanced Computational Tools and Techniques with Artificial Intelligence and Machine Learning in Operating Nuclear Plants

This report presents the project Idaho National Laboratory conducted for Nuclear Regulatory Commission to explore the advanced computational tools and techniques, such as artificial intelligence (AI) and machine learning (ML), for operating nuclear plants. The report reviews the nuclear data sources, with the focus on the operating experience data, that could be applied by advanced computational tools and techniques. Plant-specific and generic (national and international) data from different sources are described. The report describes the relationships between statistics and AI/ML and then introduces the most widely used AI/ML algorithms in both supervised and unsupervised learning. The report reviews the recent applications of advanced computational tools and techniques in various fields of nuclear industry, such as reactor system design and analysis, plant operation and maintenance, and nuclear safety and risk analysis. Finally, the report presents the insights from the project on the potential applicability of AI/ML techniques in improving advanced computational capabilities, how the advanced tools and techniques could contribute to the understanding of safety and risk, and what information would be needed to provide meaningful insights to decision makers. The report also documents an NRC survey on the current state of commercial nuclear power operations relative to the use of AI and ML tools as well as the role of AI/ML tools in nuclear power operations was published by the NRC as in FRN NRC-2021-0048 in April 2021. A summary of the survey including the survey questions, survey participants, survey responses, and the conclusions and insights derived from the survey is provided in the report. Finally, the report investigates potential applications of using AI/ML in operating NPPs and advanced reactors (both advanced LWRs and advanced NLWRs) to improve nuclear plant safety and efficiency. Three main application fields are defined and discussed: (1) plant safety and security assessments; (2) plant degradation modeling, fault and accident diagnosis and prognosis; and (3) plant operation and maintenance efficiency improvement.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2025

Developing and Distributing HEP Software Stacks with Spack

The Computational Science and AI Directorate at Fermilab is using Spack to support the development efforts of a large number of scientific programmers, in many independent projects and experiments. While independent, these projects share many dependencies. They are typically under continuous and fairly rapid development. They have to support deployment on diverse hardware. This is a different context than is typical for the management of HPC software, where Spack was born. To support our community, we have created a model that enables users to develop code with greater efficiency than is possible with Spack’s current development facilities. In this talk we will present: - a brief introduction to the science we support (particle physics) - how the code we work with is naturally organized into several layers of packages - how we are using Spack to manage those layers - how we leverage the layering to provide efficient support for developers, using our Spack extension “MPD”. - some suggestions for changes or additions to Spack to make such work easier.

Knoepfel, Kyle J. [Fermilab]↗
DOE OSTI2026

Score-based deterministic density sampling

We propose a deterministic sampling framework using Score-Based Transport Modeling for sampling an unnormalized target density π given only its score ∇ log π. Our method approximates the Wasserstein gradient flow on KL($f_t$∥π) by learning the time-varying score ∇ log $f_t$ on the fly using score matching. While having the same marginal distribution as Langevin dynamics, our method produces smooth deterministic trajectories, resulting in monotone noise-free convergence. We prove that our method dissipates relative entropy at the same rate as the exact gradient flow, provided sufficient training. Numerical experiments validate our theoretical findings: our method converges at the optimal rate, has smooth trajectories, and is often more sample efficient than its stochastic counterpart. Experiments on high-dimensional image data show that our method produces high-quality generations in as few as 15 steps and exhibits natural exploratory behavior. The memory and runtime scale linearly in the sample size.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

SimLBR: Learning to Detect Fake Images by Learning to Detect Real Images

The rapid advancement of generative models has made the detection of AI-generated images a critical challenge for both research and society. Recent works have shown that most state-of-the-art fake image detection methods overfit to their training data and catastrophically fail when evaluated on curated hard test sets with strong distribution shifts. In this work, we argue that it is more principled to learn a tight decision boundary around the real image distribution and treat the fake category as a sink class. To this end, we propose SimLBR, a simple and efficient framework for fake image detection with Latent Blending Regularization (LBR). Our method significantly improves cross-generator generalization, achieving up to +24.85% accuracy and +69.62% recall on the challenging Chameleon benchmark. SimLBR is also highly efficient, training orders of magnitude faster than existing approaches. Furthermore, we emphasize the need for reliability-oriented evaluation in fake image detection, introducing risk-adjusted metrics and worst-case estimates to better assess model robustness. All the code and models are availabe at: https://github.com/mvrl/SimLBR

Dhakal, Aayush [Washington University, St. Louis]↗
DOE OSTI2022

Foundation Models of Scientific Knowledge for Chemistry: Opportunities, Challenges and Lessons Learned

Foundation models pre-trained on large corpora demonstrate significant gains across many natural language processing tasks and domains e.g., law, healthcare, education, etc. However, only limited efforts have investigated the opportunities and limitations of applying these powerful models to science and security applications. In this work we develop foundation models of scientific knowledge for chemistry to augment scientists with the advanced ability to perceive and reason at scale previously unimagined. Specifically, we build large-scale (1.47B parameter) general-purpose models for chemistry that can be effectively used to perform a wide range of in-domain and out-of-domain tasks. Evaluating these models in a zero-shot setting, we analyze the effect of model and data scaling, knowledge depth, and temporality on model performance in context of model training efficiency. Our novel findings demonstrate that (1) model size significantly contributes to the task performance when evaluated in a zero-shot setting; (2) data quality (aka diversity) affects model performance more than data quantity; (3) similarly, unlike previous work (Luu et al., 2021) temporal order of the documents in the corpus boosts model performance only for specific tasks, e.g., SciQ; and (4) models pre-trained from scratch perform better on in-domain tasks than those tuned from general-purpose models like Open AI’s GPT-2.

Foundation Models, Chemistry↗
DOE OSTI2023

A Search for Technosignatures Around 11,680 Stars with the Green Bank Telescope at 1.15–1.73 GHz

We conducted a search for narrowband radio signals over four observing sessions in 2020–2023 with the $L$-band receiver (1.15–1.73 GHz) of the 100 m diameter Green Bank Telescope. We pointed the telescope in the directions of 62 TESS Objects of Interest, capturing radio emissions from a total of ~11,680 stars and planetary systems in the ~9' beam of the telescope. All detections were either automatically rejected or visually inspected and confirmed to be of anthropogenic nature. We also quantified the end-to-end efficiency of radio SETI pipelines with a signal injection and recovery analysis. The UCLA SETI pipeline recovers 94.0% of the injected signals over the usable frequency range of the receiver and 98.7% of the injections when regions of dense radio frequency interference are excluded. In another pipeline that uses incoherent sums of 51 consecutive spectra, the recovery rate is ~15 times smaller at ~6%. The pipeline efficiency affects calculations of transmitter prevalence and SETI search volume. Accordingly, we developed an improved Drake figure of merit and a formalism to place upper limits on transmitter prevalence that take the pipeline efficiency and transmitter duty cycle into account. Based on our observations, we can state at the 95% confidence level that fewer than 6.6% of stars within 100 pc host a transmitter that is continuously transmitting a narrowband signal with an equivalent isotropic radiated power (EIRP) > 10 13 W. For stars within 20,000 ly, the fraction of stars with detectable transmitters (EIRP > 5 × 10 16 W) is at most 3 × 10 -4 . Finally, we showed that the UCLA SETI pipeline natively detects the signals detected with AI techniques by Ma et al.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

Energy Efficient Mobility Systems (2022 Annual Progress Report)

DOE conducts research to understand how the changing mobility landscape will affect transportation energy consumption and identifies opportunities to create more efficient, affordable, reliable, accessible, equitable, and secure transportation options that enhance mobility for individuals and businesses. Within EERE, the EEMS Program is responsible for this research portfolio. This APR describes work that the EEMS Program conducted during FY 2022 in support of the EEMS Program goals.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2026

Optimizing enzymes for plastic upcycling using machine learning design and high throughput experiments

Plastic use is ubiquitous in the modern world, and polyethylene terephthalate (PET) is one of the most abundantly produced plastics (and the most highly produced polyester), with ~65 million metric tons manufactured annually. To the consumer, PET is likely most recognizable as the plastic used to make beverage bottles. Like many plastics, traditional mechanical or chemical means of PET deconstruction and upcycling are costly and inefficient. Because of these challenges, recycled plastic is generally of lower quality and is more expensive to produce than virgin plastic derived from petroleum. Ultimately, this results in most plastic ending up as waste. We view plastic waste as an underutilized resource which, with the development of more efficient and high-quality recycling processes, could (1) generate significant economic value while (2) decreasing petroleum usage and greenhouse gas emissions, as well as (3) minimizing its negative environmental and health impacts. Biocatalytic recycling, or biomanufacturing the basic building blocks of new plastic from plastic waste, is a promising approach to plastic reuse that complements existing recycling technologies. Recently, biological enzymes capable of breaking down PET have garnered significant attention as an attractive means of dealing with the plastic problem. These enzymes are currently undergoing pilot studies for implementation in industrial-scale enzyme-based recycling. However, there are significant limitations to current enzymes, including the need to perform costly pre-processing of the plastic waste before the enzymes are able to work. Further optimization of these enzymes is necessary to make these technologies competitive, and ultimately incentivise industry-wide adoption of this biology-based green recycling technology. n this work we demonstrate a means to design and generate performant biological enzymes, capable of efficiently deconstructing plastic waste. Specifically, we applied recent advances in artificial intelligence, machine learning, and statistical analysis to design new versions and discover natural enzymes capable of breaking down PET. We focused on optimizing key properties that are important for industrial-scale enzymatic recycling such as pH and thermotolerance. Normal testing of enzymatic plastic-deconstruction is extremely labor intensive and so through this work we also developed a robotic-assisted experimental pipeline capable of characterizing thousands of candidate enzymes. The results of this iterative, AI-guided, multi-discipline approach have led to increases in enzymatic breakdown of over 150X over starting enzymes. This work supports the rapidly developing and transformative field of biocatalytic solutions to environmental problems beyond the discovery and predictive understanding of enzymes for polymer recycling, and has wide implications for tackling numerous energy problems such as carbon capture and fixation (e.g., engineering carbon monoxide dehydrogenase and the rubisco-pathway), biomining (e.g., design of lanthanide-binding proteins) and biomanufacturing (e.g., lignin-deconstruction enzymes).

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2025

Fast and robust strategies for large-scale mixed-integer SCOPF

This project develops scalable, computationally efficient algorithms to solve realistic large-scale power system optimization problems, including systems with more than 8,000 buses, as part of a larger series of competitions run by ARPA-E. These problems are critical because the secure and reliable operation of the power grid is becoming increasingly challenging, especially under conditions of increased uncertainty and variability. The economic feasibility of our methods is high, given that they are purely software-based solutions designed to operate power grids more efficiently. The technical effectiveness balances heuristics and approximations to provide a trade-off between speed and accuracy.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2026

Managing autonomous materials labs with multi-agent AI and its implications for the science of science

Self-driving lab systems (aka, autonomous experimentation) accelerate research - letting scientists learn faster, spend less resources, and fail smarter in well defined, narrow studies. The next-generation materials lab combines self-driving systems to tackle broader challenges - orchestrating complex research campaigns while optimizing lab resources. We propose that agent-based and agentic artificial intelligence will be an integral part of next-generation lab management and discuss potential implementation scenarios. Additionally, digital and physical sandboxes will allow scientists to evaluate diverse and dynamic research and lab management strategies. Beyond the immediate benefit to lab optimization, such sandboxes will enable realistic computational studies of the philosophy of science (i.e., science of science) to achieve higher level scientific efficiencies.

Computer science↗