Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “learning 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 1,369 records · Page 76

Public Discourse in Energy Policy Decision-Making: Final Report

The ground is littered with projects that failed because of strong public opposition, including natural gas and coal power plants proposed in Idaho over the past several years. This joint project , of the Idaho National Laboratory, Boise State University, Idaho State University and University of Idaho has aimed to add to the tool box to reduce project risk through encouraging the public to engage in more critical thought and be more actively involved in public or social issues. Early in a project, project managers and decision-makers can talk with no one, pro and con stakeholder groups, or members of the public. Experience has shown that talking with no one outside of the project incurs high risk because opposition stakeholders have many means to stop most (if not all) energy projects. Talking with organized stakeholder groups provides some risk reduction from mutual learning, but organized groups tend not to change positions except under conditions of a negotiated settlement. Achieving a negotiated settlement may be impossible. Furthermore, opposition often arises outside pre-existing groups. Standard public polling provides some information but does not reveal underlying motivations, intensity of attitudes, etc. Improved methods are needed that probe deeper into stakeholder (organized groups and members of the public) values and beliefs/heuristics to increase the potential for change of opinions and/or out-of-box solutions. The term “heuristics” refers to the mental short-cuts, underlying beliefs, and paradigms that everyone uses to filter and interpret information, to interpret what is around us, and to guide our actions and decisions. This document is the final report of a 3-year effort to test different public discourse methods in the subject area of energy policy decision-making. We analyzed 504 mail-in surveys and 80 participants in groups on the Boise State University campus for their preference, financial support, and evaluations of eight attributes for energy conservation and efficiency, fossil fuels, nuclear energy, hydropower, and renewable energy. All participants saw a 7-person diverse energy expert panel. Some participants attended deliberation sessions; some received a 35-page briefing document that included pros and cons of the different energy options.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Establishing Building-Level Energy Goals in Procurement Documents: Lessons Learned from Pilot Utility and Portfolio Projects

Encouraging commercial building owners to set measurable energy goals before design begins can drive design and contractor teams to develop innovative energy efficiency solutions within conventional building budgets. A federal building owner piloted this technique and created a large-scale zero energy office building on a budget comparable to local market construction rates. The successes and lessons learned from this performance-based procurement project formed the basis of an expanded program using utilities as the outreach channel to replicate the approach. The utilities delivered incentive-based offerings to focus building owners on the whole building rather than on individual building components and systems. In addition, a ripple effect was evident, with individual building owners as well as owners of multiple-building portfolios adopting the techniques, sometimes with variations, but always maintaining the same core principles. The original performance-based procurement process and its successful implementation in a federal building project informed all these efforts. Those successes and lessons learned demonstrate that the approach can be adapted to utility programs with some variation and is a powerful tool for engaging building owners as they make critical design decisions that impact energy performance over the life of the building.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

A survey of numerical linear algebra methods utilizing mixed-precision arithmetic

The efficient utilization of mixed-precision numerical linear algebra algorithms can offer attractive acceleration to scientific computing applications. Especially with the hardware integration of low-precision special-function units designed for machine learning applications, the traditional numerical algorithms community urgently needs to reconsider the floating point formats used in the distinct operations to efficiently leverage the available compute power. In this study, we provide a comprehensive survey of mixed-precision numerical linear algebra routines, including the underlying concepts, theoretical background, and experimental results for both dense and sparse linear algebra problems.

97 MATHEMATICS AND COMPUTING↗

A Future with Quantum Machine Learning

Could combining quantum computing and machine learning with Moore's law produce a true “rebooted computer”? Furthermore, this article posits that a three-technology hybrid-computing approach might yield sufficiently improved answers to a broad class of problems such that energy efficiency will no longer be the dominant concern.

97 MATHEMATICS AND COMPUTING↗

MaLTESE: Large-Scale Simulation-Driven Machine Learning for Transient Driving Cycles

Optimal engine operation during a transient driving cycle is the key to achieving greater fuel economy, engine efficiency, and reduced emissions. In order to achieve continuously optimal engine operation, engine calibration methods use a combination of static correlations obtained from dynamometer tests for steady-state operating points and road and/or track performance data. As the parameter space of control variables, design variable constraints, and objective functions increases, the cost and duration for optimal calibration become prohibitively large. In order to reduce the number of dynamometer tests required for calibrating modern engines, a large-scale simulation-driven machine learning approach is presented in this work. A parallel, fast, robust, physics-based reduced-order engine simulator is used to obtain performance and emission characteristics of engines over a wide range of control parameters under various transient driving conditions (drive cycles). We scale the simulation up to 3,906 nodes of the Theta supercomputer at the Argonne Leadership Computing Facility to generate data required to train a machine learning model. The trained model is then used to predict various engine parameters of interest, and the results are compared with those predicted by the engine simulator. Our results show that a deepneural-network-based surrogate model achieves high accuracy: Pearson product-moment correlation values larger than 0.99 and mean absolute percentage error within 1.07% for various engine parameters such as exhaust temperature, exhaust pressure, nitric oxide, and engine torque. Once trained, the deep-neural-network-based surrogate model is fast for inference: it requires about 16 mu s for predicting the engine performance and emissions for a single design configuration compared with about 0.5 s per configuration with the engine simulator. Moreover, we demonstrate that transfer learning and retraining can be leveraged to incrementally retrain the surrogate model to cope with new configurations that fall outside the training data space.

deep learning↗

Machine Learning‐Guided Discovery of High‐Entropy Perovskite Oxide Electrocatalysts via Oxygen Vacancy Engineering

Abstract High‐entropy perovskite oxides (HEPOs) have recently emerged as multifunctional catalysts. However, the HEPOs’ structural and compositional complexity hinders the easy and accurate extrapolation of activity indicators, which are essential for establishing structure‐property correlations. Here, OxiGraphX, is introduced as a novel graph neural network (GNN) model designed to capture the complex relationships among structure, composition, and atomic chemical environments for accurate prediction of oxygen vacancy formation energies (OVFEs) in HEPOs. By integrating machine learning (ML), density functional theory (DFT), and experimental validation, this work demonstrates an efficient framework for rapidly and accurately screening HEPO electrocatalysts for oxygen evolution reaction (OER). The OxiGraphX predicts OVFEs with a precision exceeding existing data, enabling the identification of compositions of higher oxygen vacancy content (OVC) and, thus, higher catalytic activity. Furthermore, the model explores latent spaces that translate effectively into experimental domains, bridging computational predictions with real‐world applications. This approach accelerates the discovery of high‐performance HEPO catalysts while providing deeper insights into their catalytic mechanisms.

Chemistry↗

Volumetric Data Exploration with Machine Learning-Aided Visualization in Neutron Science

Recent advancements in neutron and X-ray sources, instrumentation and data collection modes have significantly increased the experimental data size (which could easily contain 108–1010 data points), so that conventional volumetric visualization approaches become inefficient for both still imaging and interactive OpenGL rendition in a 3D setting. We introduce a new approach based on the unsupervised machine learning algorithm, Density-Based Spatial Clustering of Applications with Noise (DBSCAN), to efficiently analyze and visualize large volumetric datasets. Here we present two examples of analyzing and visualizing datasets from the diffuse scattering experiment of a single crystal sample and the tomographic reconstruction of a neutron scanning of a turbine blade. We found that by using the intensity as the weighting factor in the clustering process, DBSCAN becomes very effective in de-noising and feature/boundary detection, and thus enables better visualization of the hierarchical internal structures of the neutron scattering data.

Hui, Yawei↗

Prospective Study on Total Fluoroscopic Time in Patients Undergoing Uterine Artery Embolization: Comparing Transradial and Transfemoral Approaches

Purpose: Comparing total fluoroscopy time (FT) to perform uterine artery embolization (UAE) with transradial approach (TRA) versus transfemoral approach (TFA). Our hypothesis was that there would be no significant procedural time penalty incurred, despite the learning curve associated with adopting a new approach. Materials and Methods: A cohort study was undertaken including 66 consecutive patients undergoing UAE with either TRA/TFA between January and September 2015. Total FT was recorded prospectively for each procedure, and data subsequently analyzed retrospectively. Each operator had at least 2 years of experience as an interventional radiologist having performed at least 200 TFA UAEs. All operators had recently incorporated TRA into their practice. Results: A total of 39 TFA and 27 TRA cases were included in the study; mean age for TFA group was 44.4 years (± 4.9) and for TRA group was 45.1 years (± 4.9) (p = 0.59). Mean FTs were comparable between the two groups (p = 0.86) despite a learning curve associated with TRA: The mean total FT with TFA was 20.36 min (± 9.48) compared to TRA 20.12 min (± 7.67). Conclusions: FTs for TRA UAE were comparable to TFA UAE, even though TRA had been recently adopted as a new approach. Despite the learning curve associated with developing a novel technique, operators should not expect the efficiency of their service to be significantly compromised. Introducing this safe and effective method of vascular access should therefore be considered.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Non-intrusive reduced-order modeling for dynamical systems with spatially localized features

This work presents a non-intrusive reduced-order modeling framework for dynamical systems with spatially localized features characterized by slow singular value decay. The proposed approach builds upon two existing methodologies for reduced and full-order non-intrusive modeling, namely Operator Inference (OpInf) and sparse Full-Order Model (sFOM) inference. We decompose the domain into two complementary subdomains that exhibit fast and slow singular value decay. The dynamics of the subdomain exhibiting slow singular value decay are learned with sFOM while the dynamics with intrinsically low dimensionality on the complementary subdomain are learned with OpInf. The resulting, coupled OpInf-sFOM formulation leverages the computational efficiency of OpInf and the high resolution of sFOM, and thus enables fast non-intrusive predictions for conditions beyond those sampled in the training data set. A novel regularization technique with a closed-form solution based on the Gershgorin disk theorem is introduced to promote stable sFOM and OpInf models. We also provide a data-driven indicator for subdomain selection and ensure solution smoothness over the interface via a post-processing interpolation step. We evaluate the efficiency of the approach in terms of offline and online speedup through a quantitative, parametric computational cost analysis. We demonstrate the coupled OpInf-sFOM formulation for two test cases: a one-dimensional Burgers’ model for which accurate predictions beyond the span of the training snapshots are presented, and a two-dimensional parametric model for the Pine Island Glacier ice thickness dynamics, for which the OpInf-sFOM model achieves an average prediction error on the order of 1% with an online speedup factor of approximately 8$\times$ compared to the numerical simulation.

42 ENGINEERING↗

HTESP (High-throughput electronic structure package): A package for high-throughput ab initio calculations

High-throughput ab initio calculations are the indispensable parts of data-driven discovery of new materials with desirable properties, as reflected in the establishment of several online material databases. The accumulation of extensive theoretical data through computations enables data-driven discovery by constructing machine learning and artificial intelligence models to predict novel compounds and forecast their properties. Efficient usage and extraction of data from these existing online material databases can accelerate the next stage materials discovery that targets different and more advanced properties, such as electron–phonon coupling for phonon-mediated superconductivity. However, extracting data from these databases, generating tailored input files for different ab initio calculations, performing such calculations, and analyzing new results can be demanding tasks. Here, in this work, we introduce a software package named “HTESP” (High-Throughput Electronic Structure Package) written in Python and Bash languages, which automates the entire workflow including data extraction, input file generation, calculation submission, result collection and plotting. Our HTESP will help speed up future computational materials discovery processes.

36 MATERIALS SCIENCE↗

Davis Computational Spectroscopy Workflow—From Structure to Spectra

Here, we describe an automated workflow that connects a series of atomic simulation tools to investigate the relationship between atomic structure, lattice dynamics, materials properties, and inelastic neutron scattering (INS) spectra. Starting from the atomic simulation environment (ASE) as an interface, we demonstrate the use of a selection of calculators, including density functional theory (DFT) and density functional tight binding (DFTB), to optimize the structures and calculate interatomic force constants. We present the use of our workflow to compute the phonon frequencies and eigenvectors, which are required to accurately simulate the INS spectra in crystalline solids like diamond and graphite as well as molecular solids like rubrene. We have also implemented a machine-learning force field based on Chebyshev polynomials called the Chebyshev interaction model for efficient simulation (ChIMES) to improve the accuracy of the DFTB simulations. We then explore the transferability of our DFTB/ChIMES models by comparing simulations derived from different training sets. We show that DFTB/ChIMES demonstrates ~100× reduction in computational expense while retaining most of the accuracy of DFT as well as yielding high accuracy for different materials outside of our training sets. The DFTB/ChIMES method within the workflow expands the possibilities to use simulations to accurately predict materials properties of increasingly complex structures that would be unfeasible with ab initio methods.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Core microbiomes for sustainable agroecosystems

In an era of ecosystem degradation and climate change, maximizing microbial functions in agroecosystems has become a prerequisite for the future of global agriculture. Furthermore, managing species-rich communities of plant-associated microbiomes remains a major challenge. Here, we propose interdisciplinary research strategies to optimize microbiome functions in agroecosystems. Informatics now allows us to identify members and characteristics of ‘core microbiomes’, which may be deployed to organize otherwise uncontrollable dynamics of resident microbiomes. Integration of microfluidics, robotics and machine learning provides novel ways to capitalize on core microbiomes for increasing resource-efficiency and stress-resistance of agroecosystems.

60 APPLIED LIFE SCIENCES↗

Machine learning predictions of high-Curie-temperature materials

Technologies that function at room temperature often require magnets with a high Curie temperature, $T$ C , and can be improved with better materials. Discovering magnetic materials with a substantial $T$ C is challenging because of the large number of candidates and the cost of fabricating and testing them. Using the two largest known datasets of experimental Curie temperatures, we develop machine-learning models to make rapid $T$ C predictions solely based on the chemical composition of a material. We train a random-forest model and a k -NN one and predict on an initial dataset of over 2500 materials and then validate the model on a new dataset containing over 3000 entries. The accuracy is compared for multiple compounds' representations (“descriptors”) and regression approaches. A random-forest model provides the most accurate predictions and is not improved by dimensionality reduction or by using more complex descriptors based on atomic properties. Further, a random-forest model trained on a combination of both datasets shows that cobalt-rich and iron-rich materials have the highest Curie temperatures for all binary and ternary compounds. An analysis of the model reveals systematic error that causes the model to over-predict low-$T$ C materials and under-predict high-$T$ C materials. For exhaustive searches to find new high-$T$ C materials, analysis of the learning rate suggests either that much more data is needed or that more efficient descriptors are necessary.

36 MATERIALS SCIENCE↗

APSO-enhanced algebraic derivative estimation approach for real-time traffic flow prediction on critical road sections during wildfire evacuation

In rapid-onset disaster scenarios such as wildfires, evacuation traffic often significantly deviates from historical patterns, rendering conventional data-driven forecasting methods less effective. To address this challenge, we propose an improved algebraic derivative estimation (ADE) incorporating particle swarm optimization (PSO) for real-time traffic flow prediction. Our approach dynamically adjusts the ADE prediction time window at each step by minimizing a cost function based on the mean and variance of accumulated forecasting errors within the window, thereby balancing bias and variability. We evaluate the method using traffic data from the January 2025 California wildfires, focusing on key road segments critical for large-scale evacuations. The results demonstrate that our approach surpasses established machine learning and deep learning models—XGBoost, LSTM, and GRU—in predictive accuracy and maintains high computational efficiency. Notably, the proposed method eliminates the need for offline model training. Moreover, rapid PSO-based tuning enables real-time deployment, which provides a crucial advantage in scenarios where evacuation timings and road closures change dynamically. In conclusion, these findings highlight the benefits of the PSO-enhanced ADE framework for emergency traffic management, where rapid, data-sparse forecasts are essential for effective evacuation planning.

Algebraic derivative estimation↗

DISCOVERY OF BRIGHT GALACTIC R CORONAE BOREALIS AND DY PERSEI VARIABLES: RARE GEMS MINED FROM ACVS

We present the results of a machine-learning (ML)-based search for new R Coronae Borealis (RCB) stars and DY Persei-like stars (DYPers) in the Galaxy using cataloged light curves from the All-Sky Automated Survey (ASAS) Catalog of Variable Stars (ACVS). RCB stars-a rare class of hydrogen-deficient carbon-rich supergiants-are of great interest owing to the insights they can provide on the late stages of stellar evolution. DYPers are possibly the low-temperature, low-luminosity analogs to the RCB phenomenon, though additional examples are needed to fully establish this connection. While RCB stars and DYPers are traditionally identified by epochs of extreme dimming that occur without regularity, the ML search framework more fully captures the richness and diversity of their photometric behavior. We demonstrate that our ML method can use newly discovered RCB stars to identify additional candidates within the same data set. Our search yields 15 candidates that we consider likely RCB stars/DYPers: new spectroscopic observations confirm that four of these candidates are RCB stars and four are DYPers. Our discovery of four new DYPers increases the number of known Galactic DYPers from two to six; noteworthy is that one of the new DYPers has a measured parallax and is m Almost-Equal-To 7 mag, making it the brightest known DYPer to date. Future observations of these new DYPers should prove instrumental in establishing the RCB connection. We consider these results, derived from a machine-learned probabilistic classification catalog, as an important proof-of-concept for the efficient discovery of rare sources with time-domain surveys.

79 ASTRONOMY AND ASTROPHYSICS↗

A deep-learning based raw waveform region-of-interest finder for the liquid argon time projection chamber

The liquid argon time projection chamber (LArTPC) detector technology has an excellent capability to measure properties of low-energy neutrinos produced by the sun and supernovae and to look for exotic physics at very low energies. In order to achieve those physics goals, it is crucial to identify and reconstruct signals in the waveforms recorded on each TPC wire. In this work, we report on a novel algorithm based on a one-dimensional convolutional neural network (CNN) to look for the region-of-interest (ROI) in raw waveforms. We test this algorithm using data from the ArgoNeuT experiment in conjunction with an improved noise mitigation procedure and a more realistic data-driven noise model for simulated events. This deep-learning ROI finder shows promising performance in extracting small signals and gives an efficiency approximately twice that of the traditional algorithm in the low energy region of ~0.03–0.1 MeV. This method offers great potential to explore low-energy physics using LArTPCs.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Development of a deep machine learning interatomic potential for metalloid-containing Pd-Si compounds

Interatomic potentials based on neural-network machine learning (ML) approach to address the long-standing challenge of accuracy versus efficiency in molecular-dynamics simulations have recently attracted a great deal of interest. In this work, utilizing Pd-Si system as a prototype, we extend the development of neural-network ML potentials to compounds exhibiting various types of bonding characteristics. The ML potential is trained by fitting to the energies and forces of both liquid and crystal structures first-principles calculations based on density-functional theory (DFT). We show that the generated ML potential captures the structural features and motifs in Pd 82 Si 18 and Pd 75 Si 25 liquids more accurately than the existing interatomic potential based on embedded-atom method (EAM). The ML potential also describes the solid-liquid interface of these systems very well. Moreover, while the existing EAM potential fails to describe the relative energies of various crystalline structures and predict wrong ground-state structures at Pd 3 Si and Pd 9 Si 2 composition, the developed ML potential predicts correctly the ground-state structures from genetic algorithm search. The efficient ML potential with DFT accuracy from our study will provide a promising scheme for accurate atomistic simulations of structures and dynamics of complex Pd-Si system.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

From Sim to Real: A Pipeline for Training and Deploying Traffic Smoothing Cruise Controllers

Designing and validating controllers for connected and automated vehicles to enhance traffic flow presents significant challenges, from the complexity of replicating real-world stop-and-go traffic dynamics in simulation, to the intricacies involved in transitioning from simulation to actual deployment. In this work, we present a full pipeline from data collection to controller deployment. Specifically, we collect 772 km of driving data from the I-24 in Tennessee, and use it to build a one-lane simulator, placing simulated vehicles behind real-world trajectories. Using policy-gradient methods with an asymmetric critic, we improve fuel efficiency by over 10% when simulating congested scenarios. Our comprehensive approach includes reinforcement learning for controller training, software verification, hardware validation and setup, and navigating various sim-to-real challenges. Furthermore, we analyze the controller's behavior and wave-smoothing properties, and deploy it on four Toyota Rav4’s in a real-world validation experiment on the I-24. Lastly, we release the driving dataset, the simulator and the trained controller, to enable future benchmarking and controller design.

42 ENGINEERING↗